Group Relative Policy Optimization (GRPO) and its variants, originally developed for Large Language Models (LLMs), have recently been applied to Multimodal LLMs and produced strong results. However, their coarse-grained holistic credit assignment from a single scalar advantage underfits vision-language (VL) tasks, where outputs are often long-form responses grounded in semantically rich images. To address this limitation, we exploit a structured signal that single-scalar formulations discard: the natural segmentation of long-form VL outputs. Concretely, we propose Segment-Decomposed GRPO (SD-GRPO), which z-normalizes verifiable per-segment rewards across the rollout group, yielding a vector of per-segment advantages in place of a single scalar. We evaluate SD-GRPO across three settings spanning controlled and real-world long-form VL generation, organized by increasing semantic entanglement across segments. On a controlled multi-panel dense-captioning task constructed from DOCCI, where segments are semantically independent, SD-GRPO consistently outperforms the GRPO baseline, with larger gains at higher segment counts. Extending to a controlled multi-chart long-form VQA task constructed from MultiChartQA, we show both theoretically and empirically that rollout-level rewards suffer from cross-segment credit misattribution that scales with output length. On a real-world scientific figure captioning task on the MMSci dataset, where subfigure captions share context across the figure, blending holistic and per-segment rewards further improves on both, suggesting per-segment normalization alone is insufficient when segments are semantically entangled. Finally, by integrating SD-GRPO into Dr. GRPO, we confirm that it can be applied to any GRPO framework with minimal implementation overhead to enhance long-form VL generation.

Coastline detection in remote sensing imagery is commonly formulated as a pixel-wise segmentation problem, where the final coastline is extracted from a predicted mask through post-processing. This formulation relegates coastline geometry, the primary representation used in coastal change analysis, to a secondary artifact rather than the learning objective. In practice, coastlines are defined by geomorphic proxies such as vegetation lines, dune toes, or cliff edges, rather than an instantaneous land-water boundary often used in pixel-based segmentation approaches. In this work, we revisit coastline extraction from a representation perspective and formulate the task as geometric boundary localization. We use the New Zealand Coastal Change Dataset (NZCCD) and high-resolution aerial imagery from Land Information New Zealand (LINZ) to develop CoastlineVLM-7B, a vision-language model (VLM) built on the GeoChat-7B/LLaVA-1.5 architecture that jointly performs coastline presence detection, proxy-type classification, and coastline grounding. The model directly predicts a coastline as a polyline rather than a dense segmentation mask. We evaluate CoastlineVLM-7B against segmentation baselines under strict one-pixel boundary supervision. Results show that geometry-based metrics are more suitable for assessing coastline localization quality than pixel-overlap metrics such as Intersection over Union (IoU). CoastlineVLM-7B improves global geometric alignment with reference coastlines, reducing Hausdorff distance from 37.74 m to 31.84 m and Earth Mover's Distance from 21.12 m to 17.32 m. These results indicate that output representation is a critical design choice in coastline extraction, and that geometry-oriented learning, combined with the semantic reasoning capabilities of vision-language models, aligns well with how coastlines are defined and evaluated in operational coastal monitoring.

Graphical User Interfaces (GUIs) serve as the dominant medium for human-computer interaction, yet building GUI agents that generalize across the vast diversity of real-world interface environments, with the same flexibility and robustness that humans naturally exhibit, remains unsolved. Notably, GUI data are inherently non-stationary: the continual emergence of previously unseen interface instances (e.g., novel domains and resolutions) induces persistent distribution shifts, significantly impeding the continual learning of existing GUI agents. Reinforcement fine-tuning (RFT) has attracted considerable attention as a promising approach. Nevertheless, RFT exhibits pronounced instability in its grounding capability, manifested as sharp reward discontinuities and high-variance oscillations. The imbalanced distribution of rollout outcomes introduces substantial noise into advantage estimation, leading to policy overconfidence. The fixed clipping bound suppresses the increase in policy probabilities needed to adapt to new distributions, leading to a collapse in exploration capacity. To address these challenges, we propose GUI-AC, a method that enhances the continual learning capability of GUI agents. GUI-AC introduces grounding certainty to support two core mechanisms: (i) Adaptive Advantage, which down-weights noisy advantage estimates to prevent policy overconfidence; and (ii) Dynamic Clipping, which relaxes the clipping bound to encourage exploration range. Extensive experiments show that these mechanisms jointly improve performance, enabling our method to surpass state-of-the-art baselines. Code is available anonymously at https://anonymous.4open.science/r/GUI-AC.

Audio-visual captioning generates natural language descriptions from video and audio content. Multimodal LLMs have advanced this task, but both modalities contribute many tokens to the LLM input, where prefill self-attention scales quadratically. Existing token-pruning methods usually retain tokens by attention, saliency, or cross-entropy loss, yet the hard threshold selection makes it difficult to retain tokens that are truly valuable, especially for high-confusing tokens near the decision boundary. To this end, we propose a AVEX-Prune, an RL-based audio-visual dynamic token pruning method in this work. In our AVEX-Prune, an audio-visual token exchange strategy is proposed to select truly valuable tokens by replacing low-confidence retained tokens with high-confidence candidate tokens from the same or the other modality, and measuring the differences in caption generation from token swaps. AVEX-Prune preserves full-token quality at a 40% retention ratio on both VILA 1.5-8B (54.5 vs. 54.6) and VideoLLaMA 2 (57.0 vs. 56.8).

We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures, enabling lossless 256K context processing while capturing critical frames and long-range temporal dependencies. This architecture is underpinned by a highly optimized training and inference infrastructure, including scalable video I/O, heterogeneous ViT-LM parallelism, and custom DSA kernels that significantly maximize throughput and minimize computational overhead. Furthermore, to overcome the algorithmic dilemma of catastrophic forgetting during multi-task alignment, we introduce Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL. By distilling dense token-level teacher feedback from on-policy rollouts back into the MoE backbone, which activates only 3B parameters, Keye-VL-2.0 natively empowers advanced agent collaboration across Code, Tool, and Search scenarios with multimodal self-correction. Extensive evaluations across video understanding, temporal grounding, reasoning, STEM, and agent benchmarks demonstrate that Keye-VL-2.0-30B-A3B achieves state-of-the-art performance among models of similar scale, particularly excelling in fine-grained temporal localization on TimeLens and long-video comprehension on Video-MME-v2 and LongVideoBench. We release our model checkpoints to accelerate community progress toward scalable and robust multimodal agentic applications.

RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery. However, existing models support only a narrow range of sensor types and tasks, yielding a fragmented view of the earth and leaving cross-modal geoscientific knowledge largely unexploited. This work presents Earth-OneVision, a 2B RS-MLLM that unifies six sensor modalities (i.e., optical, SAR, infrared, multispectral, temporal, and video) and cross-sensor fusion across 9 task categories within a single autoregressive framework. Three dedicated mechanisms address three bottlenecks. Full-Granularity Vision-Language Alignment (FGVLA) aligns multi-level visual features with the multi-dimensional language space. Spatial-Linguistic Isomorphic Serialization (SLIS) unifies heterogeneous spatial outputs as autoregressive tokens. Progressive Cross-Modality Adaptation (PCMA) decomposes the compound domain gap into sequential stages, tackling the viewpoint and imaging physics gaps in turn. To support joint training, MMRS-OneVision is constructed with ~34M QA pairs spanning all six sensor modalities and cross-sensor fusion across 9 task categories, substantially exceeding existing RS multimodal instruction datasets. With only 2B parameters, Earth-OneVision achieves competitive or state-of-the-art results across extensive benchmarks, consistently matching or outperforming 4B-72B RS-MLLMs. It achieves 87.52% P@0.5 on the OPT-RSVG testset for optical visual grounding and 80.68% on the SAR VQA benchmark SARLANG-Bench, exceeding 7B models by over 7%. It further achieves 75.74% recall on the BigEarthNet-MS testset for multispectral classification, and 81.94% MCQ accuracy on EarthMind-Bench for cross-modality reasoning.

Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. While recent CIL advances have spurred significant interest across various modalities, the audio-visual setting remains underexplored. Furthermore, although foundational multimodal models like SAM-Audio encapsulate rich static priors, our empirical analysis reveals that these representations struggle in incremental settings. This work bridges this gap by integrating SAM-Audio's audio-visual priors into the CIL setting. Specifically, we leverage its dense audio and visual representations and employ a novel guided attention strategy where the audio features contextually guide the visual representations. To further mitigate catastrophic forgetting, we introduce dual-level distillation objectives at both the feature and logit levels. Extensive evaluations on audio-visual CIL benchmarks demonstrate that our approach consistently outperforms state-of-the-art methods.

Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news feature takes a newsroom team weeks: hunting for context, running statistics, choosing an angle, and designing visuals. Recent agents handle individual steps well: data-science agents close the analysis loop, while design agents synthesize beautiful websites. But can an agent serve as a data journalist end to end? We introduce Data Journalist Agent (Data2Story), a multi-agent framework that orchestrates specialized roles into a single virtual newsroom. Data2Story contributes two innovations. (i) Claims are evidence-grounded: an Inspector links every number, angle, and asset back to data, code, or an external reference. (ii) Articles are multimodally generative: rather than defaulting to plain text and static charts, Data2Story reasons about what readers will want to see, then deploys multimodal tools, such as interactive maps for geography and audio for music. We evaluate Data2Story on 18 articles, each paired with the originally published expert piece, along four axes: (a) human-agent angle coverage; (b) rubric evaluation with 53 participants across five dimensions; (c) computer-use agents as judges, a cost-saving proxy for how readers navigate interactive articles; and (d) verifiability, where a coding verifier re-executes statements against the data and checks claims against references. Data2Story produces competitive, evidence-traceable multimedia stories, with particular strength in transparency and auditability. Human articles retain an edge in editorial angle, creative design, and presentation. We position Data2Story as a collaborator for journalists, enabling more evidence-based, transparent, and verifiable reporting. Code and demos are available at https://data2story.github.io.

This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework. ARM is built on three efforts: first, we train a discrete semantic visual tokenizer that maps images into compact token sequences. Our tokenizer is supervised with multiple objectives that jointly promote semantic discriminability, language alignment and faithful reconstruction, thereby supporting diverse tasks in a shared latent space. With this, we train a 7B autoregressive model over large-scale text and image token sequences, seamlessly developing vision-language perception and generation capabilities. Finally, to further improve preference-aligned behavior for text-to-image generation and instruction-guided editing, ARM applies reinforcement learning (RL) to optimize task-level objectives such as visual quality, instruction adherence, and edit consistency. Surprisingly, the results show that RL not only substantially improves performance on the target tasks (e.g., raising WISE overall from 0.50 to 0.56, GEdit-Bench-EN G_O from 5.75 to 6.68), but also induces cross-task synergy between text-to-image generation and editing. Collectively, these findings highlight autoregressive modeling, when paired with strong representations and preference optimization, as a scalable foundation for multimodal intelligence. Code: https://github.com/wdrink/ARM.

Multimodal Large Language Models (MLLMs) can listen and see, but how do audio and visual signals actually travel through the network to shape an answer? Despite their growing role in research and real-world applications, the internal pathways through which audio and visual tokens influence the final prediction remain poorly understood. In this study, we examine audio-visual information flow inside Audio-Visual Large Language Models (AVLLMs), tracing how AVLLMs route, utilize, and integrate audio and visual information across two input configurations, audio-visual video and multiple interleaved audio-visual items. We find that for audio-visual video, AVLLMs follow the sequential information flow pathway established for VLMs and VideoLLMs, with audio and visual contribution flowing along this pathway in proportion to the task's reliance on each modality. In settings with multiple interleaved audio-visual items, this routing shifts to different parallel streams. Furthermore, we demonstrate that audio-visual and other token types can be discarded once their information is transferred to LLM, with minimal impact on the model's prediction or even slight improvement, generalizing across multiple tasks and datasets, enabling more efficient inference. These findings hold across multiple models and scales, Qwen2.5-Omni and Video-SALMONN2 Plus at 3B and 7B scales, leading to hypotheses on why these flow structures emerge. Together, these results deliver the first coherent picture of how AVLLMs orchestrate sound and sight inside the network and lay the groundwork for the next wave of interpretability, design, and efficiency advances in audio-visual and broader MLLMs.

Vision-language models (VLMs) are increasingly deployed where answers must follow from what is in the image, yet they often answer from textual priors, the question's phrasing together with memorized world knowledge, rather than from the image itself, which inflates benchmark scores and yields confident but ungrounded answers. Existing benchmarks rarely isolate this behavior, since each image is usually paired with a single fixed question. To measure the reliance, we build a 540-image benchmark across six reasoning categories and generate four question variants over the same images, so that phrasing rather than image content is the controlled variable. The hardest variant is written directly from the image to minimize text leakage. We benchmark eleven VLMs spanning small open-weight models to large closed-source systems: every model degrades on the hardest variant, and open models fall furthest. Our central diagnostic is a no-image ablation, which collapses the open-weight models to their text-only floor (1 to 9 percent). Three further analyses, LLM-rated difficulty, low base-to-final textual similarity, and human re-annotation, corroborate genuine image-dependence. In-context exemplars that match how a variant was built recover the most accuracy, and GRPO post-training of a small VLM yields consistent gains across all four variants that transfer to a held-out out-of-distribution set. Textual-prior reliance is measurable and partly trainable away.

Multimodal Large Language Models (MLLMs) excel at utilizing digital APIs and increasingly serve as the "brain" of embodied AI, instructing robots to interact with the physical world. In such embodied settings, a central capability is the use of physical tools, which underpins MLLMs' ability to assist humans in real-world tasks. Despite the importance, MLLMs' proficiency in physical tool use remains largely unexplored. To address this gap, we introduce PhysTool-Bench, the first physical tool-use benchmark designed to evaluate MLLMs' ability to comprehend real-world scenarios, identify physical tools, and plan their use. PhysTool-Bench comprises 2,510 queries over 2,678 real-world physical tools spanning diverse domains, including manufacturing, electrical work, agriculture, and healthcare. Concretely, models are evaluated along two primary dimensions: 1) recognizing all physical tools present in the scene, and 2) planning the tool selection and use sequence based on the instruction and visual context. Across 13 leading MLLMs, even the strongest model (Gemini-3.1-Pro) identifies only 58.7% of tools in a scene and completes merely 21.0% of queries end-to-end. Our analysis reveals a two-level deficit: MLLMs struggle to perceive tools in realistic scenes, and the much larger drop at the planning stage further indicates a lack of functional commonsense for mapping perceived tools onto task semantics, pinpointing a critical bottleneck for the development of practical embodied AI.

Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments. However, existing critics suffer from two key limitations: they (1) focus primarily on short-sighted decision loops (e.g., forgetting earlier actions) and (2) lack the visual grounding needed to detect flawed actions (e.g., clicking wrong UI elements). To address these, we introduce HiViG, a History-aware Visually Grounded test-time framework, built around a multimodal critic trained on real GUI trajectories to abstract past interactions into a compact record and to evaluate actions with visual grounding. At test time, HiViG integrates the critic into the policy decision loop to provide macro-action history, which summarizes the policy's completed achievements, and visually grounded critique, which verifies raw execution coordinates against the current screenshot to intercept errors before execution. Across web, mobile, and desktop benchmarks, HiViG consistently outperforms existing scalar and verbal critics, improving average success rates over the strongest baseline by 5.8% for Qwen3-VL-32B and 9.0% for Gemini-3-Flash, and demonstrates strong cross-platform generalization. Ablations show that macro-action history mitigates short-sighted planning and visually grounded critique reduces execution errors, with both components being critical for test-time scaling in long-horizon GUI tasks.

In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models (MLLMs). To better align vision encoders with the autoregressive nature of LLMs, GenLIP trains a ViT to predict language tokens directly from visual tokens using a standard language modeling objective, without contrastive batch construction or an additional text decoder. This design offers three key advantages: (1) \textbf{Simplicity}: a single transformer jointly models visual and textual tokens; (2) \textbf{Scalability}: it scales effectively with both data and model size; and (3) \textbf{Performance}: it achieves competitive or superior results across diverse multimodal benchmarks. Trained on 8B samples from Recap-DataComp-1B, GenLIP matches or surpasses strong baselines despite using substantially less pretraining data. After continued pretraining on multi-resolution images at native aspect ratios, GenLIP further improves on detail-sensitive tasks such as OCR and chart understanding, making it a strong foundation for vision encoders in MLLMs.

Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To address this, we introduce ChartAgent, a novel agentic framework that explicitly performs visual reasoning directly within the chart's spatial domain. Unlike textual chain-of-thought reasoning, ChartAgent iteratively decomposes queries into visual subtasks and actively manipulates and interacts with chart images through specialized actions such as drawing annotations, cropping regions (e.g., segmenting pie slices, isolating bars), and localizing axes, using a library of chart-specific vision tools to fulfill each subtask. This iterative reasoning process closely mirrors human cognitive strategies for chart comprehension. ChartAgent achieves state-of-the-art accuracy on the ChartBench and ChartX benchmarks, surpassing prior methods by up to 16.07% absolute gain overall and 17.31% on unannotated, numerically intensive queries. Furthermore, our analyses show that ChartAgent is (a) effective across diverse chart types, (b) achieves the highest scores across varying visual and reasoning complexity levels, and (c) serves as a plug-and-play framework that boosts performance across diverse underlying LLMs. Our work is among the first to demonstrate visually grounded reasoning for chart understanding using tool-augmented multimodal agents.

Recent learning-based path planners use neural networks to process visual map representations and approximate heuristics for classical search algorithms, yielding near-optimal paths with reduced search effort. However, these methods are tied to the shortest-path objective implicit in their supervision, which limits their flexibility to accommodate alternative criteria. We introduce FlexPath, a two-stage framework that decouples feasibility from preference. In Stage 1, we use imitation learning to acquire a task-independent spatial prior over feasible paths from visual map inputs. In Stage 2, differentiable Path Shape Objectives (PSOs) adapt this prior toward task-specific criteria without relearning path structure, requiring only efficient objective-level adaptation. A single pretrained model can be adapted to multiple objectives. For shortest-path planning, FlexPath reduces search effort on TMP by 14.3% compared to the state-of-the-art TransPath, while also finding lower-cost paths on average and demonstrating strong zero-shot generalization across three unseen domains. For obstacle clearance with minimum clearance distance 2, it achieves 96.8% full obstacle avoidance while maintaining low search cost. The framework further extends to semantic-aware avoidance and waypoint guidance via objective-level adaptation, and remains compatible with classical planners at inference time. Data and code are available at https://github.com/FraunhoferIVI/FlexPath.

Learning high-quality latent actions from large-scale unlabeled videos, coupled with limited real-world interaction data for training an action decoder, has emerged as a promising paradigm for scalable latent policy learning. However, existing approaches typically rely on behavior cloning, which tends to collapse inherently multimodal action distributions into unimodal ones, thereby degrading the pretrained latent action structure. While flow matching provides a potential alternative, directly applying it leads to a misalignment between latent actions and physical actions during action decoder training, due to the stochastic nature of the learned policy. To address these, we propose Latent Action Flow Policy (LAFP), which leverages flow matching for latent policy learning and introduces an inference-time interpolation mechanism to mitigate stochasticity-induced misalignment. Experimental results demonstrate that LAFP consistently outperforms prior methods on downstream imitation learning tasks, achieving up to 10-15% improvement in success rate while incurring less than 1x additional inference overhead.

Reconstructing dynamic and interactive 3D scenes from real-world observations remains a fundamental challenge in computer vision and robotics. While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstruction, extending it to interactive environments with articulated robots and manipulable objects remains difficult due to complex contact interactions and abrupt pose changes. To address these challenges, we introduce ManiSplat, a unified framework that reconstructs controllable and decoupled Gaussian digital twins directly from monocular ego-view robotic videos. Our method introduces a Graph-Structured Disentangled Representation that separates the robot, objects, and background into independently optimizable Gaussian subfields organized within a scene graph. To ensure stability, we propose a Task-Oriented Spatio-Temporal Alignment module that leverages the inherent logic of manipulation tasks-alternating between Motion and Skill phases-to construct accurate pseudo-ground-truth trajectories. Finally, a joint photometric-geometric optimization ensures the reconstructed scenes are temporally coherent, physically consistent, and simulation-ready. Extensive experiments demonstrate that our approach reconstructs interaction-driven dynamic scenes with high fidelity and controllability, effectively supporting downstream robotic tasks and policy learning.

Forecasting the future evolution of dynamic scenes is crucial in autonomous driving. However, existing feed-forward paradigms are primarily designed for interpolation. When extended to future extrapolation, they suffer from ghosting artifacts under large displacements and are constrained by simplified motion assumptions or strict future priors. To overcome these challenges, we propose Envision4D, a fully self-supervised feed-forward framework for pose-free future extrapolation. Specifically, we introduce a Future Pose Prediction module that infers future camera parameters via an iterative denoising process. Furthermore, to capture non-linear dynamics, we propose In-layer Temporal Attention and employ Conditioned Motion Lifting, which transforms the highly uncertain extrapolation process into robust relational mappings. Finally, a Progressive Training Strategy is utilized to stabilize unsupervised motion learning against error accumulation. Extensive experiments demonstrate that Envision4D achieves state-of-the-art performance, significantly outperforming existing methods in future view synthesis.

Real-time inference of vision-language-action (VLA) models is essential for robotic control. While visual token pruning has shown strong potential for accelerating inference, most existing methods mainly base pruning decisions on shallow-layer cues and risk discarding visual information required by deep layers. To address this issue, we propose SAFE-Pruner, a plug-and-play pruning framework that incorporates attention cues of future layers into pruning decisions. Specifically, we identify semantic attention consistency, the tendency that VLA models concentrate their attention probability mass on the same semantic entity across execution steps. Based on this observation, we design a forward-looking strategy to forecast the token saliency in deep layers, which prevents the premature removal of critical tokens and leads to more stable acceleration. We further introduce an adaptive subtask division strategy to detect abrupt attention shifts, thereby improving forecasting accuracy and pruning reliability. Extensive experiments in simulation and real-world settings demonstrate that our method achieves up to 1.89x speedup with a minimal degradation in success rate of less than 1.7%, while outperforming state-of-the-art methods by up to 1.9%.

We present GHOST, a framework for learning visuomotor manipulation policies that generalize beyond the training distribution. GHOST factorizes control into (i) a high-level policy that predicts the next sub-goal as a distribution over 3D end-effector poses from multi-view RGB-D observations, and (ii) a low-level goal-conditioned controller that executes embodiment-specific actions. To condition image-based policies on 3D goals, we introduce a simple spatial interface that projects predicted goals into the image plane and represents them as end-effector heatmaps. Across a suite of manipulation tasks, this hierarchical factorization consistently improves performance and robustness compared to a flat Diffusion Policy. Further, we show that this hierarchical interface also makes it easy to incorporate human demonstrations without relying on (noisy) action retargeting. As sub-goals are largely embodiment-agnostic, we train the high-level policy on human video to specify how learned skills should be applied and composed, while keeping the low-level policy trained purely on robot data. This hierarchy enables adaptation to novel objects and task variations using a small number of human demonstrations.

Language-agent "memory palace" systems anchor each memory to a world coordinate, on the intuition that geometry adds something text cannot. We make that intuition testable and report three results. First, the memory-palace default of folding spatial proximity into a linear blend beside recency and importance does not help and can hurt: in a pre-registered recall experiment the shipped blend fails its own frozen test (mean Delta-Hit@5 -0.0375, Wilcoxon p=0.306), sitting at a position-blind baseline, while a geometry-led weighting wins decisively (+0.3208, p<10^-15): geometry must lead recall when the query regime is spatial. Second, memory recall and visibility must be separated: recall is occlusion-blind by design (you correctly remember the next room behind a wall), while visibility is a perception predicate over stored geometry that the live system never computed. A one-line ray-versus-voxel digital differential analyzer (DDA), re-pointed from the gaze ray the agent already casts, supplies it: text and the live FoV cone both score 0.000 on 849 behind-wall targets while cone-plus-DDA reaches 0.982 (exact McNemar p<10^-6); coordinate recall separately resolves near-duplicate locations a cosine null cannot (1.000 vs 0.533, n=150). Third, the visibility predicate is confirmed live under a git-committed pre-registration (SPMEM-OCC-LIVE-v1: eight scripted worlds, automated oracle scoring, 96 behind-wall targets, false-visible 1.000->0.000, pooled exact McNemar p=2.5x10^-29), a run that surfaced and fixed a real relay anchor defect. We concede that occlusion-needs-geometry is near-tautological; the contribution is the measurement and isolation, separating what spatial memory must store from how it is read. These pilots power a frozen confirmatory study (SPMEM-ZERO-REAL-PREREG-v1); the full human-authored multi-world study with blind raters remains future work.

Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots. A common remedy is to fine-tune these models on robot-specific demonstrations. However, robot data collection can be prohibitively expensive and time-consuming, which is particularly acute in dexterous manipulation, e.g., teleoperating a multi-fingered hand for even a single atomic task can take days. To address this, we introduce Dexterous Point Policy, a framework that learns dexterous manipulation policies directly from human videos and requires no robot demonstrations. Our core insight is that a unified 3D keypoint representation can bridge human and robot embodiments when used for both observations and actions. Specifically, we extract 3D keypoints of task-relevant objects and human hands from raw videos, and train an autoregressive transformer over these keypoints. We observe that at the keypoint level, specifically the wrist and fingertips, human and robot behaviors closely align, enabling direct policy transfer. On a suite of real-robot tasks spanning pick-and-place and tool use, Dexterous Point Policy attains 75.0% success, whereas a state-of-the-art VLA baseline reaches only 1.0%. Furthermore, our method generalizes strongly to unseen scenarios, including multi-object environments and novel object categories.

Real-world robotic manipulation tasks often involve forceful interactions with the environment, such as using tools of varying weights, transporting objects with different masses, and performing contact-rich tasks like table wiping. Previous learning-based approaches typically employ imitation learning policies that output target end-effector poses tracked by low-level impedance controllers. In these systems, forceful interactions are either implicitly realized through steady-state tracking errors or explicitly commanded using wrist force/torque or tactile sensors. However, implicit approaches generalize poorly across object weights, while explicit approaches require specialized hardware and increase system complexity. In this work, we propose IMPACT, a framework that decouples these forceful tasks into task-planning and internal-model-based predictive control. Extensive simulation and real-world experiments demonstrate that the proposed framework achieves higher success rates and improved generalization to unseen object weights, as well as better safety and energy efficiency.

Spatial perception and reasoning are crucial for Vision-Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture critical geometric cues. Experimental results on the simulation benchmarks and real-world tasks demonstrate that QDepth-VLA yields strong spatial reasoning and competitive performance on manipulation tasks.

Understanding hand-object interaction (HOI) is fundamental to computer vision, robotics, and AR/VR. However, conventional hand videos often lack essential physical information such as contact forces and motion signals, and are prone to frequent occlusions. To address the challenges, we present Glove2Hand, a framework that translates multi-modal sensing glove HOI videos into photorealistic bare hands, while faithfully preserving the underlying physical interaction dynamics. We introduce a novel 3D Gaussian hand model that ensures temporal rendering consistency. The rendered hand is seamlessly integrated into the scene using a diffusion-based hand restorer, which effectively handles complex hand-object interactions and non-rigid deformations. Leveraging Glove2Hand, we create HandSense, the first multi-modal HOI dataset featuring glove-to-hand videos with synchronized tactile and IMU signals. We demonstrate that HandSense significantly enhances downstream bare-hand applications, including video-based contact estimation and hand tracking under severe occlusion.

Scalable embodied intelligence is constrained by the scarcity of diverse, long-horizon robotic manipulation data. Existing video world models in this domain are limited to synthesizing short clips of simple actions and often rely on manually defined trajectories. To this end, we introduce MIND-V, a cognitive hierarchical world model designed to synthesize physically plausible and logically coherent videos of long-horizon robotic manipulation. Inspired by cognitive science, MIND-V bridges high-level reasoning with pixel-level synthesis through three core components: a Semantic Reasoning Hub (SRH) that leverages a pre-trained vision-language model for task planning; a Behavioral Semantic Bridge (BSB) that translates abstract instructions into domain-invariant representations; and a Motor Video Generator (MVG) for conditional video rendering. MIND-V employs Staged Visual Future Rollouts, a test-time optimization strategy to enhance long-horizon robustness. To enforce adherence to physical laws, we introduce a GRPO reinforcement learning post-training phase guided by a novel Physical Foresight Coherence (PFC) reward. PFC leverages the V-JEPA2 world model as a physics referee to penalize implausible dynamics in the latent feature space. Experiments confirm MIND-V's SOTA performance in long-horizon simulation and its significant value for policy learning, introducing a scalable and fully autonomous framework for embodied data synthesis.

Current cross-view localization methods predominantly rely on satellite imagery as the aerial modality. Although recent work explores planimetric maps (e.g., OpenStreetMap tiles), these approaches often lag in performance. Yet both modalities are widely available and possess complementary properties. Satellite images are closer to ground-level camera imagery, offering finer detail, whereas planimetric maps contain annotated objects (e.g., streetlamps) and remain informative in areas where the ground is occluded, such as by foliage. Despite this, only one prior work provides an end-to-end method to fuse the two modalities, and it does not demonstrate their potential within state-of-the-art methods. To combine the strengths of both modalities, we propose a new fusion module that augments standard encoders and demonstrates that integrating satellite imagery with planimetric maps improves state-of-the-art single-modality methods. The module comprises (i) cross-modal conditioning, which processes each modality's encoding with awareness of the other, and (ii) a patch-level fusion rule that controls the granularity of information exchange. We achieve state-of-the-art results, reducing the mean localization error by 30.13\%. Qualitatively, the fusion adaptively selects the more informative modality, improving overall accuracy.

Illegal logging and timber trade continue to pose significant challenges in the Philippines, where accurate wood species identification is essential for enforcement but limited by the need for specialised equipment and expertise. This study aims to evaluate whether AI models for macroscopic wood identification can be developed and deployed by wood scientists without programming expertise using the Xylorix platform, focusing on five Philippine hardwood species: Mangium (Acacia mangium Willd.), Rain Tree [Samanea saman (Jacq.) Merr.], Banuyo (Wallaceodendron celebicum Koord.), Tindalo [Afzelia rhomboidea (Blanco) Vidal], and Ipil [Intsia bijuga (Colebr.) O. Kuntze]. Binary classifiers were trained on 10,663 verified cross-section images from 260 specimens and evaluated using specimen-level mean scoring to mirror operational field conditions. Area Under the ROC Curve (AUC) values ranged from 0.969 (Ipil) to 1.000 (Mangium), and Average Precision (AP) values ranged from 0.589 (Samanea) to 1.000 (Mangium). Four of five species achieved AA grade (AUC and AP both \geq 0.90); Rain Tree received AE (AUC \geq 0.90, AP < 0.60) due to AP compression from its small positive test set (3 specimens). All five classifiers rank their target specimens above non-target specimens with near-perfect fidelity. Specimen-level error analysis revealed 9 false negatives from Ipil, primarily stemming from localized image artifacts and 3 false positives for Rain Tree and 1 false positive for Tindalo caused by shared tribal-level anatomical traits. These findings demonstrate that Xylorix non-programmers can leverage the Xylorix platform to construct operationally reliable wood identification models suitable for field deployment at supply chain checkpoints.

Human gaze estimation is essential for applications such as human-computer interaction, social robotics, and assistive systems. However, achieving accurate, interpretable, and real-time performance in unconstrained environments remains challenging. Existing appearance-based methods often face trade-offs between spatial robustness, computational efficiency, and effective use of contextual information. To address this, we introduce CapStARE, a capsule-based architecture that combines a frozen ConvNeXt backbone for efficient feature extraction, capsule formation with attention-based routing for structured facial reasoning, and dual GRU decoders for lightweight sequential modeling over short-horizon observation windows. This design preserves interpretable part-whole facial relationships while improving prediction stability through local contextual consistency. Experimental results demonstrate strong performance on ETH-XGaze (3.36) and MPIIFaceGaze (2.65), while also generalizing competitively on Gaze360 (9.06), all with real-time inference (<10 ms). These findings suggest that the proposed method provides a practical and robust framework for appearance-based gaze estimation in real-world interactive environments. The related code and experimental results are publicly available at: https://github.com/toukapy/capsStare

Rotation invariance is a fundamental requirement across many computer vision tasks. Historically, this inductive bias has been encoded through hand-crafted rotation-invariant representations. These are compact, interpretable, and fast to compute, but they come at the cost of descriptive power. More recently, architectures achieve inductive bias through learned representations. These are highly descriptive and achieve strong empirical performance, at the cost of efficiency and interpretability. In this work, we propose an alternative at the intersection of both paradigms. We introduce the selective disk bispectrum (SDB), a complex-valued rotation-invariant vector that preserves all information about the image except its orientation. Our key theoretical contributions are the selective disk bispectrum, its inversion, its (reduced) spatial and computational complexities (compared to the full disk bispectrum), and its expectation and variance under noise. Furthermore, we propose a numerical SDB approximation and provide theoretical guarantees for its accuracy and rotation invariance. Empirically, we validate SDB's invariance and robustness to noise classification tasks. We test our reconstruction algorithm on multi-reference alignment of rotated images.

The integration of spatial and spectral information is beneficial to the improvement of change detection performance. However, existing methods cannot efficiently suppress the influences of spatial and spectral differences in unchanged areas. To address these issues, in this paper we propose a content-guided spatial-spectral integration network (CSI-Net) for the fusion of global spatial details and spectral difference information. Specifically, the proposed CSI-Net is composed of a spatial reasoning (SR) module, a spectral difference (SD) module, and a content-guided integration (CGI) module. In the SR module, the spatial information is learned by cascaded graph convolution blocks for global modeling. The SD module is responsible for the extraction of spectral features, by calculating the means and variances of features to reduce the impact of spectral differences in unchanged regions. In addition, in order to integrate the spatial-spectral features efficiently, we design a CGI module to further take advantage of their complementary information. In this module, high-level content information is introduced as a guide for a proper interaction. Due to the efficient spatial-spectral fusion, the proposed CSI-Net can learn the changed features better while achieving a suppression of spectral differences. Experimental results on LEVIR-CD, WHU-CD, and CLCD datasets demonstrate that the proposed CSI-Net produces better performance compared to state-of-the-art methods, and is applicable to different scenarios

As one of the most destructive natural disasters, earthquakes have struck many countries around the world in recent years, causing serious economic losses. Change detection (CD) can be applied to post-earthquake damage assessment as it can infer destroyed change regions from multi-temporal remote sensing images. Furthermore, the CD with short imaging interval will better satisfy the needs of the emergency rescues after earthquakes. However, the capability of current methods built on deep neural networks is limited because the dataset with short imaging interval is absent. To meet post-disaster immediate relief, we create a CD dataset, Turkey earthquake CD dataset (TUE-CD), for the evaluation of building damage in the short term after an earthquake. Because of the short acquisition interval of the post-event images, the imaging angle is different for different temporal images, which leads to some side-looking problems. To deal with these challenges, we present a multi-scale feature interaction network (MSI-Net) for efficient interaction between bi-temporal features, as well as mitigating the effect of side-looking problems. Specifically, the proposed MSI-Net consists of joint cross-attention (JCA) modules, multi-scale offset calibration (MOC) modules, and feature integration (FeI) modules. The JCA module unifies channel cross-attention and spatial joint attention for sufficient feature interaction. The MOC module further estimates the offsets to align the bi-temporal image with the multi-scale features. Finally, calibrated features and multi-scale features are fused by FeI modules for the prediction of changed areas. Experiments on the WHU-CD, CLCD, and the constructed TUE-CD dataset indicate that the proposed MSI-Net provides better results than considered state-of-the-art CD methods.

Meta AI has recently released the Segment Anything Model (SAM), which demonstrates exceptional zero-shot image segmentation performance across various tasks with remarkable accuracy. Despite its inability to provide accurate segmentation across multiple research fields, SAM still serves as a valuable starting point for supporting the segmentation pipeline process, particularly for tasks that require extensive and senior skills annotations. This study aims to evaluate the generalization of SAM and fine-tuning SAM models using three waste segmentation datasets. Although they are captured from real scenes as SAM was pretrained on, these datasets present several challenges, including occlusions, deformable objects, transparency, and objects easily confused with backgrounds. In our findings, the fine-tuned SAM-ViT-H model outperforms the state-ofthe-art Zerowaste, and TACO datasets with a significant increase of +30 in IoU, and it closely approaches performance levels of TrashCan 1.0, with only a -1.44 difference. After evaluating these popular waste datasets, it became evident that fine-tuning SAM as a foundational model is a crucial step for providing better generalization for downstream waste segmentation tasks. Therefore, SAM should not be disregarded or wasted.

In the production process of network cables, ensuring the correct color sequence of wire pairs inside the standard connector plays a critical role in the final performance of the cable, as any misplacement or color-ordering error can lead to defective products and impose significant costs. Traditional inspection methods based on visual examination through digital microscopes are typically time-consuming, tedious, and prone to human error. In this study, an intelligent system based on the twelfth version of the YOLO1 object detection model was developed to identify the position and verify the correct color sequence of wires in patch cords. The dataset used consisted of 2,500 images captured from microscopic views of network connectors, which were divided into 70% for training, 15% for validation, and 15% for testing. The proposed model, leveraging a single-stage architecture and attention mechanisms during learning, achieved highly accurate wire detection with approximately 98% precision. Additionally, the overall mean accuracy, classification precision, and recall were around 95%, 99%, and 98%, respectively. The results demonstrate that this system can reliably and in real time verify the correctness of wire color sequencing on the production line without the need for human intervention, thereby reducing human error and enhancing efficiency in the manufacturing process.

Remote-sensing and UAV applications need models that generalize across platforms and viewpoints without task-specific training. Yet training-free pipelines often falter on oriented geometry, scale/rotation variation, and crowded ports or airfields, and rarely unify detection and segmentation. We introduce ZODS-RS, a training-free, closed-form pipeline that outputs horizontal boxes (HBB) and instance masks. Built on DINOv3 dense features and SAM-style proposals, ZODS-RS chains: PP (prototype purification via Tyler covariance), R-SEM (rotation-scale equivariant matching with separable kernels and global Hungarian assignment), and UAM (uncertainty-aware pixelwise merging with adaptive priors and optional negative prototypes). A lightweight CWLA fuses multiple DINOv3 layers. On FAIR1M (HBB) we obtain $\mathrm{mAP}_{0.50:0.95}=\mathbf{13.06}$ and $\mathrm{AP}_S=\mathbf{2.93}$ \emph{(class-averaged over ship/airplane)}; on xView (HBB) we report $\mathrm{mAP}=\mathbf{16.69}$. On our UAV dataset, ZODS-RS achieves mask $\mathrm{mIoU}=\mathbf{31.10}$ and improves small-object AP by $\mathbf{+30.70}$ over Grounded-SAM on a single 5090. This work offers a unified, \emph{no-training} solution for horizontal-box detection plus instance segmentation in aerial imagery; provides explicit closed-form formulations for PP/R-SEM/UAM tightly coupled with DINOv3; and demonstrates \emph{consistent} gains on small and crowded targets and under cross-domain shifts while keeping deployment simple.

Camera traps have become a cornerstone of biodiversity monitoring, but the artificial intelligence that turns vast quantities of images into usable ecological data is often locked behind commercial platforms or trained on fauna that does not match that of the British Isles. In an attempt to remove barriers and increase uptake, we release an open-source object detection model for 31 classes, 28 common UK mammal and bird species, plus utility classes for humans, calibration poles, and vehicles, drawn from a curated dataset of 48,165 labelled instances assembled from multiple sites over a decade of operational deployment through Conservation AI and its successor, Trap Tracker. The model, a YOLO26x detector trained and tested on an 80/10/10 class-stratified split, achieves a mean Average Precision of 0.984 at Intersection over Union (IoU) of 0.5 (0.956 at IoU 0.5-0.95) on the held-out validation set, with precision 0.988 and recall 0.965. On an unseen held-out test split, mean per-species confidence ranged from 0.96 to 0.99 across the 31 classes, with a 0.17% false-negative rate concentrated in difficult night-time, distant, or occluded images. These metrics are from data from the same pool of sites and cameras as training, so performance at entirely new sites is left to future work. We release the trained weights in ONNX format under a non-commercial licence, with local desktop and real-time camera support, aimed explicitly at ecologists with no machine-learning experience. This release is a deliberate counterweight to the multiple paid for models that have developed over the last decade.

Pedestrian detection in RGB images is a key task in pedestrian safety, as the most common sensor in autonomous vehicles and advanced driver assistance systems is the RGB camera. Low-light pedestrian detection lacks large public datasets and autolabelling pipelines. This research proposes a solution in the form of an automated infrared-RGB pipeline. The pipeline consists of 1) Infrared detection, where a fine-tuned model for infrared pedestrian detection is used 2) Label transfer process from the infrared detections to their RGB counterparts 3) Training object detection models using the generated labels for low-light RGB pedestrian detection. The research was performed using the KAIST dataset. For evaluation, three object detection models, DETR, YOLO, and RCNN, were trained on generated and ground truth labels. When compared on previously unseen images, the results showed that the models trained on generated labels out-performed the ones trained on ground-truth in 5 out of 6 cases for the mAP@50 and LAMR metrics, and outperformed ground-truth on mAP@50-95 in all cases. Acquired results indicate that the proposed auto-labelling pipeline could be used for scalable annotation of low-light datasets for pedestrian detection. The source code for this research is available on GitHub: https://github.com/BouzoulasDimitrios/IR-RGB-autoamed-low-light-pedestrian-labelling

Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications such as smart glasses and Internet-of-Things devices. We introduce PicoSAM3, a lightweight promptable visual segmentation model optimized for edge and in-sensor execution, including deployment on the Sony IMX500 vision sensor. PicoSAM3 has 1.3M parameters and combines a dense CNN architecture with region of interest prompt encoding, Efficient Channel Attention, and knowledge distillation from SAM2 and SAM3. On COCO and LVIS, PicoSAM3 achieves 65.45% and 64.01% mIoU, respectively, outperforming existing SAM-based and edge-oriented baselines at similar or lower complexity. The INT8 quantized model preserves accuracy with negligible degradation while enabling real-time in-sensor inference at 11.82ms latency on the IMX500, fully complying with its memory and operator constraints. Ablation studies show that distillation from large SAM models yields up to +14.5% mIoU improvement over supervised training and demonstrate that high-quality, spatially flexible promptable segmentation is feasible directly at the sensor level.

We present ABot-Earth 0.5, a generative 3D framework designed to synthesize vast, seamless 3D environments from ubiquitous, geospatially referenced satellite imagery. To achieve this, we propose a novel generative model formulated directly with the 3D Gaussian Splatting (3DGS) representation. The model is trained on a diverse corpus of existing real-world urban reconstructions, learning to generate realistic geometry and textures. At inference, it synthesizes novel 3D scenes conditioned solely on satellite imagery at a scalable rate of under 10 minutes per square kilometer, while demonstrating exceptional realism. The framework is designed for accessibility, with integrated hierarchical level-of-detail (LOD) structures that permit real-time, interactive visualization on web-based map engines. This high-fidelity simulation sandbox effectively mitigates the sim-to-real domain gap, enabling critical downstream Embodied AI applications like closed-loop UAV navigation. By providing an ultra-low-cost and high-efficiency solution, ABot-Earth 0.5 significantly lowers the technical and financial barriers to large-scale 3D reconstruction and empowers the future of global digital earth visualization.

Modern Diffusion Transformers for video generation provide limited control over the progression of time and the editing of temporal dynamics. We propose a temporal-control methodology that extends a pretrained DiT with explicit time editing, allowing control over motion speed and temporal structure without redesigning the backbone. Its core implementation augments the pretrained model with a lightweight temporal module, preserving the original generative prior while expanding its controllable dynamic range.

DiffC provides a principled way to reuse pre-trained diffusion models for lossy compression, but its encoding and decoding procedures remain slow because they require many discretized forward and reverse steps. We study whether few-step generative models -- Rectified Flow, Consistency Trajectory Models (CTM), and MeanFlow -- can be cast as codecs within the same reverse channel coding (RCC) framework. The main challenge is that RCC requires posterior and shared distribution parameters, whereas these models do not explicitly parameterize intermediate conditional distributions. For Rectified Flow and MeanFlow, we use the equivalence between velocity parameterization and diffusion-style denoising parameterization to derive the quantities required by RCC. For CTM, which is distilled from EDM, we adopt the EDM noise parameterization together with local Gaussian approximations of the sender and shared distributions at intermediate states. This yields a proof-of-concept probabilistic formulation that enables compression with pre-trained few-step generative models without retraining. On low-resolution benchmarks, the resulting codecs reduce encoding and decoding time and improve realism in the low-bit-rate regime.

The growing need for high-resolution image generation in autoregressive text-to-image models has resulted in extended token sequences, significantly increasing computational costs and inference times. However, existing state-of-the-art methods for accelerating autoregressive text-to-image models rely on chain-structured draft token sequences, leading to inefficient draft token search and limited acceptance lengths. To address this, we propose parallel-path cross-relaxed speculative Jacobi decoding (\textbf{PathSpec}), a novel framework that enhances efficiency through a multi-sequence draft tree structure. Our parallel-path speculative Jacobi decoding (\textbf{PathExplore}) expands the token search space, achieving a higher speedup ratio without sacrificing image quality. Additionally, we introduce cross-path relaxed verification (\textbf{PathRelax}) that exploits semantic similarities across sequences to further boost token acceptance rates. Evaluated on the Parti-Prompts, MSCOCO2017, and T2ICompBench datasets, our method achieves a speedup ratio of 4.14 $\times$, 3.95$\times$, and 4.18$\times$, respectively. Remarkably, PathExplore, without any relaxed sampling, outperforms relaxed sampling methods in the speedup ratio, such as GSD and LANTERN. Moreover, PathRelax's relaxation mechanism can be seamlessly integrated with other relaxation techniques, enabling further acceleration and providing an efficient solution for real-time text-to-image generation. Our code is available at https://github.com/Haodong-Lei-Ray/PathSpec.

Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model. However, existing LoRA merging techniques often suffer from severe parameter interference, causing destructive collisions in the shared parameter space. To address this, we propose Subspace Signal Routing (SSR), which resolves interference by routing internal signals instead of performing parameter-space merge. Specifically, SSR first constructs a unified subspace by concatenating candidate LoRAs along the rank dimension. Next, SSR employs an inverse correlation matrix to decorrelate mixed signals within this space. Finally, a directional guide matrix steers these purified signals into their respective task-specific subspaces. We provide a rigorous theoretical analysis proving that SSR aligns with the Ordinary Least Squares (OLS) solution, thereby ensuring mathematical optimality. We utilize the additivity of sufficient statistics to design a streaming algorithm. This enables on-the-fly updates that significantly reduce memory overhead and computation time. Extensive experiments validate that SSR significantly outperforms state-of-the-art methods while maintaining comparable efficiency. Code is available at https://github.com/nagara214/SSR-Merge.

Although pretrained text-to-image (T2I) generation models can produce high-quality images, they often fail to faithfully reflect the semantic intent of complex prompts due to stochastic noise and inherent model limitations. This issue frequently manifests as the model overlooking specific objects or failing to correctly bind attributes to their corresponding entities, a challenge referred to as semantic alignment. Unlike existing approaches that rely on computationally expensive fine-tuning or labor-intensive layout priors, we propose STEDiff, a training-free method designed to enhance semantic representations directly within the text-embedding space. Specifically, we introduce a method that primarily leverages the [EOT] token to strengthen the relevant semantics of sub-sentences and then replaces the corresponding tokens in the original prompt. Furthermore, a novel semantic enhancement loss is incorporated to enforce spatial constraints, ensuring that the semantics of each entity are precisely mapped to their respective image regions. Extensive quantitative and qualitative evaluations on the T2I-CompBench demonstrate that our method notably improves semantic consistency and generation integrity in complex scenarios.

Autoregressive video generators synthesize long videos by generating successive temporal segments, but their historical KV cache grows with video length. Existing bounded-cache methods reduce this cost with local windows, sink tokens, or compressed memory states, yet they usually assign fixed roles to different parts of the history. We propose FadeMem, a distance-aware KV memory consolidation mechanism that organizes historical KV blocks into a temporal hierarchy under a fixed cache budget. This design is motivated by frequency-dependent temporal decay: fine details decorrelate quickly, while coarse scene structure and identity remain useful over longer horizons. During generation, new history is inserted as fine-grained entries, while older adjacent entries are progressively merged under a power-law temporal allocation schedule, yielding a dense-near, sparse-far memory within one cache. Without architectural changes, FadeMem preserves recent context for short-term dynamics and compact long-range anchors for identity and scene coherence. Experiments show improved subject consistency, background stability, and temporal coherence over existing bounded-cache strategies.

Current identity-consistent video generation methods struggle to preserve appearance fidelity under large viewpoint changes. While introducing multi-view reference input offers a natural solution, progress remains constrained by the lack of effective frameworks for multi-view inputs and the scarcity of multi-view data. We address these challenges by proposing HarmoView, a robust framework for identity-consistent video generation that effectively integrates multi-view cues through three architectural refinements complemented by a staged training curriculum. Specifically, we first introduce Multi-level Feature Injection to anchor identity fidelity; by injecting raw ViT features from frontal references alongside text tokens via cross-attention, MFI provides persistent low-level appearance anchors that complement the high-level identity features within DiT blocks, leading to enhanced identity preservation. Then, we employ learnable proxy tokens to unify heterogeneous reference layouts across single-/multi-view settings while simultaneously resolving the reference-view mismatch problem. Jump-RoPE is further developed for identity-wise feature isolation to reduce identity crosstalk. To activate these structural capabilities while preserving the original generative priors, we propose the Progressive View Curriculum. This four-stage training strategy employs view dropout to facilitate a stable transition from vanilla T2V generation to high-fidelity, identity-persistent spatial reasoning. Furthermore, we construct a large-scale multi-view dataset to address the issue of data scarcity. Extensive evaluation on our multi-view benchmark, comprising 100 manually-curated cases spanning 52 unique identities, demonstrates that HarmoView significantly outperforms open-source baselines and matches leading closed-source engines, achieving state-of-the-art performance in identity-consistent video generation.

To showcase products, merchants often incur substantial costs creating high-quality display images. Foreground Conditioned Outpainting (FCO) meets this demand, allowing users to create desired backgrounds for foreground instances at a low cost by adjusting the text prompt. However, existing text-driven FCO methods exhibit critical flaws in their outputs, most notably the presence of artifacts, which refer to regions in the synthesized background that share the same semantics as the foreground instance. Such artifacts diminish the object's prominence and degrade image quality. We attribute the issue to the misalignment between the given instance and text-derived concept embeddings. To address this, we propose the Customized Concept Embedding Diffusion (CCE-Diffusion) framework. Its core is a CCE-Module to customize concept embeddings, bridging the gap between generic noun semantics and a specific visual instance. An Instance-Aware Loss guides the module's optimization, while a Semantic-Preserving Prompt Template prevents customized embeddings from distorting other words in the prompt. Both qualitative and quantitative evaluations demonstrate that CCE-Diffusion significantly reduces artifacts in the outputs. As a plug-and-play component, the CCE-Module can integrate with various FCO methods, enhancing their performance.

Subject Customization is a foundational task in modern image generation. By providing a few reference images and a text prompt, users can generate images of a specific object in any desired scene. However, existing methods still struggle to achieve effective pose control for customized subjects. In practice, they often exhibit inaccurate poses or inconsistent cross-pose appearances. These limitations suggest that understanding objects in a volumetric manner remains a significant challenge for 2D-native backbones. To address this challenge, we propose Pose-ICL, a tuning-free framework that leverages 3D-aware In-Context Learning (ICL) to directly adapt to new subjects through multiple paired image-pose references. Its core mechanism,Surface-Anchored Position Embedding (SAPE), equips the model with explicit 3D awareness by anchoring image tokens to the surface coordinates of a volumetric bounding box. Dedicated refinements ensure its seamless compatibility with existing DiT models. Extensive evaluations on both 3D assets and real-world subjects demonstrate that Pose-ICL significantly outperforms current methods in both pose accuracy and identity consistency.

Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail. This limitation becomes even more severe after discretization, where missing low-level information is difficult to recover. In fact, we observe that shallow VFM features retain considerably richer local appearance and structural detail, which complements the high-level semantics carried by deep features used in existing RAEs. Motivated by this complementary property, we propose Ideal, an In-depth Alignment framework for discrete representation autoencoding. By jointly aligning quantized tokens with both shallow and deep VFM features, Ideal enables the resulting discrete visual tokens to preserve both visual fidelity and rich semantics. Extensive experiments demonstrate that Ideal yields superior reconstruction performance, achieving 0.61 rFID on ImageNet and outperforming the previous best method by 0.28. When used for autoregressive image generation, Ideal further produces a gFID of 1.89, establishing a new state of the art for autoregressive image generation.

Virtual try-on aims to fit an in-shop clothing image onto a specific human body. An optimal virtual try-on method should provide diverse and flexible dressing options, accurately reflecting the varied wearing styles encountered in real-life scenarios, tailored to individual preferences and fashion aspirations. However, current methods predominantly perform a direct replacement of the original clothing with the target clothing, following the same dressing pattern. This limited control over clothing adaptation may result in fixed and monotonous try-on outputs. To delve into More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On, we propose a novel virtual try-on method, termed MOFA-VTON, which allows adjustment for clothing adaptations in try-on results through simple sketches by users. Specifically, we first design a mask construction strategy that transforms user-drawn curve sketches into a dual-region mask, replacing the traditional clothing-agnostic mask and providing fine-grained layout guidance for the subsequent generation process. Further, we propose layout adjustment blocks that utilize the cross-attention mechanism to independently learn layout correspondences for upper and lower regions of the human body, refining the spatial arrangement of the two regions. With these implementations, our method enables flexible and fine-grained adaptations of target clothing, overcoming the constraints of a fixed layout. Extensive experiments on VITON-HD and DressCode datasets demonstrate that our proposed MOFA-VTON outperforms previous state-of-the-art methods and provides more fashion possibilities for virtual try-on.

Flow Matching models have demonstrated strong performance across a wide range of generative tasks. However, their reliance on ODE-based iterative sampling incurs substantial computational overhead in inference, which limits their applicability in real-time scenes. While distillation is a promising solution, existing approaches largely borrow from diffusion-based score matching, often failing to exploit the intrinsic geometric structure of flows and suffering from training instability, high variance, and degraded generation quality. In this paper, we propose Mean Flow Distillation (MFD), a novel distillation framework tailored for flow matching models. We theoretically demonstrate that MFD acts as a temporal low-pass filter, effectively suppressing the high-frequency optimization noise inherent in variational score distillation (VSD) while ensuring global trajectory consistency. We further prove the Mean Flow Matching Theorem, establishing that matching expected average velocities is sufficient for strict distribution alignment. Empirically, on challenging tasks of high-dimensional manifolds including 4D occupancy forecasting and text-to-image generation, MFD achieves state-of-the-art performance, enabling high-fidelity single-step generation.

Diffusion-based lip synchronization models achieve strong visual quality and audio-visual alignment, but full-sequence bidirectional attention and many denoising steps make them impractical for real-time inference. We present Lip Forcing, to our knowledge the first autoregressive diffusion method for video-to-video (V2V) lip synchronization, which distills a 14B audio-conditioned bidirectional video diffusion teacher into causal students. At inference, the students generate each chunk in only two denoising steps without inference-time CFG, enabling real-time lip synchronization. A lip-sync-specific teacher-trajectory analysis reveals a CFG fidelity-sync tradeoff: no-CFG predictions favor reference fidelity, whereas CFG-guided predictions favor synchronization within a mid-trajectory band. Lip Forcing translates this finding into three analysis-derived components: Sync-Window DMD, a two-step inference schedule, and a SyncNet-based reward. We validate Lip Forcing at two student scales, both distilled from the 14B teacher. The 1.3B student crosses into real-time streaming at 31 FPS, $17.6\times$ faster than its same-scale bidirectional model. The 14B student, the largest diffusion model reported for V2V lip synchronization, runs $39.8\times$ faster than its teacher at comparable reference fidelity. Time-to-first-frame is sub-millisecond at both scales, far below every diffusion baseline.

Autoregressive video generation has emerged as a powerful paradigm for World Action Models (WAMs). However, existing approaches suffer from slow training convergence and limited converged accuracy, particularly at high frame rates, as the training supervision is confined to the current chunk without explicit signals about future dynamics; they also suffer from slow inference due to iterative video denoising. In this paper, we present Next Forcing, a multi-chunk prediction (MCP) framework for causal world modeling that enables faster training, higher accuracy, and accelerated inference. Inspired by multi-token prediction in large language models, Next Forcing introduces an MCP training objective that augments the main model with lightweight auxiliary MCP modules to simultaneously denoise video chunks at multiple future temporal horizons (next$^1$, next$^2$, next$^3$ chunks). These MCP modules form a causal chain across prediction depths, where intermediate features fused from multiple layers of the main model are leveraged to predict future dynamics, allowing near-future predictions to inform farther-future ones and providing dense multi-scale temporal supervision back to the main model. During training, the MCP modules significantly accelerate convergence and improve converged accuracy, especially at high frame rates: at 50 fps, Next Forcing achieves a 93.1% relative improvement over LingBot-VA at 5k training steps and 2.3x faster convergence, and establishes new state-of-the-art results on the RoboTwin benchmark (94.1/93.5% on Clean/Random). At inference, the MCP modules can be retained to predict the next video chunk in parallel with the current one, achieving 2x inference acceleration. Next Forcing also demonstrates significant improvements on PhyWorld, a benchmark evaluating adherence to physical laws in video generation, and over 50% FVD reduction on general video pretraining.

Diffusion-based generative models enable powerful image editing capabilities, but achieving precise control while maintaining fidelity and safety remains challenging. We present a comprehensive theoretical and empirical study of controllable diffusion-based image editing, analyzing the trade-offs between adherence to user intent, preservation of non-target content, and output quality. Our work spans text- and mask-guided edits, point/drag manipulation, and inversion-based pipelines. We derive mathematical formulations of editing objectives and analyze dynamics of noise injection, score guidance, and inversion error. We provide theoretical bounds on reconstruction error, stability under repeated edits, and locality of changes. We propose algorithmic frameworks (with pseudocode) for mask-localized and instruction-guided editing, and present extensive experiments comparing state-of-the-art methods (e.g.\ TF-ICON \cite{lu2023tficone}, DragFlow \cite{zhou2025dragflow}, InstructPix2Pix \cite{brooks2023instructpix2pix}, UltraEdit \cite{zhao2024ultraedit}) on multiple tasks and metrics (FID, identity similarity, CLIP alignment, artifact scores, etc). Our results reveal key failure modes, such as identity drift, prompt sensitivity, and compositional errors. We also discuss ethical considerations in image editing, including misuse risks, bias, consent, and concept erasure techniques (e.g.\ MACE \cite{lu2024mace}, ANT \cite{li2025ant}, EraseAnything \cite{gao2024eraseanything}) as safeguards. We conclude with best practices and future directions for responsible, high-fidelity diffusion-based editing.

Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process. Unfortunately, the high fidelity also comes at a high computational cost due to the inherently sequential generative process. In this work, we seek to optimally balance quality and computational cost, and propose a framework to allow the amount of computation to vary for each prompt, depending on its complexity. Each prompt is automatically routed to the most appropriate text-to-image generation function, which may correspond to a distinct number of denoising steps of a diffusion model, or a disparate, independent text-to-image model. Unlike uniform cost reduction techniques (e.g., distillation, model quantization), our approach achieves the optimal trade-off by learning to reserve expensive choices (e.g., 100+ denoising steps) only for a few complex prompts, and employ more economical choices (e.g., small distilled model) for less sophisticated prompts. We empirically demonstrate on COCO and DiffusionDB that by learning to route to nine already-trained text-to-image models, our approach is able to deliver an average quality that is higher than that achievable by any of these models alone. Code is available at https://github.com/winglicopy/CATImage.

Using diffusion transformers for media generation may require evaluating attention over extremely long sequences, with attention layers accounting for the majority of generation latency. Exploiting sparsity in attention maps offers a promising opportunity to reduce this cost. In this work, we show that attention maps in diffusion transformers exhibit significant fine-grained sparsity in video generation models. Existing sparse attention methods, however, are too coarse-grained, leaving a large fraction of redundant computation unaddressed, or incur high overheads at finer granularity. We propose FG-Attn, a novel, low-overhead fine-grained sparse attention mechanism that skips score computations at the granularity of a MxN tile, where N>=1 and M>=16, and where each block is the result of query-key dot products between M queries and N keys. FG-Attn addresses the key challenge of hardware underutilization in sparse attention kernels on GPUs, without incurring the overheads of irregular memory access and redundant operations. FG-Attn can fully supersede existing sparse attention methods and extend block sparse attention methods to finer granularities on modern GPUs. At 70% sparsity, FG-Attn is up to 2.45X faster than the state-of-art FlashInfer, and reduces attention kernel time by 14.7% on average. FG-Attn speeds up end-to-end video generation times by up to 1.40X (1.18X on average) over Flash Attention 3.

High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geometry problem solving that employ formal languages and symbolic solvers for enhanced correctness and interpretability, we propose GeoLoom, a novel framework for text-to-diagram generation in geometric domains. GeoLoom comprises two core components: an autoformalization module that translates natural language into a specifically designed generation-oriented formal language GeoLingua, and a coordinate solver that maps formal constraints to precise coordinates using the efficient Monte Carlo optimization. To support this framework, we introduce GeoNF, a dataset aligning natural language geometric descriptions with formal GeoLingua descriptions. We further propose a constraint-based evaluation metric that quantifies structural deviation, offering mathematically grounded supervision for iterative refinement. Empirical results demonstrate that GeoLoom significantly outperforms state-of-the-art baselines in structural fidelity, providing a principled foundation for interpretable and scalable diagram generation.

Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distinguish and generate the correct subject when inputs contain multiple candidates. This limitation restricts effectiveness in complex, realistic visual settings. We propose Scone, a unified understanding-generation method that integrates composition and distinction. Scone enables the understanding expert to act as a semantic bridge, conveying semantic information and guiding the generation expert to preserve subject identity while minimizing interference. A two-stage training scheme first learns composition, then enhances distinction through semantic alignment and attention-based masking. We also introduce SconeEval, a benchmark for evaluating both composition and distinction across diverse scenarios. Experiments demonstrate that Scone outperforms existing open-source models in composition and distinction tasks on two benchmarks. Our model, benchmark, and training data are available at: https://github.com/Ryann-Ran/Scone.

This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key ingredients. 1) We use a Dual Action Representation to enable robust action control in response to the user's keyboard and mouse inputs. 2) To enforce long-term consistency, our Reconstituted Context Memory dynamically rebuilds context from past frames and uses temporal reframing to keep geometrically important but long-past frames accessible, effectively alleviating memory attenuation. 3) We also propose Context Forcing, a novel distillation method designed for memory-aware model. Aligning memory context between the teacher and student preserves the student's capacity to use long-range information, enabling real-time speeds while preventing error drift. Taken together, WorldPlay generates long-horizon streaming 720p video at 24 FPS with superior consistency, comparing favorably with existing techniques and showing strong generalization across diverse scenes. Project page and online demo can be found: https://3d-models.hunyuan.tencent.com/world/ and https://3d.hunyuan.tencent.com/sceneTo3D.

Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information flow between text tokens and visual latents throughout denoising. In this setting, we observe a prompt forgetting phenomenon: the semantics of the prompt representation in the text branch is progressively forgotten as depth increases. We further verify this effect on three representative MMDiTs--SD3, SD3.5, and FLUX.1 by probing linguistic attributes of the representations over the layers in the text branch. Motivated by these findings, we introduce a training-free approach, prompt reinjection, which reinjects prompt representations from early layers into later layers to alleviate this forgetting. Experiments on GenEval, DPG, and T2I-CompBench++ show consistent gains in instruction-following capability, along with improvements on metrics capturing preference, aesthetics, and overall text--image generation quality.

Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions specified in the prompt. Representation-alignment objectives such as VideoREPA and MoAlign improve fine-grained text following by distilling spatio-temporal token relations from a frozen visual foundation model, but their pairwise supervision budget is allocated by visual or motion cues rather than by how relevant each pair is to the prompt. We present SARA, Semantically Adaptive Relational Alignment, which keeps token-relation distillation (TRD) on a frozen VFM target and adds a text-conditioned saliency that decides which token pairs carry supervision. A lightweight Stage~1 aligner is trained with per-entity SAM~3.1 mask supervision and an InfoNCE regulariser, and its continuous saliency is fused into TRD through a pair-routing operator that assigns each token pair a weight whenever either of its two endpoints is salient, thereby routing supervision toward subject-subject and subject-background pairs and away from background-background ones. In the Wan2.2 continual-training setting, SARA improves both text alignment and motion quality over SFT, VideoREPA, and MoAlign on a 13-dimension VLM rubric, on the public VBench benchmarks, and in a blind user study. Project page: https://saradit.github.io/.

Existing video generation frameworks treat sequence duration as an externally prescribed parameter -- fixed frame counts or text prompts -- producing clips whose temporal boundaries are decoupled from the statistical structure of real behavioral data. This assumption is fundamentally misaligned with biological behavior, where action duration varies naturally across individuals and instances and is encoded in the data itself. We present BioVid, a data-driven autoregressive video generation framework that learns the temporal structure of biological behaviors directly from training data, including their natural length distributions. In the first stage, a Finite Scalar Quantization GAN (FSQ-R3GAN) tokenizer encodes each video frame into a compact discrete representation, combining the stabilized relativistic training objective of R3GAN with FSQ's guaranteed codebook utilization to achieve high-fidelity spatial reconstruction without codebook collapse. In the second stage, a causal Transformer models the resulting token sequences autoregressively and learns to emit an End-of-Sequence (EOS) token when the behavioral event reaches semantic closure, with the termination distribution emerging naturally from the training data rather than any human-specified constraint. Experiments on a human drinking behavior dataset (NTU RGB+D, A001, n=94) demonstrate that BioVid's generated length distribution closely matches that of held-out test data, achieving a Wasserstein-1 distance of 1.24 against the ground truth -- compared to 6.05 for a fixed-length baseline and 15.48 for VideoGPT -- while maintaining competitive spatial fidelity.

In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon through comprehensive experiments, implying that different diffusion models consistently reach the same data distribution and scoring function regardless of diffusion model frameworks, model architectures, or training procedures. More strikingly, our further investigation implies that diffusion models are learning distinct distributions affected by the training data size. This is supported by the fact that the model reproducibility manifests in two distinct training regimes: (i) "memorization regime", where the diffusion model overfits to the training data distribution, and (ii) "generalization regime", where the model learns the underlying data distribution. Our study also finds that this valuable property generalizes to many variants of diffusion models, including those for conditional use, solving inverse problems, and model fine-tuning. Finally, our work raises numerous intriguing theoretical questions for future investigation and highlights practical implications regarding training efficiency, model privacy, and the controlled generation of diffusion models.

Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are especially problematic in domain adaptation tasks, where only a few reference examples are available and retraining the diffusion model is infeasible. Existing inference-time guidance methods can adjust sampling trajectories, but they typically optimize surrogate objectives such as classifier likelihoods rather than directly aligning with the target distribution. We propose \emph{MMD Guidance}, a training-free mechanism that augments the reverse diffusion process with gradients of the \textit{Maximum Mean Discrepancy (MMD)} between generated samples and a reference dataset. MMD provides reliable distributional estimates from limited data, exhibits low variance in practice, and is efficiently differentiable, which makes it particularly well-suited for the guidance task. Our framework naturally extends to prompt-aware adaptation in conditional generation models via product kernels. Also, it can be applied with computational efficiency in latent diffusion models (LDMs), since guidance is applied in the latent space of the LDM. Experiments on synthetic and real-world benchmarks demonstrate that MMD Guidance can achieve distributional alignment while preserving sample fidelity. The project code is available at github.com/matinamehdizadeh/MMD-Guidance.

We propose a fast and correspondence-free local point cloud registration method that leverages geometric surface structure and reproducing kernel Hilbert space (RKHS) embeddings. The method represents point clouds as continuous functions with point-wise anisotropic kernels that encode local geometry. This formulation improves alignment along surface normals while relaxing alignment along tangential directions. To solve the resulting registration problem, we propose a second-order on-manifold optimization scheme with approximate Riemannian Hessians, achieving a speedup of up to 10x over the first-order solvers used in prior correspondence-free RKHS-based methods. We demonstrate improved frame-to-frame LiDAR and RGB-D tracking accuracy across diverse indoor and outdoor datasets. On a LiDAR tracking registration task in the driving domain, we achieve a reduction of $>55\%$ in both translational and rotational drift in challenging feature-sparse environments. On object registration benchmarks, we show improved robustness over ICP-based methods and further gains when refining global initialization, particularly under moderate misalignment.

Reconstructing printable 3D models from Mars rover imagery is challenging because Martian terrain is low-texture, irregular, and partially observed. We evaluate a pipeline that estimates stereo depth from NASA Curiosity images, completes geometry, and exports watertight OBJ meshes. On Middlebury, RAFT-Stereo outperforms semi-global block matching (SGBM), reducing disparity MAE from 3.22px to 0.73px and increasing valid prediction coverage from 76.3% to 100.0%. On Curiosity imagery, however, RAFT's denser disparities show weaker edge alignment and higher photometric reprojection error, suggesting that benchmark accuracy does not directly transfer to Martian terrain reconstruction. Geometry completion demonstrates a tradeoff between local fidelity and global connectivity. We find that alpha shapes preserve accurate but fragmented structure, Poisson reconstruction produces more coherent meshes but adds unsupported surfaces, and a deterministic diffusion-fill baseline is intermediate but sensitive to stereo quality. Overall, standard stereo and completion methods can produce printable approximations of Martian terrain, but reliable reconstruction requires stronger domain-specific validation.

The recent receptance weighted key value (RWKV) model combines RNN-style recurrence, offering a linear-complexity alternative to Transformers' quadratic self-attention for modeling global dependencies. However, when directly applied to point clouds, RWKV, originally developed for sequential text, struggles to capture local geometric structures and model spatial dependencies effectively. To address this, we propose the \textbf{P-RWKV} block, which bridges the gap between sequence modeling and irregular 3D geometry while preserving the efficiency advantages of RWKV. It consists of a Local Perception Expansion (LPE) component to expand contextual perception along the spatio-temporal sequence and a Spatial Context Enhancement (SCE) component to strengthen spatial awareness. To validate the effectiveness of P-RWKV for point cloud understanding, we construct PointER, a single-modality self-supervised representation learning framework whose encoder is composed of stacked P-RWKV blocks. Furthermore, we extend P-RWKV to a cross-modality setting and integrate the proposed core sub-modules into multiple architectures, demonstrating strong plug-and-play flexibility and architectural generality. Extensive experiments show that the P-RWKV block and its key sub-modules achieve competitive performance across various tasks with lower computational cost and inference latency. Code will be released upon acceptance.

Most recent 3D reconstruction and editing systems operate on implicit and explicit representations such as NeRF, point clouds, or meshes. While these representations enable high-fidelity rendering, they are fundamentally low-level and hard to control programmatically. In contrast, we propose and systematically evaluate a new 3D reconstruction paradigm, 3D Code Synthesis (3D-CoS), where 3D assets are constructed as executable Blender code, a programmatic and interpretable medium. To assess how well current VLMs can use code to represent 3D objects, we evaluate representative open-source and closed-source VLMs in code-based reconstruction under a unified protocol. We further introduce a suite of structured code-synthesis workflows, including blueprint-based planning, Retrieval-Augmented Generation (RAG) over Blender API documentation, few-shot geometric demonstrations, and a component-level Agent workflow for part-wise code generation. To demonstrate the unique advantages of this representation, we further evaluate localized text-driven modifications and compare our code-based edits with a point-cloud-based 3D editing baseline. Our study shows that code as a 3D representation offers strong controllability and locality, yielding stronger edit fidelity and better preservation of unedited regions in our targeted editing evaluation. Our work also analyzes the potential of this paradigm, delineates the current capability frontier of VLMs for programmatic 3D modeling, and highlights code synthesis as a promising direction for editable 3D reconstruction.

Terrestrial Laser Scanning (TLS) point clouds captured in urban environments frequently suffer from glass-induced reflection artifacts, severely degrading downstream applications. Existing reflection artifact removal methods generally rely on ideal reflection symmetry assumptions, yet their performance is limited by inaccurate glass estimation and insufficient geometric representations. To address these issues, we propose a novel unified framework aimed at robust reflection artifact removal: In the first stage, we leverage a multi-modal vision foundation model to produce initial glass masks, which are then refined using geometric cues to achieve high-precision glass regions, followed by glass completion to recover missing regions caused by no-return measurements on transparent surfaces; In the second stage, we propose a physics-driven descriptor, termed Reflection-aware Local-Global Geometric Similarity (RE-LGGS), which is grounded in actual laser reflection geometry and jointly encodes multi-scale geometric structures and orientation consistency using PCA-based local shape representations, thereby significantly improving robustness against imperfect observations. Extensive experiments on multiple public TLS datasets demonstrate that our framework consistently outperforms state-of-the-art methods in reflection artifacts removal.

3D vision-language segmentation aims to segment target objects in 3D scenarios according to the linguistic instructions and visual observations. Prior art heavily relies on the coarse superpoint representation to reduce the computation complexity, which suffers from poor segmentation quality and messy object boundaries. In this paper, we propose the SEGment-And-select (SEGA3D) paradigm for 3D visionlanguage segmentation that directly operates on the fine-grained visual information and is free from the superpoint dependency. Specifically, we first leverage a mask candidate generator to provide fine-grained categorical mask candidates, substantially improving the quality of candidate masks over the superpoint counterparts. Then, a Large Language Model (LLM) is utilized to generate the semantic and spatial information based on the linguistic description and visual features. The LLM output and visual features are fed to the Semantic-Spatial Selector (SSS) to produce the top-ranking mask candidates. Eventually, the Loopback Verification Module (LVM) is designed to yield the segmentation mask from the selected candidate masks. Our SEGA3D attains competitive performance on ScanRefer, ScanNet and Matterport3D benchmarks. Notably, our SEGA3D surpasses the top-performing counterpart by 8.3 mIoU and 5.3 mIoU on ScanNet and Matterport3D, respectively. Codes will be available upon publication.

Precise rover localization is a prerequisite for autonomous lunar exploration, yet the absence of Global Navigation Satellite System (GNSS) signals and the cumulative drift of local localization methods severely constrain long-range missions. Cross-view localization provides a promising drift-free global solution by matching rover-view and satellite-view imagery. However, the lunar environment poses unique challenges for correspondence alignment, including inter-entity entanglement, inter-viewpoint divergence, and simulation-to-real domain shift. To address these challenges, we propose Warped Alignment of Reprojected Graphs (WARG), a framework that leverages unified graph learning and reprojected graph matching for robust cross-view alignment. Pretrained on the synthetic LuSNAR dataset, WARG achieves an average test error of 0.32 m and demonstrates robust zero-shot generalization to the synthetic lunar south pole region with an error of 3.63 m. More importantly, when validated on real-world data from the YuTu-2 rover, WARG achieves a localization error of 1.68 m within a 100 m x 100 m search area, corresponding to nearly one-pixel precision in low-resolution satellite imagery with a spatial resolution of 1.40 m/pixel. Beyond accuracy, WARG is computationally efficient, containing only 1.56M parameters, corresponding to 16.12% of previous lightweight models, and operating at 5.49 Hz on an NVIDIA RTX A6000 GPU, approaching GNSS-level update frequency. Finally, we observe that WARG naturally develops low-level spatial awareness, including semantic segmentation and structural reasoning, through cross-view localization learning, highlighting its potential as a promising paradigm for spatial intelligence with minimal annotation cost. The source code is available at https://github.com/maochen-casia/warg.

While recent advancements in generative AI have substantially accelerated static 3D model creation workflows, the synthesis of category-agnostic 3D animations remains a significant bottleneck in 3D asset production. Current methods for category-agnostic animation generation exhibit critical limitations in inference speed, motion quality, and adherence to textual prompts, thereby leaving the process dependent on labor-intensive manual artistry. To address these challenges, this paper introduces AnimaSpark, a novel pipeline for category-agnostic 3D animation generation. Our approach is motivated by the key insight that for many fundamental motions in the 3D world, the corresponding joint transformations can often be effectively modeled within a two-dimensional subspace. The pipeline begins by rendering a rigged static 3D model into multi-layered image representations of its mesh and skeleton, which are subsequently fed into a video generation model. We then employ a keypoint tracking algorithm on the generated video to capture the motion of the skeletal joints projected onto the camera's viewing plane. In the final stage, we distill the planar translations and rotations from these tracked keypoints and lift them from the 2D domain into 3D space to animate the character. Comprehensive evaluations reveal that our method achieves superior performance over existing state-of-the-art techniques across key metrics, including text-motion alignment, quality of motion, and computational efficiency.

We present Layered Ray Intersections (LaRI), a fully supervised method for occluded geometry reasoning from a single image. Unlike conventional depth estimation, which is limited to visible surfaces, LaRI predicts multiple surfaces intersected by the camera rays using layered point maps. Compared to the existing approaches that leverage neural implicit representations or iterative refinement, LaRI achieves complete scene reconstruction in one feed-forward pass, enabling efficient and view-aligned geometric reasoning to underpin both object-level and scene-level tasks. We further propose to predict the ray stopping index, which identifies valid intersecting pixels and layers from LaRI's output. To better underpin and evaluate this task, we build an annotation pipeline using rendering engines, construct annotations for five public datasets, including synthetic and real-world data covering 3D objects and scenes. As a generic method, LaRI's performance is validated in object-level and scene-level reconstruction tasks.

Reconstructing accurate implicit surface representations from point clouds remains a challenging task, particularly when data is captured using low-quality scanning devices. These point clouds often contain substantial noise, leading to inaccurate surface reconstructions. Inspired by the Noise2Noise paradigm for 2D images, we introduce NoiseSDF2NoiseSDF, a novel method designed to extend this concept to 3D neural fields. Our approach enables learning clean neural SDFs from noisy point clouds through noisy supervision by minimizing the MSE loss between noisy SDF representations, allowing the network to implicitly denoise and refine surface estimations. We evaluate the effectiveness of NoiseSDF2NoiseSDF on benchmarks, including the ShapeNet, ABC, Famous, and Real datasets. Experimental results demonstrate that our framework significantly improves surface reconstruction quality from noisy inputs.

Monocular shape-from-polarization (SfP) leverages the intrinsic relationship between light polarization properties and surface geometry to recover surface normals from single-view polarized images, providing a compact and robust approach for three-dimensional (3D) reconstruction. Despite its potential, existing monocular SfP methods suffer from azimuth angle ambiguity, an inherent limitation of polarization analysis, that severely compromises reconstruction accuracy and stability. This paper introduces a novel segmentation-driven monocular SfP (SMSfP) framework that reformulates global shape recovery into a set of local reconstructions over adaptively segmented convex sub-regions. Specifically, a polarization-aided adaptive region growing (PARG) segmentation strategy is proposed to decompose the global convexity assumption into locally convex regions, effectively suppressing azimuth ambiguities and preserving surface continuity. Furthermore, a multi-scale fusion convexity prior (MFCP) constraint is developed to ensure local surface consistency and enhance the recovery of fine textural and structural details. Extensive experiments on both synthetic and real-world datasets validate the proposed approach, showing significant improvements in disambiguation accuracy and geometric fidelity compared with existing physics-based monocular SfP techniques.

Existing feed-forward networks excel at predicting a single set of physical properties from visual appearance, but this point-estimate paradigm fundamentally fails to capture the real world's inherent physical ambiguity. We address this by reframing physics prediction as a task of learning a controllable, continuous distribution of material properties. We introduce UNIPIXIE, a framework trained to predict a continuous and parameterized path of physically plausible material properties from a single visual input. By learning a direct mapping along an object's softest-to-stiffest spectrum on our PIXIEMULTIVERSE dataset, UNIPIXIE allows for controllable generation of diverse, physically valid material fields via a single intuitive parameter. Crucially, UNIPIXIE introduces a novel unified architecture to produce simulation-ready parameters for diverse physics solvers, including continuum-based Material Point Method (MPM), reduced-order deformation based on Linear Blend Skinning (LBS), and anchor-based Spring-Mass systems, addressing a key portability issue in prior work. Experiments show our approach not only generates a rich variety of plausible dynamics but also reduces Young's Modulus prediction error by over 50% against the strongest deterministic baseline, bridging the gap between static point estimates and the continuous nature of physical reality. Project page: https://unipixie.github.io/

Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gaussian surfels as a unified representation to progressively reconstruct unknown objects with both photorealistic appearance and accurate geometry. Addressing the limitations of conventional opacity or depth-based cues, we introduce a geometry-aware viewpoint evaluation pipeline that explicitly models back-face visibility and occlusion-aware multi-view covisibility, reliably identifying under-reconstructed regions even on geometrically complex objects. Furthermore, to overcome the limitations of greedy planning strategies, ObjSplat employs a next-best-path (NBP) planner that performs multi-step lookahead on a dynamically constructed spatial graph. By jointly optimizing information gain and movement cost, this planner generates globally efficient trajectories. Extensive experiments in simulation and on real-world cultural artifacts demonstrate that ObjSplat produces physically consistent models within minutes, achieving superior reconstruction fidelity and surface completeness while significantly reducing scan time and path length compared to state-of-the-art approaches. Project page: https://li-yuetao.github.io/ObjSplat-page/ .

Lumbar spine conditions are a leading cause of disability worldwide, yet reliable quantification of degeneration from MRI remains challenging. In clinical practice, analysis is predominantly performed in two dimensions (2D), as manual three-dimensional (3D) assessment is time-consuming. However, 2D measurements suffer from limited reproducibility, particularly when anatomical structures are not aligned with the imaging plane. Existing automated approaches are often restricted to 2D, rely on discrete grading, or lack robustness and interpretability. We introduce SpineReport, an open-source, fully automated framework for comprehensive 3D morphometric analysis of lumbar spine MRI. Leveraging robust anatomical segmentations, the method extracts quantitative metrics from key structures, including the spinal canal, spinal cord, vertebrae, intervertebral discs, and foramina. These include both morphological and signal-based features, enabling cross-subject and longitudinal assessment. SpineReport further generates subject-specific reports that allow comparison with cohort distributions, improving interpretability and objective characterization of spinal morphology. Clinical relevance was evaluated against radiologist-reported severity grades for central canal, lateral recess, and foraminal stenosis. Metrics showed strong associations with central canal stenosis severity, with T2-weighted CSF signal providing the highest performance (AUC = 0.95). Canal AP diameter and area ratios also demonstrated strong correlations and high discriminative ability (AUC > 0.80). For lateral recess stenosis, associations were moderate, with lateral CSF signal being the most informative (AUC = 0.73). No significant associations were observed for foraminal stenosis despite robust region-of-interest extraction. SpineReport is released as an open-access tool: https://ivadomed.github.io/SpineReport/

Reduced facial expressivity is a common motor manifestation of Parkinson's disease (PD), often described as hypomimia or facial bradykinesia. This paper examines whether temporal motion descriptors extracted from facial-region keypoints can support in-the-wild PD-related video classification on the YouTubePD benchmark. Each video is represented using geometric descriptors from 14 predefined facial regions. Static geometry, normalized geometry, velocity-based descriptors, relative-velocity descriptors, and a GRU sequence baseline are compared under the same binary classification protocol. To assess stability and interpretability, the study includes seed-robustness analysis, region-level ablation, and permutation importance. The best result is obtained with normalized velocity descriptors and a Random Forest classifier, reaching a balanced accuracy of 0.826 and an AUROC of 0.855 on the held-out test split. Across 10 random seeds, this representation remains stable, with balanced accuracy of 0.810 +/- 0.018 and AUROC of 0.855 +/- 0.005. Overall, the results suggest that normalized facial-region motion is a lightweight and interpretable representation for YouTubePD video classification. The study is framed as a benchmark-level analysis and does not claim clinical severity assessment or MDS-UPDRS facial-expression scoring.

Accurate lesion segmentation from whole-body Positron Emission Tomography (PET)/Computed Tomography (CT) scans is essential for cancer staging and treatment planning. PET provides functional metabolic information with different radiotracers, while CT offers anatomical localization. Lesion delineation from PET/CT imaging is clinically challenging due to subtle imaging features, confounders, and inter-reader variability. Existing deep learning approaches suffer from training-related stochasticity, inconsistent predictions, missed lesions in high tumor-burden cases, and lack uncertainty quantification, limiting their clinical reliability. Using nnU-Net as a baseline, we propose an uncertainty-aware framework for whole-body PET/CT lesion segmentation that integrates (1) Bayesian ensembling to reduce training stochasticity, (2) voxel-wise uncertainty quantification with epistemic and aleatoric decomposition, and (3) epistemic uncertainty-augmented training to improve lesion detection. Two public datasets, AutoPET-III (1,611 scans) and Deep-PSMA (200 scans), comprising FDG and PSMA studies across multiple cancer types, are used for training and evaluation. Bayesian ensembling improves robustness and performance over deterministic nnU-Net models on the unseen AutoPET-III test set. Uncertainty maps highlight regions of model disagreement and correlate with misclassifications, particularly false positives. Uncertainty-augmented training improves lesion recovery at the cost of increased FPVol, reflecting a precision-recall trade-off. A case-adaptive routing strategy further improves Dice by selecting between the base and augmented models. To our knowledge, this is the first study to systematically investigate uncertainty quantification in multi-tracer, pan-cancer PET/CT segmentation and to combine Bayesian ensembling with uncertainty-aware modeling for this task.

In abdominal CT imaging, developing a low-dose, no-reference image quality assessment (No-reference IQA) model that mimics doctors' reading habits for evaluating CT image quality has significant practical value. This paper proposes a novel deep learning-based framework, ClinReadNet, whose design aligns with the clinical reading logic of radiologists: first, it introduces the Sobel ordinal quality network (SOQN) module, which can simultaneously focus on edge details highly relevant to image quality and the quality distribution pattern of the entire image, accurately matching the clinical image-reading judgment habit of "considering both local details and overall context"; second, the framework integrates the (shifted) window multi-scale temperature multi-head self-attention ((S)W-MTMSA) module, which further replicates the radiologists' image-reading process of shifting from overall scanning to local focusing, and accurately locks in regions of interest through multi-sharpness attention; third, it designs the hierarchical ranked probability score (HRPS) loss function, which combines the dual logics of coarse classification and fine classification, while paying attention to the distance information between grading labels, effectively improving the performance of image quality assessment. Experiments conducted on the LDCTIQAG2023 dataset show that the proposed method achieves the current state-of-the-art (SOTA) performance: the values of Pearson's linear correlation coefficient (PLCC), Spearman's rank-order correlation coefficient (SROCC), and Kendall's rank-order correlation coefficient (KROCC) reach 0.9507, 0.9554, and 0.8629 respectively, with the sum of their absolute values (Score) being 2.7690, outperforming existing methods.

Accurate segmentation of carotid arteries in ultrasound imaging is critical for stroke risk assessment. However, speckle noise, low contrast, and blurred boundaries remain major challenges. In this paper, we propose a Frequency-Spatial Synergy Network (FSS-Net) to achieve noise-robust and high-precision carotid artery segmentation. The network integrates wavelet transform, multi-domain attention, and edge enhancement into a unified encoder-decoder architecture. Specifically, a Channel-Spatial-Wavelet Attention (CSWA) module is designed to suppress noise and purify semantic features in the frequency domain. A Wavelet-Enhanced Bottleneck (WEB) module is introduced to capture long-range global dependencies efficiently. Furthermore, a Laplacian-Guided Adaptive Edge Fusion (LAEF) module compensates high-frequency details and maintains boundary continuity. Extensive experiments on carotid ultrasound datasets show that FSS-Net achieves a Dice score (DSC) of 96.46% and strong robustness under low SNR conditions, outperforming several state-of-the-art methods. This method realizes accurate segmentation of carotid artery in ultrasonic imaging, effectively identifies carotid atherosclerotic plaque, and is verified by other task (such as segmentation of breast cancer), suggesting that it has good clinical application potential in identifying abnormal tissue masses in ultrasonic images.

Bone marrow smear review remains important for acute myeloid leukemia (AML) assessment, but manual single-cell interpretation is labor-intensive and patient-level diagnosis requires aggregation of many cellular observations. We present a cell-to-patient deep learning pipeline for AML-assisted diagnosis from bone marrow smear images. The study included 258 patients from six anonymized centers, including a main cohort of 169 patients from Centers 1-3 and an external validation cohort of 89 patients from Centers 4-6. A 16-category cell annotation vocabulary was used to describe the global cellular composition, including granulocytic, monocytic, erythroid, lymphoid, eosinophilic, and other cells. Rather than identifying strict AML blasts or leukemic blasts, the model targets an expert-defined composite category termed Composite Blast-like Cells (CBLC), comprising N, N1, M, M1, R, R1, J, and J1 according to the project-wide morphological standard. A fixed YOLO-based segmentation module detected cells, predicted contours were matched to expert polygon annotations by contour IoU, and standardized single-cell crops were generated. An EfficientNet-B0 classifier was trained through a two-stage GT-to-YOLO and YOLO-to-YOLO strategy with class-imbalance correction, center-border regularization, and morphology-assisted supervision. Cell-level predictions were aggregated into patient-level CBLC ratios for AML-oriented diagnostic support. The pipeline achieved stable internal validation and maintained external generalization, with ensemble weighted F1-scores of 0.9076, 0.8696, and 0.9124 on Centers 4, 5, and 6, respectively.

Accelerated acquisition of fMRI enables enhanced detection of neurovascular (BOLD) activity in the brain, but image reconstruction becomes challenging with high k-space undersampling: Task-evoked BOLD signals are small in magnitude, which traditional anatomical MRI reconstruction methods fail to recover, as they favor spatial accuracy over temporal fidelity. We present DD-INR, a Dynamics-Driven Implicit Neural Representation framework tailored for accelerated fMRI that benefits from incoherent time-varying sampling and a tailored spatiotemporal prior, outperforming traditional methods, demonstrated in simulation and in-vivo acquisition, both in terms of image quality and retrieval of activation patterns. DD-INR achieves this by splitting the fMRI data into a static background and a temporally varying dynamic component, representing only the dynamics with a dedicated INR, thereby focusing the model's capacity on activation-relevant changes while remaining compact. In general, DD-INR provides a promising framework for accelerated fMRI reconstruction, with the potential to improve the sensitivity and robustness of fMRI studies within practical scan time limits. The source code is available at https://github.com/JoosenLi/DD-INR.

Foundation Models (FMs) have recently redefined the state-of-the-art in histopathology by providing robust representations for whole-slide image (WSI) analysis. However, selecting the optimal foundation model (FM) for a specific clinical cohort currently requires multiple preprocessing steps, followed by computationally expensive feature extraction and the training of a Multiple Instance Learning (MIL) aggregator for every model. In this work, we investigate whether efficient tile-level linear probing can serve as a reliable proxy for slide-level performance, reducing the need to run full slide-level pipelines for every candidate encoder. We benchmark 19 state-of-the-art FMs on 42 slide-level and 16 tile-level tasks, comparing tile probing metrics against slide-level outcomes using ABMIL and Mean Pooling aggregations. We observe a high correlation between tile and slide performance across varying task difficulties, indicating that encoder representation quality is the primary determinant of WSI success. Sensitivity analyses show that transferability is stable across models and is more influenced by cohort sizes and numbers of tiles per slide than by average task difficulty. We also measure the agreement in best performing models between tile and slide-level tasks, showing tile benchmarks reliably shortlist strong candidates. Overall, our study indicates that tile-level benchmarking provides an efficient and practical first step for narrowing down candidate models, while slide-level evaluation remains essential for final validation on clinical tasks.

Zinc-based alloys are indispensable emerging absorbable metallic biomaterials, and their macroscopic performance is governed by microstructural characteristics. Intermediate phases-key microstructural constituents-are pivotal in regulating mechanical and functional properties. However, intermediate phase segmentation in zinc alloy microstructures faces formidable challenges: scarce annotated datasets, low contrast, difficulty detecting small targets, and heterogeneous morphologies. To this end, we construct IPSM-Bench, the largest high-quality dataset for zinc-alloy intermediate phase segmentation. Furthermore, we propose SCoP-SAM, a new Spatial Context Prior-guided SAM method that leverages the gradient structure and grayscale properties of intermediate phases to capture spatial context priors and incorporates them into the entire SAM encoding-decoding process, improving segmentation performance. Based on the proposed IPSM-Bench, we establish a new benchmark for intermediate phase segmentation to systematically evaluate state-of-the-art (SOTA) methods and advance research on zinc alloy microstructure analysis. Extensive experiments on IPSM-Bench and additional public alloy benchmarks demonstrate that our SCoP-SAM not only achieves SOTA performance for zinc-alloy intermediate phase segmentation but also generalizes remarkably well to other alloy scenarios.

Background and purpose: oART enables daily plan adaptation to interfraction anatomical variations, but cumulative dose estimation remains limited by DIR, segmentation, and anatomical uncertainties. We introduce IMPACT-DoseAcc, an uncertainty-aware dose accumulation framework, within IMPACT for semantic feature-driven image analysis. The framework is modality- and disease-agnostic and is applied to CBCT-guided oART for cervical cancer (LACC). Material and Methods: Nine LACC patients were retrospectively analyzed using daily CBCT-derived virtual CTs for dose recalculation. IMPACT-DoseAcc focuses on uncertainty from DIR, without modeling vCT-generation uncertainty. Two DIR uncertainty strategies were tested within IMPACT-Reg: a Bayesian segmentation-guided approach using one probabilistic model to quantify anatomical uncertainty, and an ensemble of segmentation models targeting structures to capture epistemic variability. Voxel-wise uncertainty maps were propagated through dose warping and accumulation to generate probabilistic dose-volume histograms. Ensemble uncertainty was quantified from voxel-wise standard deviation across deformation fields, and geometric error was assessed using surface distance between warped and validated contours. Anatomical-variability weighting refined aggregation. Results: Ensemble DIR uncertainty correlated with geometric error, with Pearson coefficients of 0.63 for CTVt and 0.66 for bladder. For CTVt, pDVHs achieved 96.3 +/- 3.9% coverage, showing calibration of propagated uncertainty. Weighting stabilized estimates across fractions and organs. Conclusions: IMPACT-DoseAcc propagates registration-driven uncertainty to cumulative dose metrics, improving interpretation of accumulated dose under anatomical variations. Its 3DSlicer integration supports reproducible, uncertainty-informed ART workflows.

A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women receive no skilled sonography. Current deep learning approaches address detection, segmentation, or classification in isolation, each demanding a separate model and expert-specified labels at inference. We present FADA, a unified vision-language model built on Qwen3.5-VL that performs clinical interpretation, classification, detection, and segmentation through a single interpretation-first pipeline without external labels. FADA distills knowledge from four domain-specific foundation models (FetalCLIP, UltraSAM, USF-MAE, UltraFedFM) via offline pre-computed feature caching. Selective distillation, which applies feature alignment only to annotation tasks while interpretation relies on standard fine-tuning, consistently outperforms full distillation across most evaluation axes. The recommended variant, FADA-SKD, achieves 0.8820 mean Dice for segmentation, 0.7671 mAP@0.50 for detection, and 100% structured interpretation compliance. Expert sonographer validation across 237 images confirms clinically acceptable outputs in both autonomous and human-in-the-loop modes, with 73.5% of interpretations scoring perfectly under clinician guidance. The system is trainable on a single consumer GPU and deployable without cloud connectivity. We validate edge deployment by running the compressed 0.8B model on a commodity smartphone (Qualcomm Snapdragon 7 Gen 1, 12 GB RAM) using llama.cpp with GGUF quantization, completing the full 5-phase pipeline in approximately 60 seconds entirely offline. This establishes a practical pathway for integrating AI-assisted fetal assessment with portable ultrasound devices, directly addressing diagnostic access gaps in resource-constrained settings. Code, models, and data are available at https://github.com/mahmoodphd/FADA.

The nnU-Net has demonstrated continuous success in medical segmentation tasks, which heavily rely on the availability and diversity of annotated biomedical data. However, assembling medical imaging cohorts remains challenging due to numerous factors such as privacy regulations and annotation costs. As a result, data augmentation plays a crucial role in increasing data availability while maintaining anatomical feasibility. Hence, we propose the ++nnU-Net, a novel data augmentation module based on image registration that operates prior to preprocessing and training take place. Our framework was evaluated across five different 2D datasets. In this workflow, image data go through a two-stage registration process, generating new warped images. The transformations are then applied to the respective segmentation. In addition, the pipeline computes available disk space, generates supplementary binary synthetic masks and generates checkpoints. We demonstrate that the ++nnU-Net outperforms the nnU-Net baseline, yielding improvements in Dice Similarity Coefficient scores. In the most prominent cases, we observe performance gains of approximately 22\%. These findings highlight the effectiveness of registration-based data augmentation, particularly for 2D medical imaging datasets and suggest that the ++nnU-Net provides a practical and scalable approach for enhancing segmentation performance in data-limited settings. The source code for the ++nnU-Net is available at: https://github.com/sofia-adelie/plusplusnnunet.git

Whole slide images (WSIs) play a crucial role in cancer diagnosis due to their ultra-high resolution and rich morphological information, and multiple instance learning (MIL) has become a prevalent paradigm to solve the massive size of WSIs and the scarcity of fine-grained annotations of instance. However, most existing MIL methods struggle to accurately identify diagnostically critical local regions (instance) using only slide-level labels, and suffer from modelling the relationship of instances efficiently. To address these defects, we propose a Dual-Stream Attention-Guided Learning (DSAGL) framework. DSAGL bridges slide-level supervision and instance-level learning through a teacher-student dual-stream architecture, and mitigates instance ambiguity by generating attention-guided pseudo labels. The framework employs a shared lightweight encoder to efficiently model long-range dependencies and an attention-based fusion mechanism to enhance sensitivity to sparse, informative regions. Extensive experiments on synthetic benchmarks and real-world pathological WSI datasets demonstrate that DSAGL consistently outperforms state-of-the-art MIL methods, achieving superior discriminative performance and robustness under weak supervision.

Musculoskeletal disorders pose significant risks to athletes, and early risk assessment is essential for prevention. However, most existing methods are designed for controlled settings and fail to reliably assess risk in complex environments due to their reliance on a single type of data. This research introduces ViSK-GAT (Visual-Skeletal Geometric Attention Transformer), a novel multimodal deep learning framework that classifies musculoskeletal risk using both visual and skeletal coordinate-based features. A custom multimodal dataset (MusDis-Sports) was created by combining images and skeletal coordinates, with each sample labeled into eight risk categories based on the Rapid Entire Body Assessment (REBA) system. ViSK-GAT integrates two innovative modules: the Fine-Grained Attention Module (FGAM), which refines intra-modal features through self-attention before fusion, and the Multimodal Geometric Correspondence Module (MGCM), which enhances cross-modal alignment between image features and coordinates. The model achieved robust performance, with all key metrics exceeding 93%. Probability distribution error metrics also showed a low Root Mean Squared Error (RMSE) of 0.1205 and a Mean Absolute Error (MAE) of 0.0156. ViSK-GAT consistently outperformed state-of-the-art (SOTA) deep learning backbones and showed its potential to advance artificial intelligence-driven musculoskeletal risk assessment and enable timely interventions in sports.

Multiple-instance Learning (MIL) is commonly used for computational pathology (CPath), where multi-scale features are essential for capturing both fine cellular details and broad tissue architecture. However, existing multi-scale MIL approaches typically rely on the inflexible multi-magnification inputs or the computationally expensive architectures. As pre-trained foundation models (FMs) become the trend for feature extraction and boost lightweight models, we rethink and explore a more efficient multi-scale MIL method. In this paper, we propose the Multi-scale Pyramidal Network (MSPN), a plug-and-play module for attention-based MIL. MSPN introduces progressive multi-scale whole-slide image analysis using only a single high-magnification input. It consists of (1) grid-based remapping that aggregates high-magnification features to derive spatially-aware coarse feature maps, and (2) the Coarse Guidance Network (CGN) that learns coarse contexts. We benchmark MSPN as an add-on module to 4 attention-based frameworks on 5 clinically relevant tasks with 2 foundation models, and a pre-trained MIL framework. Our results demonstrate that MSPN consistently improves MIL across the compared configurations and tasks, while being lightweight and easy-to-use.

Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions. Moreover, small-lesion cues can be diluted by multi-scale feature extraction, causing under- or over-segmentation. To address these challenges, we propose an Uncertainty-Aware Hypergraph Refinement Network (UHR-Net). First, we introduce an Uncertainty-Oriented Instance Contrastive (UO-IC) pretraining strategy that couples geometry-aware copy-paste augmentation with hard-negative mining of lesion-like background regions to improve instance-level discrimination for small and visually ambiguous lesions. Second, we design an Uncertainty-Guided Hypergraph Refinement (UGHR) block, which derives an entropy-based uncertainty map from a coarse probability map to guide hypergraph refinement. By splitting hyperedge prototypes into foreground and background groups, UGHR decouples higher-order interactions and improves refinement in ambiguous regions. Experiments on five public benchmarks demonstrate consistent gains over strong baselines. Code is available at: https://github.com/CUGfreshman/UHR-Net.

Eye movements, including saccades, are widely regarded as highly sensitive and objective biomarkers of neurophysiologic states. Detecting saccadic signatures in neurologic diseases offers a rapid, portable alternative to brain imaging, avoiding access and cost barriers. Currently, there are no robust AI-enabled video-oculographic solutions (e.g., digital biomarkers) for screening, triaging, or localizing brain abnormalities due to privacy issues and scarce datasets. In this work, we propose the first fully synthetic, patient-free, multimodal eye movement generation pipeline for generalizable saccade analysis. Using this synthetic dataset, we trained a deep learning classifier to distinguish between normal and abnormal (hypometria and hypermetria) saccadic accuracies and evaluated its performance on real-world clinical data. The model achieved an AUROC of 0.76 and a sensitivity of 0.71, showing that the synthetic data has strong potential to generalize for clinical applications, including as a screening tool in at-home and emergency room settings or a tool for precise neuroanatomic localization.

CT radiomics-based machine learning has potential to predict lung cancer in pulmonary nodules (PNs) earlier than standard-of-care methods. Low malignancy rates in early-development PNs and variable image acquisition hinder development of radiomic models for diagnosing these PNs. To address these challenges, we augmented training using later-development PNs and harmonized for acquisition effects. We examine early-development benign and malignant PNs (n=106) below the sensitivity of standard-of-care diagnosis. Classifiers predicting malignancy performed near chance when trained on ComBat-harmonized radiomic features from only early-development PNs. We then augmented training with later-development benign and malignant PNs (n=225). We evaluated whether harmonization must incorporate biology that impacts acquisition effects in added training data. To correct variability from four acquisition protocols, we compared: 1) biology-unaware harmonization, 2) harmonizing with a covariate distinguishing early-development, later-development benign, later-development malignant datasets, 3) harmonizing each dataset separately. Models trained using augmentation, but biology-unaware harmonization, failed to improve consistently. Augmented training data harmonized with a covariate (ROC-AUC 0.74 [0.69-0.79]) or separately (ROC-AUC 0.71 [0.66-0.77]) yielded higher test ROC-AUC (Delong, p<=0.05) and PR-AUC (Wilcoxon, p<=0.05). In a proof-of-principle methodological study, we demonstrate with a small single-center dataset that combining radiomic features from later-development benign and malignant PNs requires biology-aware harmonization.

Pancreatic cancer is projected to be the second-deadliest cancer by 2030, making early detection critical. Intraductal papillary mucinous neoplasms (IPMNs), key cancer precursors, present a clinical dilemma, as current guidelines struggle to stratify malignancy risk, leading to unnecessary surgeries or missed diagnoses. Here, we introduce Cyst-X, a multi-center MRI benchmark and a federated learning framework for IPMN malignancy-risk stratification. The dataset comprises 1,461 abdominal MRI scans from 764 patients at seven international centers, with three-tier malignancy labels anchored in histopathology or three-year imaging follow-up and expert pancreas segmentations. The pipeline couples the PanSegNet pancreas segmenter with a 3D DenseNet-121 classifier and a parallel radiomics predictor. On internal cross-validation, the deep learning classifier reached a mean area under the receiver operating characteristic curve (AUC) of 0.85 (95% confidence interval 0.84-0.86) on T2-weighted MRI for high-risk versus low- or no-risk discrimination, with the average precision rising from a prevalence baseline of 0.23 to 0.64. This performance was preserved (AUC 0.85, FedProx) when training was distributed across institutions without exchange of raw patient images. Benchmarked against three blinded radiologists on a 629-case reader subset evaluated under imaging-only conditions, the classifier matched or exceeded sensitivity at comparable specificity. To accelerate research in early pancreatic cancer detection, we publicly release the Cyst-X dataset, segmentation masks, and trained models as the first large-scale, multi-centre MRI resource for pancreatic cystic neoplasm analysis.

In this report, we present our champion solution for the DataMFM Challenge Track 2: Chart Understanding. This track requires models to recover structured chart data and generate faithful natural-language summaries from chart images. To address the complementary requirements of accurate data extraction and factual narration, we propose ChartLens, a dual-branch framework for chart data correction and summary refinement. ChartLens consists of two key modules: Structure-Aware CSV Verification and Correction (SAVC) and Text-Retention-Guided Summary Refinement (TRSR). SAVC improves the reliability of structured data extraction through verification and correction, while TRSR enhances summary generation by preserving critical textual and numerical evidence from charts. By combining model adaptation, correction-based generation, and OCR-assisted evidence grounding, ChartLens improves both structured data recovery and summary factuality. On the test set, our final system achieves an overall score of 69.10 and ranks first in Track 2, demonstrating its effectiveness for accurate chart understanding. Our code will be released at: https://github.com/iLearn-Lab/CVPRW26-ChartLens.

Remote sensing vector mapping aims to generate structured maps of geospatial entities, such as buildings, roads, and water bodies, from remote sensing imagery. In practice, vector maps usually contain multiple category layers and heterogeneous entity structures, requiring a unified model for diverse mapping needs. However, existing methods typically represent vector objects as polygons or graphs, making them suitable only for specific categories: polygons poorly capture topological relations, while graphs often blur instance boundaries. We observe that language, as a natural medium for human communication, offers a flexible and expressive representation that can accommodate heterogeneous map elements, including geometry, semantics, and topolog. Motivated by this insight, we propose Vector Map as Language (VecLang), a unified paradigm that reformulates multiclass vector mapping as structured text generation. VecLang encodes the common elements of different geospatial entities into a GeoJSON-like vector language, enabling cross-category modeling within a shared textual format. To generate this language reliably, we design a progressive vision-language mapping framework that first localizes vectorization units and then generates structured map elements. We further introduce Hierarchical Vector Language Optimization, which uses reinforcement learning to improve syntax validity, content fidelity, and map executability. We also build VecMap-Bench with 54K images and 800K instances, supporting training and evaluation across standard and generalization settings. Extensive experiments demonstrate that VecLang handles both single-class and multiclass vector mapping while achieving strong cross-dataset and open-vocabulary generalization. The model and dataset are publicly available at https://github.com/yyyyll0ss/VecLang.

Furnished floor plans are fundamental to real estate visualization, interior design, and architectural workflows. However, progress in automatic furniture arrangement has been limited by the lack of real, professionally designed floor-plan datasets with object-level furniture annotations. To address this gap, we introduce AntPlan-270, a curated dataset of 270 architectural floor plans with per-room furniture bounding box annotations across ten residential room categories. Building on this dataset, we present Architect-Ant, an editable automatic furnishing framework powered by a fine-tuned vision-language model. Furniture layouts are represented using a compact, coordinate-based domain-specific language (DSL) that encodes object categories and placements relative to the room geometry. To improve spatial reasoning, we generate procedural reasoning traces that capture architectural constraints such as wall alignment, door and window clearance, circulation, fixture compatibility, and room-specific furniture inventories, and use them to supervise fine-tuning of the model. We then apply preference optimization over candidate object placements to further refine layout quality. The generated DSL can be rasterized into semantic masks and used to condition a Flux-based LoRA renderer, producing realistic blueprint-style furnished floor-plan images while preserving the editable symbolic layout. Experiments on layout furnishing show that Architect-Ant produces geometrically valid and functionally plausible layouts, and suggest a scalable path for furnishing larger structure-only floor-plan datasets.

Kuzushiji was one of the most widely used cursive writing systems in pre-modern Japan. Due to its highly cursive forms and extensive glyph variations, most modern Japanese readers are unable to read Kuzushiji characters. Consequently, recent studies have focused on developing automated Kuzushiji character recognition (KCR) methods, which have achieved strong performance on relatively clean Japanese historical document images. Although seals frequently appear in Japanese historical documents, existing methods often fail to maintain recognition accuracy under seal interference, particularly when seals overlap with characters. To address this challenge, we propose a seal-robust KCR framework. Based on character detection, classification, and ordering, the proposed framework additionally incorporates document restoration to mitigate seal interference, thereby improving overall recognition performance. In addition, we introduce a novel synthetic data augmentation strategy to enhance the performance of character detection models. We further correct annotation errors, reconstruct the dataset, and create a synthetic test set to simulate severe seal interference. Experimental results demonstrate the effectiveness of the proposed framework in mitigating the impact of seal interference on KCR. Compared with a conventional baseline and NDLkotenOCR, it achieves relative character error rate (CER) reductions of 39.7% and 5.9%, respectively, on the real test set, and 50.1% and 41.7%, respectively, on the synthetic test set.

Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of growing chart-to-code datasets, simply scaling homogeneous chart-code pairs conflates visual perception with program logic, preventing models from fully leveraging the richness of multimodal supervision. We present CharTide, a novel data-centric framework that systematically redesigns both training and alignment data for chart-to-code generation. First, we construct a 2M-sample dataset via a Tri-Perspective Tuning strategy, explicitly decoupling training into visual perception, pure-text code logic, and modality fusion streams, enabling a 7B model to surpass specialized baselines using only supervised data. Second, we reformulate alignment as a data verification problem rather than a heuristic scoring task. To this end, we introduce an Inquiry-Driven RL framework grounded in the principle of information invariance: a downstream model should yield consistent answers to identical visual queries across both original and generated charts. Moving beyond rigid rule matching or VLM scoring, we employ a frozen Inspector to objectively verify generated charts through atomic QA tasks, providing verifiable reward signals based on answer accuracy. Experiments on ChartMimic, Plot2Code, and ChartX show that CharTide-7B/8B significantly outperforms open-source baselines, surpasses GPT-4o, and is competitive with GPT-5.

Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision and language models, yet most prior work focuses on natural images. In contrast, existing chart referring expression grounding-related benchmarks remain limited: (1) they largely adopt bounding boxes, constraining localization precision for fine chart elements (2) they mostly assume a single and two referred target instances, failing to handle multi-instance target references; (3) the language expressions over-rely on textual cues or data-rank clues (4) they cover only a narrow range of chart types. To address these issues, we introduce a chart referring expression grounding benchmark that systematically supports multiple localization forms, multiple referred targets, diverse grounding cues and diverse chart types. Results across representative multimodal large models reveal a significant performance gap. We further introduce a code-driven synthesis pipeline that exploits the inherent alignment between plotting programs and rendered chart primitives to derive pixel accurate instance masks across chart element types and granularities. We train an instance segmentation model with the synthesized masks and integrate it into a general-purpose multimodal grounding framework. The resulting system consistently outperforms baselines on our benchmark and generalizes well to a ChartQA-derived real-chart grounding benchmark.

Real-world image super-resolution (SR) is often designed with a single restoration objective, despite the current capacity of generative models to produce multiple high-quality reconstructions for the same input. In this paper, we argue that the best restoration strategy is subject to the specific restoration profile: a Faithful restoration prioritizes reference consistency, structure preservation, and hallucination suppression, whereas an Aesthetic restoration prioritizes visually pleasing and natural-looking details. We propose FoA-SR, a novel preference optimization approach to real-world SR based on profiles. To achieve this goal, FoA-SR starts with our supervised FLUX.2-based SR adapter (Flux2SR) trained with LR latent conditioning, flow matching, and image-space reconstruction losses for paired LR-to-HR image super-resolution. Following the development of the shared supervised super-resolution adapter, FoA-SR generates a shared stochastic candidate pool for each input image and ranks the same candidates using profile-specific Faithful and Aesthetic rewards to mine winner-loser pairs. These pairs are used to fine-tune separate LoRA adapters while keeping the base model frozen. Experiments on RealSR and DIV2K show that FoA-SR can steer the same SR adapter towards distinct restoration objectives: a Faithful adapter improves reference-consistent metrics while an Aesthetic adapter boosts metrics that measure perceptual quality without reference. Our candidate-pool analysis shows that Faithful and Aesthetic rewards frequently select different winners, and a Hybrid-LoRA ablation shows that collapsing both profiles into one reward yields an implicit compromise rather than explicit profile control.

UAV multispectral imagery naturally contains multi-angular observations due to low flight altitude and wide field-of-view imaging, which may introduce geometry-driven radiometric variability. This study proposes a geometry-aware multi-angular observation extraction workflow to quantify observation-geometry effects from a BRDF perspective. Specifically, camera intrinsics and extrinsics are refined via structure-from-motion (SFM), and homogeneous regions annotated on an orthomosaic are reprojected onto multiple raw sub-images acquired from different viewpoints. This enables joint extraction of multi-band reflectance and observation geometry parameters for the same ground targets under varying viewing directions. The extracted observations are further analyzed using band-wise polar visualization in the (VZA, RAA) domain. Results on a grassland target show clear reflectance anisotropy across ten bands, with red-edge and nearinfrared bands exhibiting 119-137% variability between maximum and minimum reflectance, indicating non-negligible observation-geometry effects on radiometric consistency.

Snapshot Broadband Filter Array (BFA) imaging provides high light throughput for spectral reconstruction but introduces severe spectral aliasing due to complex modulation. Current deep learning approaches, limited to spatial denoising, often fail to address the global frequency-specific degradations caused by the mask structure. To address this, we propose a Physics-embedded Frequency-aware Transformer (PF-Trans) for high-fidelity remote sensing spectral reconstruction. Our method explicitly integrates the physical sensing model through mask injection and a gray-scale consistency loss to ensure physical fidelity. Furthermore, we introduce a Dual-domain Block with a parallel Fast Fourier Transform (FFT) branch, enabling the network to perceive and suppress aliasing artifacts in the frequency domain. Extensive experiments on multiple datasets demonstrate that PF-Trans achieves state-of-the-art performance, achieving a Peak Signal-to-Noise Ratio (PSNR) of up to 48.50 dB on the GF-5 Shanghai dataset, significantly outperforming comparison methods.

We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predicting the relative depth in football scenarios is challenging, especially with only thousands of training samples available. To address this issue, our method leverages the powerful zero-shot capabilities of models pretrained on large-scale datasets to learn metric depth for effective relative depth prediction, achieving a score of $2.68 \times 10^{-3}$ on the challenge set.

Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT.

Most existing deep learning-based PET image denoising methods assume a fixed and known dose reduction factor (DRF) for low-dose PET images. However, these methods encounter significant performance degradation when the DRF varies beyond the assumed one in practical applications. To address the challenge posed by varied DRFs, several preliminary studies focus on the task of universal PET image denoising, aiming to train a universal model over low-dose data across DRFs. Nonetheless, these vanilla universal models often struggle with misaligned styles present in different DRF data, leading to the \textit{style elimination issue} with a significant over-smoothing effect. To deal with this issue, we innovatively introduce domain generalization to PET image denoising and propose a universal PET image denoising network (UniPET) to achieve high-quality PET image denoising across diverse DRFs. UniPET comprises two primary innovations: a style alignment network (SAN) and a region-aware learning strategy (RALS). Specifically, SAN utilizes style alignment techniques derived from domain generalization to align and recover styles across different DRFs, ensuring the model's generalizability across various DRFs while effectively preserving styles. Furthermore, to enhance style recovery, RALS distinguishes between flat and stylized regions, exclusively conducting adversarial learning on the latter, thereby more effectively guiding the model's focus towards learning stylized regions. It is demonstrated that our proposed UniPET can adaptively recover different DRF styles and achieve high-quality PET image denoising across DRFs. Comprehensive experiments show that UniPET exhibits comparable performance to individual DRF-specific models at specific DRFs and realizes state-of-the-art performance in universal PET image denoising quantitatively, perceptually, and clinically.

Low-light video enhancement (LLVE) remains a challenging task due to severe information degradation under low-illumination conditions. Recent multimodal approaches have significantly improved enhancement performance by incorporating auxiliary modalities, such as event streams and infrared images. However, these methods typically assume the availability of these modalities at inference, which is often not feasible in real-world scenarios. To solve this problem, in this work, we propose AMNet, a unified multimodal framework for LLVE, to support flexible modality-agnostic inference, where auxiliary modalities may be unavailable. To address the issue of modality absence, we introduce a Spatial-Spectral Dual-Gated Translator that learns the correspondence between auxiliary modalities and RGB inputs, producing implicit auxiliary representations to support the robust enhancement. Additionally, to fully facilitate the learning of cross-modal correspondence, we conduct large-scale multimodal pretraining based on the RGB-only dataset with synthetic auxiliary modalities. Extensive experiments demonstrate that AMNet could handle arbitrary inference-time modality combinations and exhibits superior performance for LLVE under modality absence conditions. Code and models are available on the project page.

In this study, we propose an overlapped wavelet diffusion framework for Low-Light Image Enhancement (LLIE), which incorporates two complementary components to achieve blocking artifact-free and detail-preserving enhancement. Although recent diffusion-based LLIE methods have demonstrated remarkable performance compared with traditional approaches, DiffLL still suffers from blocking artifacts caused by the Haar Wavelet Transform (WT) and blurred edges or over-smoothed textures due to the limitations of its High-Frequency Restoration Module (HFRM). To overcome these issues, we introduce an Overlapped WT (OWT) that incorporates correlations across neighboring regions, thereby structurally preventing blocking artifacts. Furthermore, we integrate a low-frequency-guided High-Frequency Enhance Block (HFEBlock) to strengthen detail recovery, yielding sharper edges and more reliable textures. Extensive experiments on the LOLv1 and LOLv2-real datasets demonstrate that our framework, termed OWDiff, consistently outperforms existing LLIE methods both qualitatively and quantitatively, achieving superior visual quality while maintaining computational efficiency. OWDiff effectively addresses the structural limitations of the Haar WT and the HFRM, achieving an average PSNR gain of 0.58 dB, along with a 1.64% relative improvement in SSIM and a 5.9% relative reduction in LPIPS, compared to DiffLL across both the LOLv1 and LOLv2-real datasets.

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate diffusion-based SR models, some (e.g., SinSR) fail to produce realistic perceptual details, while others (e.g., OSEDiff) may hallucinate non-existent structures. To overcome these issues, we present RSD, a new distillation method for ResShift. Our method is based on training the student network to produce images such that a new fake ResShift model trained on them will coincide with the teacher model. RSD achieves single-step restoration and outperforms the teacher by a noticeable margin in various perceptual metrics (LPIPS, CLIPIQA, MUSIQ). We show that our distillation method can surpass SinSR, the other distillation-based method for ResShift, making it on par with state-of-the-art diffusion SR distillation methods with limited computational costs in terms of perceptual quality. Compared to SR methods based on pre-trained text-to-image models, RSD produces competitive perceptual quality and requires fewer parameters, GPU memory, and training cost. We provide experimental results on various real-world and synthetic datasets, including RealSR, RealSet65, DRealSR, ImageNet, and DIV2K. We provide the code at https://github.com/Daniil-Selikhanovych/RSD.

Reconstructing Hyperspectral Images (HSI) from RGB images can yield high spatial resolution HSI at a lower cost, demonstrating significant application potential. This paper reveals that local correlation and global continuity of the spectral characteristics are crucial for HSI reconstruction tasks. Therefore, we fully explore these inter-spectral relationships and propose a Correlation and Continuity Network (CCNet) for HSI reconstruction from RGB images. For the correlation of local spectrum, we introduce the Group-wise Spectral Correlation Modeling (GrSCM) module, which efficiently establishes spectral band similarity within a localized range. For the continuity of global spectrum, we design the Neighborhood-wise Spectral Continuity Modeling (NeSCM) module, which employs memory units to recursively model the progressive variation characteristics at the global level. In order to explore the inherent complementarity of these two modules, we design the Patch-wise Adaptive Fusion (PAF) module to efficiently integrate global continuity features into the spectral features in a patch-wise adaptive manner. These innovations enhance the quality of reconstructed HSI. We perform comprehensive comparison and ablation experiments on the mainstream datasets NTIRE2022 and NTIRE2020 for the spectral reconstruction task. Compared to the current advanced spectral reconstruction algorithms, our designed algorithm achieves State-Of-The-Art (SOTA) performance.

While existing AI-generated image detectors report high performance, we identify that this is largely driven by a critical prediction asymmetry: a bias toward the real class that severely limits sensitivity to generated content, especially under standard post-processing operations such as compression and resizing. We hypothesize that this stems from the model's reliance on spurious features, distracting signals that obscure true generative artifacts. To address this, we propose DEAR (Dissect and Prune), which leverages inpainted images to identify and prune these interfering components. Specifically, we find that features strongly aligned to either inpainted or non-inpainted regions are less robust to post-processing. By measuring the alignment between channel activations and inpaint masks, DEAR removes features at both extremes, retaining only those that capture genuine generative artifacts. Experimental results demonstrate that our approach significantly enhances robustness against unseen generators and post-processing, effectively mitigating the prediction asymmetry. Our code is available at https://github.com/dahyedahye/dear.

Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness. A key property is cross-model transferability, which enables transfer-based black-box attacks. However, existing attacks often rely heavily on the surrogate model, causing cross-model performance drops. One reason is that adversarial optimization may follow surrogate model responses more than input semantics, making the update direction effective on the surrogate but less transferable to unseen targets. We refer to this dependency as surrogate-specific bias. Motivated by this observation, DeBias-Attack improves transferability by correcting surrogate-specific bias in adversarial optimization directions. It maintains two perturbation branches. The main branch optimizes a perturbation on the original image and obtains the adversarial gradient used to disrupt image-text alignment. The reference branch optimizes a perturbation on a weak-semantic image constructed from the dataset mean image with small Gaussian noise resampled at each iteration. Since this weak-semantic image contains little clear visual content, its optimization reflects surrogate responses more than image semantics, and its reference gradient estimates surrogate-specific bias. DeBias-Attack removes the aligned projection of the main gradient on the reference gradient before updating the adversarial image, then performs context-aware text substitution using the updated adversarial image. DeBias-Attack is the first transfer-based VLP attack that corrects surrogate-specific bias through gradient correction. Experiments show strong performance across VLP models, downstream tasks, and open-source and closed-source multimodal large language models.

3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of 3DGS models across digital platforms create pressing challenges for intellectual property protection and forensic traceability. To address this, we propose GaussTrace, a novel framework for constructing directed provenance graphs for 3DGS models. GaussTrace formulates provenance analysis as an evidence-based reasoning problem. It builds upon attribute-wise statistical profiling of 3DGS parameters to capture intrinsic properties. Moreover, we introduce hypothesis-driven editing simulations of common operations to provide auxiliary evidence for plausible transformation pathways. These statistical and simulated cues jointly enable a Large Language Model (LLM) to perform structured Chain-of-Thought (CoT) reasoning, yielding directional provenance inferences and explainable edge reasons. Experimental results demonstrate that GaussTrace effectively constructs evolutionary relationships among diverse 3DGS models, delivering accurate, interpretable, and robust provenance graphs without requiring model training or access to editing histories. Project page: https://haolianghan.github.io/GaussTrace.

Image steganalysis, the detection of hidden information embedded in digital images, is a core component of modern cybersecurity and digital forensics. Recent residual Transformer architectures, such as the Pixel-Difference-Convolution and Enhanced-Transformer-Network (PENet) [1], achieve strong detection accuracy, but their computational and memory demands hinder deployment in resource-constrained settings. We present PENet+, a lightweight steganalysis framework that preserves PENet's discriminative structure while substantially improving efficiency. Rather than redesigning or compressing the attention blocks, we retain PENet's self-attention topology for reproducibility and add a classifier-streamlining stage that progressively narrows the SPP-to-FC1 input channels (SPP: spatial pyramid pooling; FC1: first fully connected layer), yielding large reductions in parameters and FLOPs with negligible accuracy loss. We further refine the high-pass-filter (HPF) stem with an activation-aware mechanism that aggregates HPF responses early and selects a balanced SRM-Gabor top-K subset, and we replace PENet's backbone with a MobileNetV2-style inverted residual network. A balanced configuration with K=31 filters (16 Gabor + 15 SRM) matches or surpasses heavier settings at lower compute. Finally, we motivate PReLU from a steganalysis standpoint, arguing that preserving negative responses helps capture weak stego cues that ReLU suppresses. On a disjoint ALASKA2 JPEG QF90 protocol at 512x512 resolution (5,000 cover images for training, validation, and internal testing; a separate 19,000-cover evaluation set), PENet+ achieves up to 45.5% fewer parameters and about 97% fewer FLOPs than the re-evaluated PENet baseline, offering a computationally efficient direction for resource-constrained steganalysis. Device-level latency and power measurements remain future work.

Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacrifice accuracy. We introduce Face-Fairness (FF), a plug-and-play framework for bias mitigation. Our primary contribution, Face-Feature Tuning (FFT), is the first demographic label-free fairness method demonstrated for deepfake detection: a lightweight calibrator that performs a logit remapping conditioned on frozen face embeddings. We complement FFT with two variants: FF-Max, which maximizes worst-group accuracy when demographics are available, and FF-Discover, which does the same with embedding-discovered groups. Across in-domain and cross-dataset test settings, FF consistently reduces FPR/TPR gaps and improves minimum group accuracy while maintaining (often improving) overall accuracy. The approach is detector-agnostic, adds negligible runtime overhead, and requires no access to identity attributes.

With the growing concerns over copyright infringement in diffusion-based customization, adversarial attacks have emerged as a prominent defense strategy to prevent malicious content forgery in personalized image generation. However, current defenses typically introduce persistent perturbations in the latent space of Latent Diffusion Models (LDMs), which remain susceptible to adaptive bypasses by adversaries. In this paper, we introduce Two-Stage Latent Feature Optimization (TS-LFO), an efficient and effective copyright-stealing attack against protected diffusion-based customization. We begin by observing that existing defenses primarily disrupt the mapping between input images and their latent representations, thereby degrading the model's ability to produce personalized outputs. To counteract this, TS-LFO restores the broken mapping through a two-stage optimization process. In the Latent Denoising Stage, we enhance semantic consistency between latent codes and input images by jointly minimizing a Latent-Image Alignment Loss and a Latent Diffusion Loss with timestep-dependent weights, effectively suppressing the high-frequency noise introduced by defenses. In the Latent Reconstruction Stage, we recover low-frequency semantic information using pixel-level constraints to refine the latent features. Extensive experiments show that TS-LFO consistently bypasses state-of-the-art (SOTA) copyright defenses and outperforms SOTA copyright attacks such as DiffPure, GrIDPure and IMPRESS across diverse settings.

Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output. However, their reliability is strongly affected by how feature removal is implemented: externally selected baselines can introduce bias, out-of-distribution samples, and unstable explanations, while in nonlinear models the occlusion of a set of features can also alter the contribution of non-occluded features. We refer to this effect as attribution shift, as the attribution scores of the non-occluded features drift from their initial values. To challenge these major issues that render explanations unstable, we introduce XtrAIn, a training-guided attribution method that transfers the occlusion operation from the input space to the parameter space. Instead of replacing input values with hand-crafted baselines, XtrAIn follows the model's training trajectory and measures how feature-associated parameter updates affect the output logits. We further introduce Xstep, a lightweight approximation for reducing computational cost, and XtrAIn+, a target-focused variant that emphasizes updates aligned with the target class. Experiments on controlled image datasets and PAM50 breast-cancer subtype classification show that the proposed methods produce cleaner and more interpretable attribution patterns than standard attribution baselines. Overall, XtrAIn provides a training-aware perspective on feature attribution and offers a useful diagnostic tool for studying how feature-level evidence is formed during training.

Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification. However, interpreting their predictions is challenging due to the size and complexity of these models. State-of-the-art saliency methods generate local explanations highlighting the area in the input image where a class is identified but cannot explain how a concept of interest contributes to the prediction. On the other hand, concept-based methods, such as TCAV, provide insights into how sensitive the network is to a human-defined concept but cannot compute its attribution in a specific prediction nor show its location within the input image. We introduce Visual-TCAV, a novel explainability framework aiming to bridge the gap between these methods by providing both local and global explanations. Visual-TCAV uses Concept Activation Vectors (CAVs) to generate class-agnostic saliency maps that show where the network recognizes a certain concept. Moreover, it can estimate the attribution of these concepts to the output of any class using a generalization of Integrated Gradients. We evaluate the method's faithfulness via a controlled experiment where the ground truth for explanations is known, showing better ground truth alignment than TCAV. Our code is available at https://github.com/DataSciencePolimi/Visual-TCAV.

Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial examples (AEs). While test-time defenses are promising, existing methods fail to provide sufficient robustness against strong attacks and are often hampered by high inference latency and task-specific applicability. To address these limitations, we start by investigating the intrinsic properties of AEs, which reveals that AEs exhibit severe feature inconsistency under progressive frequency attenuation. We further attribute this to the model's inherent spectral bias. Leveraging this insight, we propose an efficient test-time defense named Contrastive Spectral Rectification (CSR). CSR optimizes a rectification perturbation to realign the input with the natural manifold under a spectral-guided contrastive objective, which is applied input-adaptively. Extensive experiments across 16 classification benchmarks demonstrate that CSR outperforms the SOTA by an average of 18.1% against strong APGD with modest inference overhead. Furthermore, CSR exhibits broad applicability across diverse visual tasks. Code is available at https://github.com/Summu77/CSR.

Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious background correlations. As a result, modern vision models remain brittle and difficult to interpret. We propose Energy-Regularized Spatial Masking (ERSM), a novel framework that reformulates feature selection as a differentiable energy minimization problem. By embedding a lightweight Energy-Mask Layer inside standard convolutional backbones, each visual token is assigned a scalar energy composed of two competing forces: an intrinsic Unary importance cost and a Pairwise spatial coherence penalty. Unlike prior pruning methods that enforce rigid sparsity budgets or rely on heuristic importance scores, ERSM allows the network to autonomously discover an optimal information-density equilibrium tailored to each input. We validate ERSM on convolutional architectures and demonstrate that it produces emergent sparsity, improved robustness to structured occlusion, and highly interpretable spatial masks, while preserving classification accuracy. Furthermore, we show that the learned energy ranking significantly outperforms magnitude-based pruning in deletion-based robustness tests, revealing ERSM as an intrinsic denoising mechanism that isolates semantic object regions without pixel-level supervision.

The evolution and dissemination of AI-synthesized images is occurring at an unprecedented rate. Image generators are making rapid progress in their goal of perfectly imitating natural images, which also challenges image forensics. In this work, we exploit an underexplored cue in current generative models, namely their weakness to imitate color statistics of natural images. We first show that the LPIPS loss used for training image generators is less sensitive to chrominance than to luminance, which may lead to statistical discrepancies in the colors of synthetic images. Building on this observation, we then introduce six hand-crafted color transformations and a method to learn a task-optimized color transform to statistically expose generated images. These transformations can be used in various ways. First, we define color-sensitive features at pixel-level or patch-level. A simple, interpretable classifier achieves with these features an average generalization accuracy of 93.27% and strong robustness against six types of post-processing. Second, we demonstrate that the transformations exhibit characteristic visual noise patterns in natural and synthetic image areas, which enables an intuitive visual image evaluation. Third, we demonstrate that the transforms can enhance color patterns in generated images for improved multiclass attribution.

Watermarking is becoming the default mechanism for AI content authentication, with governance policies and frameworks referencing it as infrastructure for content provenance. Yet across text, image, and audio modalities, watermark signal strength, detectability, and robustness depend on statistical properties of the content itself, properties that vary systematically across languages, cultural visual traditions, and demographic groups. We examine how this content dependence creates modality-specific pathways to bias. Reviewing the major watermarking benchmarks across modalities, we find that, with one exception, none report performance across languages, cultural content types, or population groups. To address this, we propose three concrete evaluation dimensions for pluralistic watermark benchmarking: cross-lingual detection parity, culturally diverse content coverage, and demographic disaggregation of detection metrics. We argue that watermarking is part of the pluralistic alignment pipeline and should be held to the same evaluation standards. We connect this to governance frameworks currently mandating watermarking deployment without requiring fairness evaluation. Our position is that evaluation must precede deployment, and that the same bias auditing requirements applied to AI models should extend to the verification layer.

The paradigm of digital twin cities is shifting from coarse visual mapping toward more precise and actionable digitization of urban assets. However, existing datasets predominantly focus on coarse visual perception, lacking the strict multi-modal alignment and attribute and status diagnosis required for automated infrastructure maintenance. To bridge this gap, we introduce WHU-Infra3D, a large-scale, multi-modal benchmark dataset dedicated to roadside infrastructure inventory. Covering 53.8 km across three cities, WHU-Infra3D uniquely integrates panoramic imagery and LiDAR point clouds with rigorous 2D-3D instance association and cross-frame tracking. Comprising over 175k multi-view 2D bounding boxes alongside thousands of 3D infrastructure instances, the dataset provides over 181k detailed attribute and status annotations (e.g., rust, occlusion) to empower operational health assessment. We establish comprehensive baselines across five core tasks: 2D detection, 2D cross-view matching, 3D geo-identification, 3D point cloud segmentation, and attribute recognition. Extensive evaluations expose significant cross-city domain gaps and inherent vulnerabilities of current models on long-tailed defective statuses, establishing WHU-Infra3D as an essential testbed for advancing scalable, AI-driven urban infrastructure inventory and lifecycle management. The WHU-Infra3D dataset is available at https://github.com/WHU-USI3DV/WHU-Infra3D.

Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for years, yet reported accuracy assumes these examples were absent from pretraining. We audit open VLMs on SLAKE-En, PathVQA, VQA-RAD, and an auxiliary public OmniMedVQA mirror using four detector families: image-side near-neighbour overlap against PMC-OA-beta, canonical-order exchangeability, cohort-relative Min-K%++ tail enrichment, and cross-model top-K overlap. We find measurable image-side source overlap on SLAKE-En: 19.8% of images are flagged under SigLIP-B-16 and 4.2% under SigLIP-SO400M, while out-of-domain controls produce 0/2000 flags. Manual adjudication shows same-modality, same-projection matches to different patients rather than verified pixel-level duplicates, so we interpret this as source or distributional overlap rather than confirmed per-image memorization. On the text side, Qwen2.5-VL on SLAKE-En shows a canonical-order exchangeability signal that survives ordering ablation and external non-medical baselines. On the OmniMedVQA mirror, exchangeability fires for five medical and general VLMs while BLIP-2 remains clean. In contrast, cohort-relative Min-K%++ tail enrichment and cross-model top-K overlap collapse under an external pre-domain baseline: BLIP-2 reproduces the apparent positive signals despite lacking plausible medical-VQA exposure. We conclude that these cohort-relative detectors are unreliable as standalone membership-inference signals on small medical-VLM cohorts.

Reliable evaluation of instance segmentation models requires metrics that accurately and consistently reflect segmentation quality. However, the metrics most widely used in biological imaging carry fundamental mathematical weaknesses: hard Intersection-over-Union (IoU) thresholds that produce discontinuous, low sensitivity scoring; per-object normalization that distorts scores under object size variation; and greedy or one-to-many matching procedures that yield non-optimal, order-dependent correspondences. Together, these properties produce unintuitive and unreliable model rankings under common failure modes such as split cells, merged cells, and cell boundary imprecision. We propose Maximum Matching Accuracy (MMA), a threshold-free continuous metric that finds a globally optimal one-to-one matching between predicted and ground truth objects and aggregates total overlap using per-pixel normalization. We evaluate MMA against AP@50, PQ, SEG, and AJI across three experiments: synthetic failure cases, progressive corruption tests, and a model ranking comparison. MMA produces scores that are more stable, more sensitive, and more interpretable than existing alternatives, providing a principled foundation for fair instance segmentation benchmarking in biological cell imaging.

Semantic segmentation in remote sensing requires costly pixel-level annotations, and nearly every problem demands a new dataset since models rarely transfer across sensors, platforms, or geographies. Existing human-in-the-loop frameworks expand sparse clicks into dense supervision via auxiliary machinery (pseudo-labels, propagation, CRFs, foundation-model prompts, auxiliary heads), all operating on the model's predictive distribution. A confidently wrong pixel is indistinguishable from a confidently correct one in that distribution by construction, so no rule reading it can separate the two; the distinguishing signal is external to the model. This paper hypothesizes that expert clicks targeting confident model errors, not arbitrary pixels, suffice to match dense supervision, with no expansion machinery. iSAGE (Iterative Sparse Annotation Guided by Expert) realizes this hypothesis on an integrated open-source platform, where an error-weighted loss amplifies the gradient at each click and the annotation record itself is the dataset, extensible, correctable, and auditable. Experiments use a minimum-effort regime: at most one labeled pixel per class per frame. On BsB Aerial, iSAGE recovers 97.2% of dense supervision (74.79% mIoU on 0.040% of pixels) with contrasting class dynamics: amorphous classes (permeable areas) saturate from the seed, while small classes (cars) require late-iteration effort. On ISPRS Vaihingen (external benchmark), iSAGE reaches 76.78% mIoU with 0.011% of pixels, matching the dense baseline (76.65%) and exceeding all published methods. Under the same pipeline, four output-reading mechanisms (oracle entropy across budgets 1--100x, pseudo-labels across thresholds 0.90--0.99, CRF-based propagation, uniform random) plateau 7.4 to 14.5 pp below iSAGE. Across 31 surveyed methods, iSAGE is the only iterative human-in-the-loop framework operating without auxiliary machinery.

Recent advances in 3D generation have led to substantial improvements in realism, controllability, and efficiency, yet the evaluation of 3D assets remains underexplored. Existing evaluation paradigms, including human evaluation, learned metrics, and vision-language models (VLMs) as judges, suffer from limitations in cost, scalability, resolution handling, or task-specific alignment. In this work, we focus on 3D mesh evaluation and introduce DB-3DME, the Dataset and Benchmark for 3D Mesh Evaluation. DB-3DME contains 2,619 synthetic 3D meshes paired with human ratings on Geometry and Prompt Adherence. Using this dataset, we systematically benchmark state-of-the-art VLMs and identify visual encoding of 3D representations as a key factor for human-aligned evaluation performance. Motivated by this finding, we fine-tune an open-weight VLM, Qwen-2.5-VL-7B, for 3D mesh evaluation by adapting the visual encoder while freezing the language model. The fine-tuned model substantially outperforms existing pre-trained VLMs across multiple evaluation dimensions, establishing a new benchmark for automatic 3D mesh evaluation. We publicly release the benchmark dataset on GitHub and Hugging Face to facilitate future research.

Wildfire detection and monitoring are critical for mitigating fire spread and reducing environmental and infrastructural damage. In this work, we introduce GWFP (Global Wildfire Prevention Dataset), a large-scale, open-source dataset of wildfire images and videos designed to support early fire and smoke detection research. GWFP contains geographically diverse wildfire scenes, including flames, smoke, Waterdog/Fog environmental conditions, Near Infrared (NIR) imagery, Ember, and challenging negative samples collected from real-world scenarios worldwide. To evaluate dataset robustness and cross-domain generalization, we benchmark multiple convolutional and transformer-based architectures across both in-domain and cross-dataset settings. Additionally, we explore lightweight frequency--spatial feature interaction using Hadamard-enhanced residual connections (HTE-ResNet) to analyze representation robustness under domain-shift conditions. Experimental results demonstrate strong cross-dataset generalization and practical utility for real-world wildfire monitoring applications. The dataset and source code will be publicly released upon acceptance.

Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose this subset from fixed architectural heuristics rather than using dynamic, task-aware criteria. We introduce \textbf{FisherAdapTune}, a Fisher-guided Adaptive Fine-Tuning framework that progressively selects parameter groups by tracking the temporal drift of their Fisher geometry. Starting from a PAC-Bayesian view of fine-tuning, we decompose the generalization error bound into Fisher-weighted update costs and show that parameter groups whose curvature contribution has stabilized can be frozen to reduce the error bound without interrupting the remaining adaptation dynamics. FisherAdapTune formulates this criterion with a scale-invariant Jensen-Shannon distance between consecutive Fisher distributions, yielding an adaptive active parameter set. We evaluate our approach on a downstream segmentation task, and results show FisherAdapTune improves the in-distribution performance and zero-shot transfer in multiple settings, validating that Fisher structural drift is a useful signal for efficient, task-aware adaptation. We release our \href{https://github.com/AtlasAnalyticsLab/FisherAdapTune}{code} publicly to enable further application of our proposed approach.

Parameter-Efficient Fine-Tuning (PEFT) methods provide a streamlined and efficient tool for adapting large models to domain-specific multimodal downstream tasks. Although these methods proved their tangible effects in practice, their principal aspects remain under-explored. Therefore we remain curious about the underlying generalization mechanisms in various PEFT methods and how they can be further enhanced. In this paper, we reveal the flatness preference widely present in various PEFTs, where a small fraction of sharp dimensions dominates the generalization of PEFT. This finding suggests an appealing possibility: we may be satisfied with a better generalization by merely attending to this small fraction of sharp dimensions instead of all of them. Furthermore, we propose Flatness Preference Optimization (FlatPO) to flatten these key sharpness dimensions, leading various PEFTs toward better generalization. Extensive experiments demonstrate the effectiveness of our findings and the proposed method. Code is available at https://github.com/Can-Lin/FlatPO.

Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood. Practical workflows such as storyboarding, step-by-step illustration, reference-guided editing, and video previsualization require models to preserve identities, objects, spatial relations, and causal order across multiple visual states. Existing evaluations largely measure single-image correctness, compositional alignment, or video quality, leaving open whether an image model can coherently imagine a temporally ordered process. We introduce ImageTime, a diagnostic benchmark that uses spatiotemporal consistency as a behavioral probe of visual world modeling in image generation. Given an action instruction, and optionally a reference image specifying the initial state, a model must generate one image containing four ordered key states: initial state, action onset, transition state, and final state. This four-keyframe protocol is more temporally demanding than single-image generation while avoiding the confounds of dense video dynamics. ImageTime organizes tasks with a progressive capability hierarchy and decomposes each scenario into stage-wise state predicates, cross-frame temporal constraints, and forbidden causal violations. GPT-5.5 scores all generated images under a structured VLM-as-judge protocol, producing interpretable capability scores, diagnostic subscores, and failure labels. Through multi-family benchmarking, ImageTime reveals where current image generation systems succeed, fail, and drift when asked to maintain coherent visual world states over time.

Annotation errors are widespread in computer vision datasets and can significantly degrade the performance of systems trained on them, particularly in complex tasks such as object detection. Several approaches exist to identify annotation errors, including training-free feature-space methods which provide a fast and interpretable way to analyze annotations. However, the behavior on object detection annotations, which include semantic and spatial information, remains largely unexplored. In this work we analyze the applicability of feature-space-based approaches for detecting annotation errors in object detection datasets. By adapting an existing feature-space method, we show that such approaches reliably expose semantic mislabel, while positional errors remain difficult to detect. We evaluate this behavior across multiple pretrained embedding models, synthetic noise types (symmetric, asymmetric, and positional), and real-world annotation errors using VOC2012 and KITTI. All code and real-world corruptions are publicly available at the following repository: https://github.com/ ChristianSieberichs/BoundingBox\_corruption\_detection

Existing hand detection algorithms work on images and the detection rate is restricted by the frame rate of the camera. In hand detection applications for moving robotic systems, conventional cameras cause motion blur, especially in darker lighting conditions. We can leverage the use of event-based cameras which possess a high dynamic range, high temporal resolution, and low power consumption. Recent work has shown that using a stereo setup of an event-based and a frame-based camera improves detection accuracy and the bandwidth-latency tradeoff. The main bottleneck in using event-based cameras in object detection and recognition tasks is a relatively low amount of training data. In this work, we propose a methodology and an exemplary synthetic event-based hand dataset from an egocentric, first-person view perspective. The data is synthesized from the existing RGB Egohands dataset with the v2e toolbox. Parameters of the v2e toolbox are varied to provide versions of the dataset with different lighting conditions and scales. Ground truth detections are generated with a fine-tuned YOLOv8 model which is applied to the RGB images in the Egohands dataset and interpolated on the high-temporal resolution events. We use the multi-modal dataset to perform hand detection with existing object detection algorithms which use a multi-modal setup of event and RGB cameras and demonstrate performance comparable to the state-of-the-art.

This paper presents an overview of the inaugural PortraitCraft Challenge, held as one of the official competitions at CVPR 2026. The challenge focuses on portrait composition understanding and generation, aiming to advance AI research in portrait aesthetics analysis and controllable image synthesis. Unlike existing datasets and tasks that primarily focus on global aesthetic scoring, PortraitCraft introduces a unified evaluation framework comprising two complementary tracks. Track 1 requires models to perform structured portrait composition understanding, and Track 2 requires models to generate portrait images from structured composition descriptions under explicit compositional constraints. To support the challenge, we constructed and publicly released a large-scale portrait composition dataset consisting of approximately 50,000 curated real portrait images, providing multi-level supervision. This report describes the challenge setup, evaluation protocols, dataset composition, and final results, along with an analysis of the technical characteristics of the submitted solutions. The PortraitCraft Challenge provides a standardized and reproducible platform for research on portrait composition understanding and generation, and is expected to foster further progress in the fields of portrait aesthetics and controllable image generation.

Visual in-Context Learning (VICL) aims at making progress towards adaptive vision models, that can -- based on a few examples -- adapt to a new task at test-time. With the history of in-context learning in natural language processing research, where large, parameter-heavy models are in use, one pathway that current VICL methods take is model- and data-scaling as key ingredients. Yet, it is not clear, whether these ingredients are the key for in-context learning to take shape in vision models. To stress-test such large models, we challenge them with an extreme counterexample: we train a tiny visual in-context model with merely $1$ million parameters and a modest amount of $70,000$ images. We compare the results of this severely capacity capped tiny model to $7,000\times$ larger VICL models in different adaptive settings, (1) on image data with small distribution shifts, (2) on unseen task encodings and (3) on a completely new task, i.e., the setting VICL envisions. With the chasm of training resources between the tiny- and large models, our experiments showcase a lack in how adaptive capabilities are measured, with respect to how tasks are encoded, which tasks were used in pre-training and the choice of metrics. These gaps in current VICL benchmarking underscore a need for innovation in evaluation of adaptive capabilities.

Visual in-context learning has been proposed as a pathway towards dynamic models that can generate predictions based on a provided context and thereby can adapt to new vision tasks at test-time. Yet, the evaluation of the adaptation capabilities of these models has been limited to narrow setups that mainly mirror tasks or image domains from pre-training for which real adaptation is not required. We address this gap by constructing a broad Visual In-Context BEnchmark (VIBE) with a focus on diverse imaging domains and a wide range of tasks. With this, we are able to get a much clearer picture of the adaptive capabilities of visual in-context models when faced with new image- and task distributions. We stress test six models on $14$ datasets and $12$ tasks (in total, we explore $106$ dataset-task combinations) and compare them under a unified, reproducible evaluation protocol, in an one-shot setting. Our evaluation uncovers key insights on the state of visual in-context learning, including limitations, systematic failure modes and promising directions. To foster broader evaluation, we will openly release our VIBE toolkit.

We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchmarks often focus on visual quality, semantic alignment, or short-term temporal coherence, they provide limited insight into whether generated videos obey physical rules, preserve coherent 3D structure, and sustain controllable interactions over long horizons. To address this gap, WorldOlympiad decomposes world-model evaluation into three complementary dimensions. The physical track uses object segmentation and MLLM-as-judge to assess whether generated videos follow interpretable rules in mechanics, thermal phenomena, and material properties. The geometry track reconstructs generated videos with Gaussian splatting and evaluates structural consistency, cross-view coherence, and camera-trajectory alignment. The interaction track assesses whether generated rollouts follow complex action prompts and maintain smooth, coherent transitions across consecutive video chunks. WorldOlympiad further covers three major downstream scenarios, including gaming, robotics, and general real-world videos, capturing diverse challenges from interactive control and embodied manipulation to open-domain motion and camera dynamics. Together, these tracks and scenarios form a scalable and interpretable evaluation suite that exposes failure modes beyond generic video quality. Experiments on state-of-the-art models reveal substantial gaps in physical reasoning, 3D consistency, and long-horizon interaction, underscoring the need for more structured evaluation protocols for generative world models.

Cryo-electron tomography (cryoET) has emerged as a powerful tool in structural and cellular biology by enabling direct visualization of macromolecular structures within intact cells, thereby linking molecular architecture to cellular organization in a native context. Realizing the full potential of cryoET, however, increasingly depends on advances in computational analysis, particularly machine learning (ML), to interpret its complex and information-rich data. Despite rapid progress, ML development for cryoET remains bottlenecked by the lack of standardized, well-annotated benchmarks. Existing evaluations are typically small, task-specific, and are assembled in isolation, limiting robust comparisons across methods. Here, we present POPSICLE, a benchmark suite for cryoET segmentation and macromolecular localization built from the CryoET Data Portal - an open, ML-ready repository of tomographic data, metadata, and annotations. POPSICLE spans eukaryotic and prokaryotic systems, both purified and fully in situ samples, and dense voxel-wise segmentation as well as sparse localization tasks. Built on a living data resource, it can expand as new datasets and annotations become available. Baseline experiments reveal substantial variation in model rankings across tasks, underscoring the need for benchmarks tailored to the unique characteristics of cryoET rather than evaluation practices adapted from adjacent biomedical imaging domains. POPSICLE thus provides an open and extensible foundation for reproducible ML evaluation in cryoET.

Vision Transformers (ViTs) often need to be compressed for deployment on resource-constrained edge devices like drones and smart vehicles. However, existing model compression methods ignore that many edge devices only require the knowledge of specific classes for their applications. As a result, the derived all-class ViTs retain redundant knowledge and perform suboptimally on these classes. We discovered that simply replacing the calibration dataset with class-specific data does not suffice to address this issue, as these methods face two fundamental limitations. First, they overlook the existence of class-detrimental weights, which interfere with specialization, while removing them can improve class-specific performance. Second, the diversity of target classes and resource constraints on edge devices demand numerous customized models. Existing methods are time-consuming and computationally expensive, thus unscalable. In this work, we present NuWa, a cost-efficient method that addresses these challenges by deriving small ViTs from base ViTs for edge devices with specific class requirements. NuWa performs self-knowledge purification to prune class-detrimental weights and efficiently derives compact ViTs through closed-form optimization. Without post-pruning retraining, the derived edge ViTs surpass the base ViT in class-specific accuracy and accelerate inference. Comprehensive experiments demonstrate that NuWa outperforms state-of-the-art training-free pruning methods on class-specific tasks by up to 29.00\% in accuracy. Compared with the best-performing training-dependent pruning method, NuWa achieves a 33.69x pruning speedup and reduces pruning cost by up to 99.83\%, with only a 0.61\% average accuracy loss. Project Page: https://github.com/CGCL-codes/NuWa.

Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, limiting comparison and real-world relevance. We introduce CleanPatrick, the first large-scale benchmark for data cleaning in the image domain, built upon the publicly available Fitzpatrick17k dermatology dataset. We collect 496,377 binary annotations from 933 medical crowd workers, identify off-topic samples (4%), near-duplicates (21%), and label errors (32%), and employ an aggregation model inspired by item-response theory followed by expert review to derive high-quality ground truth. CleanPatrick formalizes issue detection as a ranking task and employs standard ranking metrics that mirror real audit workflows. We benchmark classical anomaly detectors, perceptual hashing, SSIM, Confident Learning, NoiseRank, FINE, BHN, and SelfClean. On CleanPatrick, self-supervised representations excel at near-duplicate detection, classical methods achieve competitive off-topic detection under constrained review budgets, and detecting implausible labels under conservative human judgment remains challenging for fine-grained medical classification. By releasing both the dataset and the evaluation framework, CleanPatrick enables a systematic comparison of image-cleaning strategies.

While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space. Such visual thinking paths not only provide step-by-step exploration and verification as an AI detective but also produce better interpretations of the final answers. However, these paths are challenging to evaluate due to the large exploration space of intermediate steps. To bridge the gap, we develop an evaluation suite, ``Visual Reasoning with multi-step EXploration (V-REX)'', which is composed of a benchmark of challenging visual reasoning tasks requiring native multi-step exploration and an evaluation protocol. V-REX covers rich application scenarios across diverse domains. V-REX casts the multi-step exploratory reasoning into a Chain-of-Questions (CoQ) and disentangles VLMs' capability to (1) Planning: breaking down an open-ended task by selecting a chain of exploratory questions; and (2) Following: answering curated CoQ sequentially to collect information for deriving the final answer. By curating finite options of questions and answers per step, V-REX achieves a reliable quantitative and fine-grained analysis of the intermediate steps. By assessing SOTA proprietary and open-sourced VLMs, we reveal consistent scaling trends, significant differences between planning and following abilities, and substantial room for improvement in multi-step exploratory reasoning.

Current state-of-the-art multi-class unsupervised anomaly detection (MUAD) methods rely on training encoder--decoder models to reconstruct anomaly-free features. However, we argue that such task-specific training is costly under distribution shifts, and that reconstruction-based residual scoring further faces a fidelity--stability dilemma. Existing training-free alternatives, in turn, remain prone to cross-category and cross-region mismatches in MUAD. Motivated by these limitations, we propose Retrieval-based Anomaly Detection (RAD), a task-specific training-free framework that stores anomaly-free features in a memory and detects anomalies through multi-level retrieval, matching test patches against the memory. Experiments demonstrate that RAD achieves state-of-the-art performance across four established benchmarks (MVTec-AD, VisA, Real-IAD, 3D-ADAM) under both standard and few-shot settings. On MVTec-AD, RAD reaches 96.7% Pixel AUROC with just a single anomaly-free image compared to 98.5% of RAD's full-data performance. Collectively, these findings overturn the assumption that MUAD requires task-specific training, showing that state-of-the-art anomaly detection is feasible with training-free memory-based retrieval. Our code is available at https://github.com/longkukuhi/RAD.

Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks either rely on image-centric or subjective metrics insensitive to structure, or evaluate intermediate symbolic representations rather than final rendered images, leaving pixel-based diagram generation underexplored. We introduce SciFlow-Bench, a structure-first benchmark for evaluating scientific diagram generation directly from pixel-level outputs. Built from real scientific PDFs, SciFlow-Bench pairs each source framework figure with a canonical ground-truth graph and evaluates models as black-box image generators under a closed-loop, round-trip protocol that inverse-parses generated diagram images back into structured graphs for comparison. This design enforces evaluation by structural recoverability rather than visual similarity alone, and is enabled by a hierarchical multi-agent system that coordinates planning, perception, and structural reasoning. Experiments show that preserving structural correctness remains a fundamental challenge, particularly for diagrams with complex topology, underscoring the need for structure-aware evaluation.

Despite their empirical success across a wide range of generative tasks, the fundamental principles underlying the ability of diffusion models to learn data distributions are poorly understood. In this work, we develop a new mathematical framework that explains how diffusion models can effectively learn low-dimensional distributions from a finite number of training samples without suffering from the curse of dimensionality. Specifically, motivated by the intrinsic low-dimensional structure of image data, we theoretically analyze a setting in which the data distribution is modeled as a mixture of low-rank Gaussians. Under suitable network parameterization, we show that optimizing the training objective of diffusion models is equivalent to solving the canonical subspace clustering problem over the training samples, where each subspace basis corresponds to the low-rank covariance of a Gaussian component. This equivalence allows us to show that the sample complexity for learning the underlying distribution scales linearly with the intrinsic dimension of the data, rather than exponentially with the ambient dimension. Our theoretical findings are further supported by empirical evidence that demonstrates phase transition phenomena in generalization on both synthetic and real-world image datasets. Moreover, we establish a correspondence between the learned subspace bases and semantic attributes of image data, providing a principled foundation for controllable image generation.

Generative models guided by text prompts are widely evaluated for fidelity and prompt alignment, yet their ability to produce outputs remains underexplored. Existing diversity metrics such as Vendi and RKE, which are based on the von Neumann and Rényi entropies of kernel matrices, were developed for unconditional models and cannot distinguish prompt-induced from model-induced variability. We address this gap by introducing \textit{Conditional-Vendi} and \textit{Conditional-RKE}, diversity measures derived from the conditional entropy of positive semidefinite matrices. These scores isolate model-induced diversity in prompt-guided generation, with Conditional-RKE enjoying an $O(1/\sqrt{n})$ convergence rate. For Conditional-Vendi, we introduce a truncated-spectrum approximation that yields scalable and consistent estimates. Experiments on text-to-image, image-captioning, and LLM tasks show that the conditional scores recover ground-truth diversity orderings and can also guide diffusion models toward more diverse samples. The codebase is available at https://github.com/mjalali/conditional-vendi.

Weed pressure in forage corn production causes yield losses of up to 31.5%, yet site-specific weed management (SSWM) systems built on UAV imagery and deep learning remain constrained by the scarcity of field-representative training datasets. We present USU-Corn-WeedDB, a publicly available UAV RGB image dataset collected from a commercial forage corn field in Cache Valley, Utah, designed to support multi-class weed detection under both supervised and semi-supervised learning frameworks. RGB imagery was acquired on 27 June 2025 using an Autel EVO II Dual 640T V2 drone at ~10m above ground level, yielding a ground sampling distance of approximately 0.48 cm/pixel. A total of 366 full-resolution images were tiled into 8,800 patches at 640 x 640-pixel resolution. Of these, 800 images were manually annotated for three weed species; common lambsquarters (Chenopodium album), redroot pigweed (Amaranthus retroflexus), and green foxtail (Setaria viridis) comprising 10,539 bounding-box instances, with the remaining 8,000 tiles retained as an unlabeled pool for semi-supervised experiments. This dataset reflects a natural class imbalance where redroot pigweed constitutes 53.86% of annotated instances, which was preserved intentionally to mirror real field conditions. To validate dataset utility, we trained 28 object detection models spanning five architecture families including YOLOv8, YOLOv9, YOLOv10, YOLO11, YOLO26, and RT-DETR under identical conditions without hyperparameter tuning. Test set mAP@0.5 ranged from 0.773 to 0.840, with lightweight models achieving competitive performance relevant to edge-deployed UAV systems. USU-Corn-WeedDB is publicly available at https://doi.org/10.5281/zenodo.20044178.

Multi-task vehicle routing problems play a critical role in enhancing efficiency across various industries and service sectors. These problems consist of multiple variants that optimize routing costs while meeting diverse customer constraints. Existing multi-task VRP solvers solely utilize a graph-based modality, limiting their ability to address variants with multiple constraints. As a format to represent complex semantics, vision modality shows great potential for encoding diverse VRP constraints. This motivates us to learn patch-level semantics from the vision images, and then integrate them into a graph-based model to solve various VRP variants simultaneously. However, directly applying this approach to multi-task VRPs presents three challenges: 1) existing VRP images lack constraint representations, which are essential for multi-task VRPs, 2) the fixed receptive field of individual patches cannot effectively accommodate varying requirements across tasks, and 3) imbalanced pixel distribution among constraints may cause the model to overlook constraints with fewer pixels. In this paper, we propose a vision-assisted foundation model (VaFM) to address these challenges. In the vision modality, input images tailored to all constraints are encoded by a convolutional neural network. The obtained patch embeddings are fused with graph-based nodes to generate solutions, with an auxiliary task designed to address the pixel-imbalanced issue. The performance of VaFM is evaluated across 16 different VRP variants. The experimental results demonstrate the superiority of VaFM over state-of-the-art methods, especially for variants with complex constraints.

There is no doubt that over the last decade, techniques from the field of machine learning have revolutionized how we process and interpret data, especially images and text. For underwater observations acoustics is a primary source of information, and naturally, deep learning methods have been applied to echograms and other acoustics data, but so far with rather modest results. Here, we argue that due to intrinsic properties of acoustic data, substantial advances will likely require research into deep learning methods beyond mere recycling of models and techniques from image processing. Currently, the potential for breakthroughs in method development is hindered by the lack of standard data formats and organization, and even more by the lack of readily available, high quality data sets with established performance goals. To advance the field, these shortcomings should be remedied

In quantum image processing, a fundamental step is encoding classical image data into quantum states. This can be achieved using methods such as Flexible Representation of Quantum Images (FRQI), Quantum Probability Image Encoding (QPIE), and Novel Enhanced Quantum Representation (NEQR). However, on real quantum hardware, these encodings can quickly lead to circuits with many gates, large circuit depth, and high qubit usage, which is a problem for Noisy Intermediate-Scale Quantum (NISQ) devices. In this work, we investigate whether low-rank state approximation, formulated via Schmidt decomposition, can help reduce this complexity. The method keeps only the most significant parts of a quantum state's entanglement structure, making state preparation more efficient while preserving most of the image information. We compare the three encoding techniques in their original form and with low-rank approximation, evaluating metrics such as circuit depth, CNOT count, MSE, and visual quality of reconstructed images. The results reveal meaningful trade-offs between accuracy and resource efficiency, with the FRQI model achieving a 97 percent reduction in circuit depth while maintaining a near-perfect reconstruction (MSE of about 0.27). This demonstrates the potential of low-rank techniques for advancing practical quantum image processing on near-term hardware.

Applying Human Pose Estimation (HPE) in real world environments remains a challenging task, this paper explores and surveys real time HPE approaches and their limitations in sports analysis for individuals, alongside developing a practical lightweight prototype for real world testing and usage. The older marker-based motion capture systems evolving to the modern accessible and adaptable markerless deep learning approaches, this survey explores the foundational architectures, which balance precision and efficiency. We also compare algorithmic frameworks (top-down, bottom-up, one-stage approaches, etc.) on practical deployment metrics such as inference latency, frame rate, mean per-joint position error, and temporal jitter to guide model selection process for sports application. As our prime contribution, we are proposing a modular, lightweight software prototype, which uses MediaPipe HPE framework with multiple exercise specific logic to deliver real-time insights and AI based feedback for non-expert users. We derive sports insights and providing feedback with minimal computational resources, while showcasing the performance and reliability metrics. In the end, we suggest other future research directions like combining sensors, and AR/VR. This work caters to researchers, engineers, sport scientists, etc., as both technical resource and a valid blueprint to implement a similar or improved real-time HPE analysis system for athletic performance enhancement or other purposes.

Building-integrated photobioreactors (PBRs) offer a pathway for carbon-neutral architecture, yet deployment is hindered by configuration complexity and biological maintenance. This paper presents a modular PBR facade system powered by a computational framework reconciling design intent with physical validity. We introduce 'carbon-neutralization bricks' featuring integrated vessel-and-conduit geometry; monolithic fluid channels enable 'plug-and-play' assembly. To navigate the combinatorial complexity of 14 modular geometries, we develop a Computational Sketch-to-Layout Agent that formulates layout synthesis as a Constraint Satisfaction Problem (CSP). Using the CP-SAT engine, the agent treats sparse user sketches as soft priors while enforcing hard constraints like port alignment and global connectivity. This allows non-experts to synthesize fabrication-ready configurations in near real-time. Furthermore, to facilitate autonomous maintenance, we propose a weakly supervised algae health monitoring pipeline. By employing a hybrid CNN-attention backbone and a temporal ranking loss, the system quantifies biological vitality from photographs without absolute ground-truth labels. Experiments demonstrate the CSP solver achieves a 95.5% success rate on grid scales up to 15 x 15. Qualitative evaluations confirm the framework preserves design semantics while ensuring operational integrity. Long-term tests show the vision module produces health trajectories aligned with 14-day biological cycles, suggesting that integrating interactive synthesis with low-cost computer vision can democratize scalable carbon capture systems.

Traditional UV unwrapping relies on direct optimization of geometric distortion energies and can fail through invalid initialization, local minima, or topological foldovers. We recast fixed-chart UV unwrapping as continuous neural reparameterization: an untrained SIREN maps per-vertex mesh features to UV coordinates, and its weights are optimized for a geometric objective. The practical contribution is a robust chart-solver recipe, combining Laplace--Beltrami spectral inputs, Tutte residual warm-up, a $C^2$ determinant extension, an injectivity barrier, and validity-checked retry/fallback routing, rather than a claim that any single component guarantees validity or that recutting methods should be replaced. NTK--LBO diagnostics show that spectral conditioning changes update geometry, especially at initialization and mid-rank subspaces, but does not by itself predict chart success. On compact pre-cut charts and a 47-chart stratified Thingi10K/xatlas-cut benchmark, the neural solver produces zero flips on all compact charts and 42/47 valid zero-flip stratified solves. BFF and OptCuts comparisons sharpen the scope: recutting can be faster and lower-distortion when allowed, while the neural solver targets supplied-chart validity and validation-first atlas construction. On Amara Spatial generated meshes, the full atlas construction path gives packed-atlas coverage on a 25-asset set and 1000/1000 strict locally valid atlases with zero UV flips in a large-scale Rust atlas run after fallback routing.

Attributing a synthetic utterance to its originating system remains an open challenge: closed-set models fail to reject unseen synthesizers and produce overconfident predictions. To address this, we propose a dual-branch gated fusion framework that pairs XLSR-53 with CORES, a 66-dimensional descriptor that, unlike prior Linear Filter Bank (LFB)-only work, spans cepstral, oscillatory, rhythmic, energy, and spectral dimensions to capture complementary synthesis artifacts. Our analysis shows XLSR-53 remains discriminative in-domain (ID) while CORES generalizes stably under distribution shift (OOD), yet their naive concatenation fails due to SSL representational imbalance. To resolve this, an input-conditioned gate adaptively weights each branch under joint training with cross-entropy, an energy margin loss for ID/OOD separation, and a gate diversity term. On the MLAAD benchmark, our system achieves 97.6\% ID accuracy, 4.9\% EERc, and an 83.5\% relative FPR95 reduction over the Interspeech 2025 baseline.

Passive acoustic monitoring enables large-scale observation of wildlife, but most bioacoustic classifiers only predict species presence in a time window without localizing vocalizations precisely in time or frequency, limiting downstream analyses. We formulate bird vocalization detection as an object detection task on spectrograms and train YOLO11 models to localize bird calls in dense tropical soundscapes from Singapore. We additionally introduce an open-source browser-based annotation tool and propose Intersection over Minimum (IoMin), an evaluation metric that better handles ambiguous acoustic boundaries than standard IoU and is better suited to the problem at hand. The best YOLO model nearly doubles baseline performance on in-distribution soundscapes from Singapore (81.8% vs. 42.1% IoMin@50 F1-score) while still outperforming the baseline on unseen out-of-distribution recordings from Hawaii (58.6% vs. 48.6%). These results suggest that object detection frameworks are a promising approach to time-frequency localization of animal vocalizations in complex soundscapes.

Traditional heuristic solvers for the 2D irregular nesting problem share a fundamental limitation: they are blind to polygon geometry, relying on guided brute-force to navigate the continuous placement space with minimal geometrical guidance. In this paper, we argue that Reinforcement Learning is uniquely positioned to overcome this bottleneck. By pairing an optimization policy with a geometry-aware neural encoder, an agent can automatically discover rich geometric priors directly from data, utilizing these learned intuitions to strategically guide exploration. To realize this, we introduce the Polygons Transformer (PoT), a novel architecture that encodes 2D continuous vector geometries while allowing cross-polygons attention. We couple this novel architecture with a Combinatorial Optimization Reinforcement Learning (CORL) training framework to find optimal solutions. To support this paradigm, we release an open-source training dataset derived from complex geographic contours alongside a dedicated evaluation benchmark. Our empirical validation demonstrates that our trained agent achieves area utilization performance highly competitive with Sparrow, the state-of-the-art heuristic solver, proving that reinforcement learning can successfully discover and exploit geometric awareness for precise spatial tasks.

We recast pass evaluation in football (soccer) as a Monte Carlo Tree Search (MCTS)-like evaluation problem whose components mostly exist in the literature under different names: a value model (possession value), a world model (multi-agent trajectories with ball interactions), and a policy over counterfactual actions (sampling pass variants with noise). Building on the first public high-fidelity tracking dataset with 3D ball trajectories from the Bundesliga, we introduce Monte Carlo Pass Search (MCPS), which infers kick parameters for each observed pass, samples execution variants and option variants, rolls each candidate forward with a ball-conditioned world model until the next ball interaction, and scores outcomes with a learned value model to obtain a distribution over gained value. This distribution enables distribution-aware attribution with two complementary execution-surplus scores used for analysis and ranking: mean-based and percentile-based scores. To make the world model sample-efficient under limited public data, we adapt a discrete-token, autoregressive trajectory generator from autonomous driving (SMART) and show it yields strong best-of-20 forecasting accuracy compared to baselines, while supporting fully hypothetical rollouts for downstream evaluation. We have released model checkpoints and code.

Originating in quantum physics, tensor networks (TNs) have been widely adopted as exponential machines and parametric decomposers for recognition tasks. Typical TN models, such as Matrix Product States (MPS), have not yet achieved successful application in natural image recognition. When employed, they primarily serve to compress parameters within pre-existing networks, thereby losing their distinctive capability to capture exponential-order feature interactions. This paper introduces a novel architecture named \textit{\textbf{D}eep \textbf{T}ree \textbf{T}ensor \textbf{N}etwork} (DTTN), which captures $2^L$-order multiplicative interactions across features through multilinear operations, while essentially unfolding into a \emph{tree}-like TN topology with the parameter-sharing property. DTTN is stacked with multiple antisymmetric interaction modules (AIMs), and this design facilitates efficient implementation. Furthermore, our theoretical analysis demonstrates the equivalence between quantum-inspired TN models and polynomial/multilinear networks under specific conditions. We posit that the DTTN could catalyze more interpretable research within this field. The proposed model is evaluated across multiple benchmarks and domains, demonstrating superior performance compared to both peer methods and state-of-the-art architectures. Our code is publicly available at https://github.com/NieCha/deep_tree_tensor_network.

Wildfires are among the most severe natural hazards, posing a significant threat to both humans and natural ecosystems. The growing risk of wildfires increases the demand for forecasting models that are not only accurate but also reliable. Deep Learning (DL) has shown promise in predicting wildfire danger; however, its adoption is hindered by concerns over the reliability of its predictions, some of which stem from the lack of uncertainty quantification. To address this challenge, we present an uncertainty-aware DL framework that jointly captures epistemic (model) and aleatoric (data) uncertainty to enhance short-term wildfire danger forecasting. In the next-day forecasting, our best-performing model improves the F1 Score by 2.3% and reduces the Expected Calibration Error by 2.1% compared to a deterministic baseline, enhancing both predictive skill and calibration. Our experiments confirm the reliability of the uncertainty estimates and illustrate their practical utility for decision support, including the identification of uncertainty thresholds for rejecting low-confidence predictions and the generation of well-calibrated wildfire danger maps with accompanying uncertainty layers. Extending the forecast horizon up to ten days, we observe that aleatoric uncertainty increases with time, showing greater variability in environmental conditions, while epistemic uncertainty remains stable. Finally, we show that although the two uncertainty types may be redundant in low-uncertainty cases, they provide complementary insights under more challenging conditions, underscoring the value of their joint modeling for robust wildfire danger prediction. In summary, our approach significantly improves the accuracy and reliability of wildfire danger forecasting, advancing the development of trustworthy wildfire DL systems.

Multi-step theorem prediction is a central challenge in geometry problem solving. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to evolving theorem libraries. In this work, we explore training-free theorem prediction through the lens of in-context learning (ICL). We identify a critical scalability bottleneck, termed Structural Drift: as reasoning depth increases, the performance of vanilla ICL degrades sharply, often collapsing to near zero. We attribute this failure to the LLM's inability to recover latent topological dependencies, leading to unstructured exploration. To address this issue, we propose Theorem Precedence Graphs, which encode temporal dependencies from historical solution traces as directed graphs, and impose explicit topological constraints that effectively prune the search space during inference. Coupled with retrieval-augmented graph construction and a stepwise symbolic executor, our approach enables LLMs to act as structured planners without any gradient-based optimization. Experiments on the FormalGeo7k benchmark show that our method achieves 89.29% accuracy, substantially outperforming ICL baselines and matching state-of-the-art supervised models. These results indicate that explicit structural priors offer a promising direction for scaling LLM-based symbolic reasoning.

From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, hoping that this analogy would allow for a better emulation of brain function. Over the years the neuroscience literature has shown that the point neuron model is too simplistic to properly represent many fundamental neural processes; however, the standard neuron model in ANNs still remains the same. Here we substitute it by a very recent model of cortical cells and demonstrate through theoretical analyses and experimental results how, simply by using a more realistic neural unit element without augmenting the number of parameters, the resulting ANNs offer a number of important advantages that include increases in expressivity, robustness and learning speed, and a reduction in memorization and the amount of training data needed.

Task planning for robotic manipulation with large language models (LLMs) is an emerging area. Prior approaches rely on specialized models, fine tuning, or prompt tuning, and often operate in an open loop manner without robust environmental feedback, making them fragile in dynamic settings. MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation. Given a natural language instruction and an image of the environment, MALLVI generates executable atomic actions for a robot manipulator. After action execution, a Vision Language Model (VLM) evaluates environmental feedback and decides whether to repeat the process or proceed to the next step. Rather than using a single model, MALLVI coordinates specialized agents, Decomposer, Localizer, Thinker, and Reflector, to manage perception, localization, reasoning, and high level planning. An optional Descriptor agent provides visual memory of the initial state. The Reflector supports targeted error detection and recovery by reactivating only relevant agents, avoiding full replanning. Experiments in simulation and real-world settings show that iterative closed loop multi agent coordination improves generalization and increases success rates in zero shot manipulation tasks. Code available at https://github.com/iman1234ahmadi/MALLVI .

Long-term visual localization has the potential to reduce cost and improve mapping quality in optical benthic monitoring with autonomous underwater vehicles (AUVs). Despite this potential, long-term visual localization in benthic environments remains understudied, primarily due to the lack of curated datasets for benchmarking. Moreover, limited georeferencing accuracy and image footprints necessitate precise geometric information for accurate ground-truthing. In this work, we address these gaps by presenting a curated dataset for long-term visual localization in benthic environments and a novel method to ground-truth visual localization results for near-nadir underwater imagery. Our dataset comprises georeferenced AUV imagery from five benthic reference sites, revisited over periods up to six years, and includes raw and color-corrected stereo imagery, camera calibrations, and sub-decimeter registered camera poses. To our knowledge, this is the first curated underwater dataset for long-term visual localization spanning multiple sites and photic-zone habitats. Our ground-truthing method estimates 3D seafloor image footprints and links camera views with overlapping footprints, ensuring that ground-truth links reflect shared visual content. Building on this dataset and ground truth, we benchmark eight state-of-the-art visual place recognition (VPR) methods and find that Recall@K is significantly lower on our dataset than on established terrestrial and underwater benchmarks. Finally, we compare our footprint-based ground truth to a traditional location-based ground truth and show that distance-threshold ground-truthing can overestimate VPR Recall@K at sites with rugged terrain and altitude variations. Together, the curated dataset, ground-truthing method, and VPR benchmark provide a stepping stone for advancing long-term visual localization in dynamic benthic environments.

With the advancement of drone technology, the volume of video data increases rapidly, creating an urgent need for efficient semantic retrieval. We are the first to systematically propose and study the drone video-text retrieval (DVTR) task. Drone videos feature overhead perspectives, strong structural homogeneity, and diverse semantic expressions of target combinations, which challenge existing cross-modal methods designed for ground-level views in effectively modeling their characteristics. Therefore, dedicated retrieval mechanisms tailored for drone scenarios are necessary. To address this issue, we propose a novel approach called Multi-Semantic Adaptive Mining (MSAM). MSAM introduces a multi-semantic adaptive learning mechanism, which incorporates dynamic changes between frames and extracts rich semantic information from specific scene regions, thereby enhancing the deep understanding and reasoning of drone video content. This method relies on fine-grained interactions between words and drone video frames, integrating an adaptive semantic construction module, a distribution-driven semantic learning term and a diversity semantic term to deepen the interaction between text and drone video modalities and improve the robustness of feature representation. To reduce the interference of complex backgrounds in drone videos, we introduce a cross-modal interactive feature fusion pooling mechanism that focuses on feature extraction and matching in target regions, minimizing noise effects. Extensive experiments on two self-constructed drone video-text datasets show that MSAM outperforms other existing methods in the drone video-text retrieval task. The source code and dataset will be made publicly available.

Artistic style transfer has long been possible with the advancements of convolution- and transformer-based neural networks. Most algorithms apply the artistic style transfer to the whole image, but individual users may only need to apply a style transfer to a specific region in the image. The standard practice is to simply mask the image after the stylization. This work shows that this approach tends to improperly capture the style features in the region of interest. We propose a partial-convolution-based style transfer network that accurately applies the style features exclusively to the region of interest. Additionally, we present network-internal blending techniques that account for imperfections in the region selection. We show that this visually and quantitatively improves stylization using examples from the SA-1B dataset. Code is publicly available at https://github.com/davidmhart/StyleTransferMasked.

3D Gaussian Splatting (3DGS) has emerged as a cutting-edge technique for real-time radiance field rendering, offering state-of-the-art performance in terms of both quality and speed. 3DGS models a scene as a collection of three-dimensional Gaussians, with additional attributes optimized to conform to the scene's geometric and visual properties. Despite its advantages in rendering speed and image fidelity, 3DGS is limited by its significant storage and memory demands. These high demands make 3DGS impractical for mobile devices or headsets, reducing its applicability in important areas of computer graphics. To address these challenges and advance the practicality of 3DGS, this survey provides a comprehensive and detailed examination of compression and compaction techniques developed to make 3DGS more efficient. We classify existing methods into two categories: compression, which focuses on reducing file size, and compaction, which aims to minimize the number of Gaussians. Both methods aim to maintain or improve quality, each by minimizing its respective attribute: file size for compression and Gaussian count for compaction. We introduce the basic mathematical concepts underlying the analyzed methods, as well as key implementation details and design choices. Our report thoroughly discusses similarities and differences among the methods, as well as their respective advantages and disadvantages. We establish a consistent framework for comparing the surveyed methods based on key performance metrics and datasets. Specifically, since these methods have been developed in parallel and over a short period of time, currently, no comprehensive comparison exists. This survey, for the first time, presents a unified framework to evaluate 3DGS compression techniques. We maintain a website that will be regularly updated with emerging methods: https://w-m.github.io/3dgs-compression-survey/ .

The versatile nature of Visual Sentiment Analysis (VSA) is one reason for its rising profile. It isn't easy to efficiently manage social media data with visual information since previous research has concentrated on Sentiment Analysis (SA) of single modalities, like textual. In addition, most visual sentiment studies need to adequately classify sentiment because they are mainly focused on simply merging modal attributes without investigating their intricate relationships. This prompted the suggestion of developing a fusion of deep learning and machine learning algorithms. In this research, a deep feature-based method for multiclass classification has been used to extract deep features from modified ResNet50. Furthermore, gradient boosting algorithm has been used to classify photos containing emotional content. The approach is thoroughly evaluated on two benchmarked datasets, CrowdFlower and GAPED. Finally, cutting-edge deep learning and machine learning models were used to compare the proposed strategy. When compared to state-of-the-art approaches, the proposed method demonstrates exceptional performance on the datasets presented.

Gliomas are the most common type of primary brain tumors. Although gliomas are relatively rare, they are among the deadliest types of cancer, with a survival rate of less than 2 years after diagnosis. Gliomas are challenging to diagnose, hard to treat and inherently resistant to conventional therapy. Years of extensive research to improve diagnosis and treatment of gliomas have decreased mortality rates across the Global North, while chances of survival among individuals in low- and middle-income countries (LMICs) remain unchanged and are significantly worse in Sub-Saharan Africa (SSA) populations. Long-term survival with glioma is associated with the identification of appropriate pathological features on brain MRI and confirmation by histopathology. Since 2012, the Brain Tumor Segmentation (BraTS) Challenge have evaluated state-of-the-art machine learning methods to detect, characterize, and classify gliomas. However, it is unclear if the state-of-the-art methods can be widely implemented in SSA given the extensive use of lower-quality MRI technology, which produces poor image contrast and resolution and more importantly, the propensity for late presentation of disease at advanced stages as well as the unique characteristics of gliomas in SSA (i.e., suspected higher rates of gliomatosis cerebri). Thus, the BraTS-Africa Challenge provides a unique opportunity to include brain MRI glioma cases from SSA in global efforts through the BraTS Challenge to develop and evaluate computer-aided-diagnostic (CAD) methods for the detection and characterization of glioma in resource-limited settings, where the potential for CAD tools to transform healthcare are more likely.