In this paper, we address the problem of detecting small, dense, and overlapping objects, a major challenge in computer vision. Our focus is on reviewing proposed methods based on deep learning supervised approaches. We provide a detailed comparison of these systems on a new dataset of more than 10k images and 120k instances, highlighting their performance, accuracy, and computational efficiency in the industrial recycling process use case. Through this comparative analysis, we identify the most reliable systems currently available and the specific challenges they are designed to tackle. Furthermore, we explore the benefits of data augmentation and synthetic images. Based on our analysis, we also propose potential future directions and innovative solutions that could enhance the effectiveness of small, dense and overlapped object detection systems. The scope of our investigations encompasses object detection, length measurement, and anomaly detection within the context of the recycling process. The anomaly detection strategy is robust against variations in image resolution and zoom levels, ensuring reliable performance in industrial applications. The repository of the proposed dataset, methods and evaluation codes can be found at: https://github.com/o-messai/SDOOD

Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible training and evaluation infrastructure. To fill this gap, we introduce FTibSuite, a comprehensive resource suite for Tibetan vision-language research, consisting of FTibData (human-verified multimodal training corpora spanning continual pretraining, image-text alignment, and instruction tuning data), FTibBench (Tibetan adaptations of five mainstream multimodal benchmarks with a hierarchical quality-control workflow to reduce translation noise), and FTibVLM, a reproducible baseline built on Qwen3-VL-8B-Instruct via a three-stage adaptation pipeline. Experiments on FTibBench show FTibVLM delivers consistent performance gains across all tasks, such as improving MMBench accuracy from 42.97 to 67.78 and POPE-random accuracy from 47.53 to 80.56, while retaining the backbone's original Chinese capabilities with minimal degradation, providing the first standardized foundation for Tibetan multimodal research.

YOLO-series and DETR-based detectors struggle with tiny-object detection. YOLO-style models benefit from efficient dense prediction, but their large-stride backbones may suppress tiny instances in deep feature maps and make grid assignment ambiguous. DETR-based models remove hand-crafted post-processing through set prediction, yet they reason over coarse token grids, where tiny objects occupy only a few weak tokens and are easily overlooked during matching. To address these limitations, we propose TinyFormer, a unified YOLO--DETR hybrid real-time detector that combines ViT representations, NMS-free set prediction, and a YOLO-style pyramid neck for accurate small-object detection. TinyFormer introduces a Parallel Bi-fusion Module (PBM), which builds high-resolution shortcuts from shallow stages to the feature pyramid, preserving fine spatial details during multi-scale fusion. We further design a Spatial Semantic Adapter (SSA) to compensate for the spatial loss caused by coarse tokenization. SSA extracts high-resolution cues from early stages and injects them into transformer token embeddings, improving tiny-object localization without sacrificing the global modeling ability of DETR. Experiments on MS COCO show that TinyFormer consistently outperforms recent YOLO-series detectors and the strong DEIMv2 baseline. TinyFormer-X achieves 58.4% AP even without PBM, while adding PBM improves the overall AP to 58.5% and brings a 1.6% AP gain on small objects. With Objects365 pre-training, TinyFormer-X-PBM reaches 60.2% AP, surpassing RF-DETR and other Objects365-pretrained detectors with fewer parameters and lower computation. These results demonstrate that TinyFormer bridges dense YOLO-style feature fusion and DETR-style set prediction, providing a strong accuracy-efficiency trade-off for real-time tiny-object detection. Code is available at https://github.com/mmpmmpmmpjosh/TinyFormer.

Modern feed-forward 3D reconstruction methods like VGGT predict pixel-aligned pointmaps in camera-centric coordinate frames. However, this choice of coordinate frame is not always optimal. We propose instead to predict pointmaps in upright, gravity-aligned frames that exploit strong structural cues present in many real-world scenes. Unlike camera-centric frames, gravity-aligned frames share a common vertical axis across viewpoints, reducing the rotational degrees of freedom needed to relate pointmaps to one another. To this end, we introduce the Gravity Grounded Geometry Transformer (G3T), fine-tuned from existing models on gravity-aligned 3D data. G3T produces highly accurate gravity-aware predictions, including upright pointmaps and camera-to-gravity poses. We further introduce G3T-Long, a submap-based incremental 3D reconstruction pipeline that leverages the reduced rotational degrees of freedom afforded by upright frames to achieve significantly improved reconstruction accuracy.

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to control the generation. We explore this conditioning space by identifying directions of variations, and demonstrate promising properties in terms of smoothness and disentanglement.

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or sampling steps, but typically commit to a fixed architecture that cannot adapt to individual inputs or denoising stages. We propose PARE (Pruning and Adaptive Routing for Efficient video generation), which jointly compresses width and depth with structure-aware pruning and input-adaptive routing. For width, we observe that attention heads specialize into spatial and temporal roles, and design importance scoring that accounts for this distinction to prevent motion-critical temporal heads from being pruned prematurely. For depth, we train a lightweight router conditioned on denoising timestep and visual content to dynamically select which blocks to execute at each step, enabling per-input compute adaptation rather than static block removal. A progressive pipeline first recovers width-pruned quality via distillation, then jointly optimizes the student and router to decouple the two learning objectives. Experiments on Wan2.1-14B for both image-to-video and text-to-video generation show that PARE substantially reduces per-step computation while preserving quality across VBench dimensions, and composes with step distillation for further acceleration.

Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversion of these flowcharts into machine-readable models for RE activities, yet, when directly applied to flowchart conversion, they often fail on topology-critical visual details. To address this, we propose EdgeFlow that augments a VLM's original input with a deterministically extracted Canny edge map-acting as a structural prior-to improve flowchart-to-Mermaid conversion, without requiring annotated training data or domain-specific model fine-tuning. We evaluate EdgeFlow on IndusReqFlow, a dataset sourced from real-world requirements. Compared with off-the-shelf VLMs, EdgeFlow improves node-level F1 by 17.39 percentage points and edge-level F1 by 16.94 percentage points. At the path level, EdgeFlow improves path F1 by 11.06 percentage points, enabling better support for model-based testing. These results demonstrate that EdgeFlow provides a practical, training-free means to improve topology-preserving flowchart-to-Mermaid conversion for industrial RE. Cross-dataset evaluation results on a public synthetic benchmark show no significant improvement; this highlights the need for diverse benchmarks incorporating industrial data for the comprehensive evaluation of future VLM-based RE tools.

Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language models improve geometric perception and long-range context modeling, but often treat memory as a generic temporal cache, which can introduce redundant or irrelevant geometry and weaken long-horizon reasoning. We propose \textbf{\ours}, a question-guided geometric memory framework for video spatial reasoning. \ours injects camera-conditioned geometry into visual tokens and maintains two complementary memories: a Fine-Grained Context Bank for recent dense features and camera states, and a Semantic-Geometric Evidence Bank for compact long-range evidence. Each candidate frame is scored by the product of Q-Former-based question relevance and novelty with respect to the retained bank; this score is stored and reused during reading, while a capacity-based replacement rule keeps the bank compact. During reasoning, both memories are read before update and adaptively fused with the current frame representation. Experiments on VSI-Bench and VSTI-Bench show that \ours achieves state-of-the-art performance among evaluated spatial reasoning models, validating the effectiveness of question-guided geometric memory. Ablations further verify the contribution of the proposed evidence scoring mechanism.

Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their own background knowledge. To strictly evaluate visual reasoning, we propose counterfactual charts where the chart-question task remains fixed, but underlying chart and the corresponding answer are varied. We introduce Chartographer, a framework to reverse engineer charts into executable code, validate reconstruction fidelity, generate seed-controlled counterfactual variants, and derive new answers from executable QA logic. We apply this framework to existing chart QA datasets and evaluate proprietary and open-source vision-language models (VLMs), measuring variation sensitivity and generalizability. Counterfactual charts reveal failures hidden by single-chart performance: VLMs often fail to generalize after answering the original chart correctly. We find failures are most prevalent when updated charts require novel visual reasoning pathways.

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an intermediate thinking image, but recent work shows that models often ignore the visual evidence in these traces. We therefore ask how to make visual thinking matter, and what kind of visual thinking works best. We study these questions in unified multimodal models (UMMs), which natively support interleaved image-text generation. For the first question, we propose View Dropout (VDrop), a training-time intervention that hides parts of one input view from the answer span while keeping them visible to the thinking-image tokens. This encourages the model to use the thinking image when answering, instead of relying only on the input views. Once the thinking image is used for answer prediction, we study which type of visual thinking is most effective. We frame this as a learnability-informativeness tradeoff and compare three thinking-image variants: top-down, panoramic, and point-matching renderings. Trained on synthetic scenes and evaluated on five real-world out-of-domain benchmarks, panoramic visual thinking with VDrop is the only configuration that is both informative and learnable, and it achieves the best out-of-domain generalization.

Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To address this gap, we present PlayClass, a pipeline for play-behaviour classification in poultry from top-down pen video. The pipeline leverages long-duration tracking with SAM 3 via YOLO-guided chunk boundaries to minimise identity errors in point-based prompting, and frozen embeddings from image and video foundation models for play action classification. Although handcrafted motion features from tracked masks alone achieved competitive accuracy, V-JEPA 2.1 consistently outperformed all other backbones across model scales, reaching 77.0 macro-averaged F$_1$ when combined with handcrafted features. Despite this result, the dataset remains challenging due to play sub-types sharing similar kinematic profiles with non-play and inter-bird occlusion. Overall, our work provides encouraging evidence towards automated frameworks for play behaviour classification in poultry.

We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage the multimodal capabilities of Gemini to produce embeddings for arbitrary combinations of interleaved inputs across all these modalities that generalize well across a wide variety of tasks. Applying large-scale contrastive learning in a multi-task multi-stage training setup, we achieve state-of-the-art performance on key embedding benchmarks including unimodal, cross-modal, and multimodal retrieval spanning a diverse set of tasks. We show that our embedding model demonstrates strong performance (with a score of 62.9 R@1 on MSCOCO, 68.8 NDCG@10 on Vatex, 69.9 on MTEB multilingual and 84.0 on MTEB Code) across a variety of tasks surpassing the performance of specialized models. These unified capabilities make Gemini Embedding 2 a promising candidate for downstream use cases such as RAG, recommendation and search. Furthermore, its robust zero-shot performance across distinct fields - from astronomy and bioscience to fine arts and the culinary arts - establishes it as a highly reliable, out-of-the-box representation even for specialized domains.

Multilevel Image thresholding is an important preprocessing algorithm in computer vision applications nowadays. Since most common thresholding methods take the desired count of thresholds as input by the user, thresholding methods that automatically determines a suitable count of thresholds from the input image itself are advantageous. In this article, a novel thresholding method based on a dynamic programming algorithm and a modification of Minimum Error Thresholding (MET) criterion is thoroughly presented. An empirical statistical study is performed to pinpoint why this proposed method is superior. Moreover, an extended comparison between this proposed method and other state-of-the-art methods is performed on a comprehensive set of natural, satellite and medical test images. The numerical results show that the proposed MET-DP method takes much less time than traditional dynamic programming thresholding methods when the number of thresholds is high. The proposed method can detect a suitable count of thresholds for most of tested images of different types. However, traditional methods that take the count of thresholds as input produce thresholded images of higher structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) values than MET-DP. Source code can be found on https://w3id.org/met-dp/article1-code

Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate relevant evidence across interleaved text and images. Prior work has studied this behavior using retrieval heads in large language models, but its copy-based criterion does not directly apply when evidence appears in images. We introduce a multimodal retrieval head detection method that scores attention from question tokens to textual or visual evidence. With this method, we show that multimodal retrieval heads are sparse, intrinsic, and causally important: only 4.4-10.2% of attention heads account for 50% of the positive retrieval-score mass, and masking the top-5% selected heads drops MMLongBench-Doc from 48.2% to 5.7% and SlideVQA from 71.2% to 8.9%, while random-head masking is far less damaging. Further analysis shows that these heads are partly shared across modalities yet remain dynamic within each modality, with image retrieval heads changing more than text retrieval heads as context length and haystack modality change. Without further training, we find that these heads can also be used directly to rank visually rich documents: on MMDocIR, Qwen3-VL-8B selected-head scoring improves Recall@1 by 7.7/7.4 macro/micro points for page retrieval and 6.3/6.8 points for layout retrieval over the strongest reported baseline.

Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains an underexplored area at scale. To address this gap, we present MRT, a 20B-parameter masked region diffusion model tailored for multi-layer transparent image generation and editing, trained on over 10M multilingual design samples spanning diverse aspect ratios and textual prompts. To fully leverage this scale, we make two key technical contributions. First, we unify three complementary tasks including text-to-layers, image-to-layers, and layers-to-layers within a shared masked region diffusion framework, where selective token masking enables flexible layer-wise generation and editing. Second, to enable overflow layer generation, we introduce an overflow-aware canvas layer that handles boundary inconsistencies and supports semi-transparent background synthesis, enabling complete editable layers extending beyond visible canvas boundaries. Additionally, we apply diffusion distillation to achieve 8-step, real-time multi-layer generation with minimal quality degradation. Extensive experiments demonstrate that our framework substantially outperforms prior state-of-the-art approaches, including various commercial systems, across all three tasks, establishing a new benchmark for multi-layer transparent image generation. Notably, our model significantly outperforms the concurrent Qwen-Image-Layered model in image-to-layers quality according to user-study results, while achieving 10-100\times faster inference and reducing activation GPU memory consumption by 50-90\% during image-to-layer inference.

Animation elevates digital documents into immersive experiences, yet creating custom motion paths remains cumbersome, requiring designers to manually select presets, plot Bézier points, and configure timing properties. We introduce Generative Animations, a system that transforms natural language prompts into production-ready animations. By chaining Large Language Models (LLMs) for semantic parsing with the Segment Anything Model (SAM) for visual grounding, our pipeline automatically generates motion paths that respect scene geometry, handle depth-based occlusions, and honor 3D perspective transforms. We demonstrate the system through three use cases: contour-following trajectories, orbital animations with z-order awareness, and perspective-aligned motion on transformed objects.

Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on short-form tasks, where outputs end after a few tokens. Extending these methods to long-form generation exposes a fundamental yet underexamined limitation: token-level distillation implicitly treats all output tokens as equally informative, but long-form outputs are dominated by high-frequency template and grammatical tokens, while the tokens that actually determine output quality are sparsely distributed. In medical report generation (MRG), two such decisive tokens stand out: pathology-related tokens that determine diagnostic content, and the end-of-sequence (EOS) event that determines termination. Both receive insufficient supervision under uniform cross-entropy, and autoregressive decoding further compounds the problem by drifting away from teacher-forced trajectories. We propose DIVE, a frozen-backbone distillation framework that addresses long-form report generation through two complementary mechanisms matched to these failures. Decisive-token supervision restores supervision balance by upweighting the cross-entropy contribution of pathology-related tokens and the EOS event, ensuring that content fidelity and termination are learned during training rather than imposed at decoding time. State-conditioned dynamic steering replaces fixed open-loop residuals with hidden-state-dependent adapters, allowing the injected signal to adapt as decoding drifts. Experiments on MIMIC-CXR and CheXpert Plus with two medical VLM backbones show that DIVE consistently ranks among the strongest methods across lexical and clinical-proxy metrics. Our method achieves the best BLEU-4, ROUGE-L, and RadGraph F1 in all dataset--backbone settings, while remaining competitive on coarse label-level CheXbert F1.

We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during training. Existing methods are typically constrained to identifying simple objects, primarily due to insufficient object priors in the learning process. In this paper, we present FoundObj, a novel framework featuring a superpoint-based object discovery agent that incrementally merges suitable neighboring superpoints, guided by our innovative semantic and geometric reward modules. These modules synergistically leverage semantic and geometric priors from self-supervised 2D/3D foundation models, providing complementary feedback to the object discovery agent and enabling robust identification of multi-class objects through reinforcement learning. Extensive experiments on diverse benchmarks demonstrate that our approach consistently outperforms existing baselines. Notably, our method exhibits strong generalization in zero-shot and long-tail scenarios, underscoring its potential for scalable, label-free 3D object segmentation.

Discovering the governing equations of a dynamical system from observed trajectories provides deeper insight into its structure than mere prediction of future states. We present a data-driven approach to model discovery based on complex-valued product-unit networks, in which each unit represents a complex monomial and the network output is a sparse linear combination of such monomials. In contrast to established library-based methods such as SINDy, our approach does not require a predefined set of candidate functions: the relevant monomials, including those with fractional or negative exponents, are learned directly from data. Across four chaotic benchmark systems (Lorenz63, Lorenz84, the Four-Wing attractor, and a fractional variant of Lorenz63), we recover the exact governing equations in 90% of trials for the first three systems, and in 70-90% of trials for the fractional case, using at least 3000 training points. Applied to real-world human-gait accelerometer signals, the model produced stable trajectories with bounded prediction errors, corresponding to an RMSE of approximately 12-14% of the signal amplitude range over a test horizon three times longer than the training interval, demonstrating its potential for high-dimensional systems in which analytic equations are unavailable.

While rule-based reinforcement learning has recently catalyzed explicit reasoning in multimodal models, tactile reasoning remains largely underexplored. Existing tactile-language models primarily rely on supervised or contrastive objectives, which limits their capacity to ground predictions in physical evidence or rectify misleading visual priors. Tactile reasoning introduces two modality-specific challenges: the ordinal nature of physical attributes (e.g., hardness, roughness) and the cross-sensor distribution shifts inherent in optical tactile hardware. In this work, we introduce TouchReason-1M, a large-scale multimodal dataset comprising over 1M synchronized tactile pairs across four distinct sensors, and TouchReason-Bench, a rigorous framework for evaluating tactile perception and visual-tactile conflict resolution. Building upon these, we propose Touch-R1, a tactile reasoning MLLM based on Qwen2.5-VL-7B. Touch-R1 is trained via a tactile-grounded GRPO objective that combines ordinal-aware accuracy, cross-sensor physical consistency, structured-format control, and an input-side tactile grounding objective. Specifically, the tactile-use reward assigns credit only when authentic tactile inputs yield superior correctness relative to counterfactual controls where the tactile stream is removed, shuffled, or noise-masked. On TouchReason-Bench, Touch-R1-7B outperforms Octopi-13B by 18.4\% and GPT-4o by 24.7\% on average. Its structured reasoning traces reveal emergent behaviors of probing, comparison, and revision, demonstrating that R1-style reasoning can be effectively grounded in physical contact.

Self-Supervised Learning (SSL) has emerged as a powerful paradigm to mitigate the reliance on large, annotated datasets, a common bottleneck in medical image analysis. However, standard SSL methods, which rely on simple geometric and color augmentations, may fail to capture the fine-grained, complex textural details necessary for classifying subtle pathologies. This paper introduces Chaos-SSL, a novel two-stage framework for medical image classification. In the first stage, we propose a new self-supervised pre-training strategy that leverages 1D chaotic maps (Logistic, Tent, and Sine) as a complex, non-linear augmentation for contrastive learning. We hypothesize that these chaotic transformations create ``harder'' and more semantically-rich views, forcing a network to learn robust representations of fine-grained medical textures. In the second stage, we introduce an attention-based fusion model that dynamically combines the specialized features from our Chaos-SSL model with the general-purpose features of a larger, ImageNet-pre-trained model. We validate our method on two public datasets: ISIC 2018 (skin lesions) and APTOS 2019 (diabetic retinopathy). Our results demonstrate that the Chaos-SSL model pre-trained with a Tent map for 30 epochs, followed by attention fusion, achieves performance fully competitive with the state-of-the-art, yielding an accuracy of 0.9261 on ISIC 2018 and 0.8726 on APTOS 2019. This significantly outperforms existing SSL methods, including several recent approaches.

Superpixel-based image classification has traditionally leveraged graph neural networks (GNNs) for processing irregular image representations. Recent advances in computer vision, driven by Vision Transformers (ViTs), have introduced new paradigms in self-attentional models, surpassing convolutional neural networks (CNNs) in various tasks. However, a synergistic connection between GNNs, superpixels, and transformers remains unexplored. In this work, we propose Superpixel Transformers (SPT), a novel framework that unifies superpixel-based image classification and ViTs. SPT generalizes the Superpixel Image Classification with Graph Attention Networks (SICGAT) model and ViT to support arbitrary superpixel-based chunking strategies, connectivity graphs, and positional encodings. We introduce refinements including a multidimensional sine-cosine positional encoding and an enriched patch data structure that fully incorporates superpixel shape and color information. By testing SPT across datasets such as CIFAR10, FashionMNIST, and Imagenette, with various superpixel generation and graph connectivity strategies, we demonstrate that SPT achieves superior performance compared to previous superpixel-based GNN methods and remains competitive with ViTs. Notably, our approach addresses the limitations of SICGAT, such as information loss during pixel aggregation, and shows how constrained graph connectivity can enhance ViT performance. SPT bridges the gap between superpixel-based and transformer models, opening avenues for cross-domain generalization and future innovations in hybrid attentional frameworks, and showing that an image can also be worth $16\times16$ superpixels.

Electron tomography (ET) plays an important role in the three-dimensional (3D) characterization of nanomaterials. However, under limited-angle and sparse-view conditions, conventional algorithms produce degraded reconstructions, which compromise the quality and interpretability of resulting 3D data. In this paper, we present deep image prior (DIP), an unsupervised deep learning (DL) approach, for highly degraded tomography acquisitions and demonstrate, using simulated data, that its performance is comparable to that of supervised approaches requiring training datasets, even for tilt ranges as limited as 60° and tilt increments of 10°. We then apply it to experimental data and show that it enables reliable 3D quantification under both sparse-view and limited-angle conditions, highlighting its potential for a wide range of materials and acquisition modalities.

Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment. However, most existing methods are adapted from the LLM literature and primarily focus on the language modality, leaving the contribution of visual information to LVLM uncertainty largely underexplored. In this paper, we investigate how LVLMs process visual information and whether this process can be used to improve uncertainty estimation. By analyzing hidden representations after the integration of visual features during the generation process, we observe that high-confidence predictions rely more heavily on visual content than uncertain ones. Building on this insight, we propose Visual-Grounded Token UQ (VIG-TUQ), a training-free framework that explicitly incorporates visual grounding into uncertainty estimation by weighting token-level language uncertainty with visual grounding scores. We evaluate VIG-TUQ on multiple datasets and across diverse LVLM architectures, including early-fusion, late-fusion, and native-fusion models. Results indicate that our method often improves upon existing token-level uncertainty approaches. Code and data will be made available upon acceptance.

With the rapid proliferation of generative models, such as diffusion models, digital watermarking has emerged as a crucial solution for identifying AI-generated images. Modern post-hoc watermarking schemes use neural networks to achieve an extremely low false-alarm rate while remaining robust to common image transformations. However, there is a lack of comparison between these modern methods and classic ones, particularly in real-world scenarios where robustness and security take precedence over achieving an extremely low false-alarm probability. In this paper, we propose a fair comparison of robustness and security between modern and classic post-hoc watermarking across various types of classic augmentations and recent sophisticated attacks. Our experiments show that, in a realistic scenario, classic watermarking outperforms modern techniques in terms of security while maintaining robustness.

Multilevel image thresholding is widely used for segmentation in applications ranging from medical imaging to remote sensing. Classical objective functions, such as Otsu's between-class variance and Kapur's entropy, are often optimized using metaheuristic algorithms, with performance evaluated via metrics like Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR). These evaluations implicitly assume that SSIM and PSNR provide unbiased measures of segmentation quality. In this study, we examine this assumption by analyzing the correlation between thresholding objective functions and quality metrics across all possible thresholds for images in the BSDS500 dataset. Results show that Otsu's criterion consistently exhibits high correlation with both SSIM and PSNR, while Kapur's entropy demonstrates weaker and more variable correlation. Otsu outperforms Kapur in correlation with PSNR for all images and with SSIM for over 91%. Our findings reveal an inherent metric-objective-function bias. This work highlights the need for more neutral evaluation frameworks and motivates extending the analysis to additional thresholding criteria and domains. Source code of this paper can be found at https://w3id.org/met-dp/icpr26-95

In greenhouse tomato production, automated harvesting requires accurate detection of ripe tomatoes, ripeness classification, and precise picking-point localization for robotic end-effectors. This paper proposes YOLO26-RipeLoc Lite, a lightweight deep learning architecture based on YOLO26 for simultaneous detection, ripeness classification, and center-point localization of greenhouse tomatoes. The model introduces three modifications: (1) a Lightweight Feature Pyramid Network (LFPN) with depthwise separable convolutions for efficient multi-scale fusion, (2) a Ripeness-Aware Attention Module (RAAM) with dual pooling and a learnable ripeness bias vector for enhanced color-texture discrimination, and (3) a Compact Detection Head (CDH) with shared convolutions and an integrated center-point regression branch for direct grasp planning. The model is evaluated on a custom dataset of 1,500 images with 6,227 instances (3,566 ripe, 2,661 unripe) from the SILAL greenhouse, Abu Dhabi, UAE. YOLO26-RipeLoc Lite achieves mAP@0.5 of 92.9% (95.2% ripe, 90.6% unripe) with the highest precision (95.2%) among all evaluated architectures using only 2.38M parameters. Post-training BatchNorm pruning at 30% reduces parameters to ~1.8M with negligible accuracy loss. Ablation studies confirm that greenhouse-aware HSV augmentation provides the largest improvement (+2.02 pp mAP@50), backbone freezing achieves peak precision (93.8%), and 3-phase progressive unfreezing yields the best localization quality (mAP@50:95 of 64.6%). Comparisons with YOLOv8n/s, YOLO11n/s, YOLO12n/s, and YOLO26s confirm superior accuracy-efficiency: 2.9 pp higher precision than YOLO12n with 7.0% fewer parameters and integrated center-point localization for robotic end-effector guidance.

Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real world environments often requires the ability to learn novel classes incrementally without retraining on the entire dataset. This capability is known as continual learning. In this regard, the standard fine-tuning methods in deep learning often fail due to catastrophic forgetting, where the model learns new information but forgets previously trained and learned classes. Contributing to this crucial domain, the current paper proposes a novel continual learning framework tailored for PIDNet, which is a widely cited state-of-the-art real-time semantic segmentation model. Our method, PILOT(Parallel Incremental Learning Over Time), introduces a real-time and lightweight strategy by implementing a parallel Derivative-branch (D-branch) designed to capture the high frequency boundary information of novel classes while freezing the trained parameters of the original segmentation network. This novel setup allows the model to adapt to new semantic categories while preserving the knowledge of previously learned classes. By using only data associated with the new class, our model significantly reduces training overhead. Experimental results demonstrate that our approach successfully segments new classes while maintaining high mean Intersection over Union (mIoU) on the original base classes, thereby comfortably outperforming all major continual learning approaches in this domain. Overall, PILOT is shown to effectively mitigate catastrophic forgetting with minimal impact on inference latency, thus maintaining real-time performance.

Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det freezes the visual encoder, preserves the text representation space using only texts of common concepts and previously injected concepts, and injects novel concepts by updating only a small subset of text-branch parameters beneficial to novel concept learning. Extensive experiments show that NoIn-Det effectively learns novel concepts, preserves old knowledge, and consistently outperforms existing continual learning methods for VLMs without introducing additional parameters.Novel-114 and the code will be released.

A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actually achieve this remains unclear. In this work, we introduce DistractionBench to evaluate whether VideoLLMs can robustly link subjects and events in the presence of unrelated video segments. Through controlled interventions, such as inserting short advertisement clips into longer videos, we show that VideoLLMs frequently hallucinate interactions between entities from different segments, incorrectly attributing actions from injected advertisements to subjects in the main video. We characterize this systematic hallucination as bag-of-events (BoE) behavior, where models process videos as collections of events rather than temporally structured sequences. Evaluating 11 popular VideoLLMs, we find that all models exhibit substantial BoE behavior. Our findings suggest that VideoLLMs lack reliable mechanisms for temporal grounding and motivate the development of models with more robust subject-event association.

Appearance-based gaze estimation always suffers from poor generalization due to limited annotated samples and insufficient dataset diversity. Leading approaches adopt weakly supervised learning to generate large-scale pseudo-labeled data from unconstrained real-world scenarios, aiming to mitigate the domain shifts. In this work, we devise a simple yet effective semi-supervised learning architecture that leverages unlabeled data to enhance domain generalization, thereby reducing reliance on labor-intensive manual annotations. Our key insight is to impose Jacobian regularization to disentangle feature representations into discriminative subspaces dedicated to specific gaze components, such as pitch and yaw angles. We further exploit the intrinsic ordinal ranking within each subspace for contrastive learning, enabling the model to learn robust gaze representations from a small set of labeled samples and an abundance of unlabeled ones. This ultimately yields our Disentangled Subspace Contrastive Learning (DSCL) framework. Extensive experiments on multiple benchmarks verify that the proposed DSCL is plug-and-play, achieving competitive performance using only 20\%, 10\%, and even 5\% of the annotated data under both in-domain and cross-domain evaluation settings. The public code is available at \href{https://github.com/da60266/DSCL}{https://github.com/da60266/DSCL}.

Diffusion Transformers (DiTs) achieve strong visual quality, but their iterative denoising process requires many costly Transformer evaluations. Training-free acceleration methods reduce this cost by caching, forecasting, or verifying intermediate features, yet the runtime decision of when to execute a Full step is often driven by fixed schedules or hand-tuned thresholds. We propose \textbf{SoftCap}, a training-free control layer for cache-based DiT inference. SoftCap couples a Trajectory Drift Observer, which estimates local cache risk from lightweight hidden-state statistics, with a Soft-Budget PI Controller, which adjusts the Full-triggering threshold from realized compute relative to a fixed reference profile. The budget is a soft ceiling: it shapes the threshold but does not require a run to spend a prescribed number of Full evaluations. On FLUX.1-dev, SoftCap improves over SpeCa at a comparable middle-compute operating point, raising ImageReward from 0.967 to 0.981 and reducing LPIPS-Full from 0.518 to 0.498 at nearly identical FLOPs, while target-sweep diagnostics show the intended soft-ceiling behavior as the budget is relaxed.

Recent multimodal large language models (MLLMs) achieve strong performance on reactive question answering, but real-world streaming assistants require proactive reasoning over continuous visual inputs. Existing benchmarks mainly study reactive or proactive interactions in isolated single-turn settings, overlooking dynamic multi-turn scenarios where users may add, modify, or cancel proactive requests alongside interleaved reactive queries. To address this gap, we introduce IPIBench, the first benchmark for evaluating Interactive Proactive Intelligence of MLLMs under streaming video settings. IPIBench covers proactive monitoring, proactive task management, and interleaved reactive-proactive requests. Evaluations on representative MLLMs reveal two major limitations: unstable proactive triggering and weak coordination between reactive and proactive behaviors. We further propose IPI-Agent, a training-free agentic framework with an interaction-control policy and a temporal-gating mechanism for stabilizing proactive triggering and coordinating multi-turn interactions. Experiments show that IPI-Agent consistently improves existing MLLMs across all benchmark settings.

Automatic movie trailer generation must select shots from a full-length film and synchronize them with background music. Existing methods either relegate music alignment to post-processing or enforce rigid one-to-one shot-music mappings, overlooking that professional editing rhythm is elastic: rapid cuts accompany high-energy passages while sustained shots span quieter bars. We introduce BEAT, a framework that addresses this gap with two core components: MuVA, a compact music-visual alignment encoder trained with Sinkhorn-regularized two-stage learning, and Bar-DP, an energy-adaptive dynamic programming algorithm that produces elastic many-to-one alignments following musical dynamics. These components are integrated into a five-phase agentic pipeline that grounds the core alignment in learned cross-modal features while coordinating higher-level creative decisions through structured text signals. To support comprehensive evaluation, we also introduce TrailerArena, a benchmark with 20+ metrics across four complementary dimensions. On TrailerArena, BEAT achieves state-of-the-art performance across shot selection, ordering, and perceptual quality, while producing fully composed trailers end-to-end.

Accurate pancreas segmentation is critical for early cancer diagnosis, where annotation scarcity necessitates Semi-Supervised Learning (SSL). However, due to significant inter-sample morphological variability, existing SSL methods face severe generalizability limitations under sparse supervision, leading to the Supervision Bias problem. To address this, we propose Structural Consensus-based KAN Prototype Learning (SCKAN), which constructs the first cross-sample structural consensus learning with Kolmogorov-Arnold Networks (KANs), to achieve more generalizable and accurate segmentation. Specifically, SCKAN contains two key designs: Structure-constrained Prototype Consistency Learning (SPCL), which prompts unbiased structural representation by enforcing cross-sample consistency via prototype-level contrastive optimization, and Consensus-based Kolmogorov-Arnold Fusion (CKaF), which reduces morphology-specific bias by aggregating stable consensus and filtering sample-wise noise via KAN's adaptive B-spline nonlinearity. Extensive experiments on two public pancreas datasets demonstrate the effectiveness of SCKAN. Code is at https://github.com/rhodaliu17/SCKAN.

Implicit neural representations have emerged as a promising paradigm for video compression, with recent methods achieving competitive performance on natural video. However, screen content video -- common in remote desktop, online education, and cloud gaming -- exhibits distinct statistics: sharp edges, limited color palettes, and strong temporal redundancy. Existing neural representation methods, designed for natural scenes, lack mechanisms to exploit these properties, leaving substantial room for improvement. In this paper, we propose NeR-SC, a neural representation framework tailored for screen content video. Building on the SNeRV backbone, NeR-SC introduces three screen-content-specific modules: (i) a learnable color palette that models the discrete color structure of screen content by restricting the low-frequency sub-band to a learned color set; (ii) a multi-gate dense fusion module that replaces sequential feature fusion with dense, attention-gated cross-stage interaction; and (iii) an embedding-level frame skip strategy that bypasses redundant decoder invocations for static frames, with zero training overhead. Experiments on DSCVC and VCD show that NeR-SC achieves 40.32~dB and 41.73~dB average PSNR, outperforming representative neural video representation methods and, at low bitrates, surpassing H.264 and H.265. The skip strategy enables real-time decoding with no loss in quality.

The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a promising tool for identifying unauthorized data usage during model training. Existing methods typically assess the ability of model to denoise perturbed suspect images as an indicator of membership status. However, the discriminative power of such features is highly dependent on the degree of model memorization and deteriorates significantly when applied to less exposed data (e.g., pre-training data). Although several methods attempt to enhance detection by leveraging internal model features, these features are generally inaccessible in mainstream closed-source image generation platforms, limiting their practicality. In this paper, we demonstrate that analyzing how a black-box diffusion model denoises a target image and corresponding perturbed textual instructions can reveal more distinctive membership cues. Based on this insight, we propose a black-box membership inference attack framework (named SD-MIA) that leverages a cross-modal data perturbation mechanism to detect pre-training data in diffusion models. We conduct extensive experiments on both a public benchmark dataset and a newly constructed dataset, each comprising pre-training membership and non-membership samples with identical distributions. Experimental results demonstrate that SD-MIA achieves superior performance compared to existing baselines, including those with the unfair advantage of accessing internal model features.

W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-step denoising trajectory. These difficulties are compounded by Wan2.2-I2V's two-expert Mixture-of-Experts DiT design, whose high-noise and low-noise experts exhibit distinct quantization sensitivities that a single global calibration policy cannot capture. We propose a post-training quantization framework combining SVDQuant-based low-rank outlier compensation, GPTQ-based reconstruction-aware residual weight quantization, and timestep-bin-wise per-layer activation clipping-ratio search conducted independently for each expert. On the OpenS2V-Eval benchmark, our method reduces peak GPU memory by 59.3\% relative to the BF16 baseline while incurring only a 0.9\% drop in VBench average score and a 2.3\% drop in Imaging Quality, demonstrating that expert- and timestep-aware calibration is essential for high-fidelity W4A4 inference on MoE video DiTs.

Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work, we present the first systematic survey and robustness analysis of VLM unlearning. We provide a comprehensive taxonomy and review of existing VLM unlearning methods, together with unified evaluations under multiple prompt settings. We then propose three attack paradigms to examine whether forgotten multimodal knowledge can be reactivated through contextual prompting or downstream retraining. Extensive experiments show that many existing methods remain vulnerable under these attacks, indicating that current approaches often hide rather than fully remove target knowledge. Our study provides new insights into the robustness and limitations of current VLM unlearning methods and highlights the need for more reliable multimodal unlearning strategies. Code is available at https://github.com/XMUDeepLIT/VLM-UnL-Attack.

Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, whereas segment-wise captions improve coverage but introduce heavy redundancy. We propose CodecCap, a codec-inspired framework for high-fidelity dense video captioning. Analogous to video codecs, CodecCap represents videos using keyframe and residual captions. Keyframe captions exhaustively encode stable visual context, while residual captions capture temporally only localized actions, motions and changes. This effectively preserves fine-grained visual evidence while reducing redundant descriptions. To quantify the fidelity of captions, we introduce VidCapQA, a caption-then-QA benchmark with 1,000 questions across 14 capability dimensions. Results on VidCapQA show that captions directly generated by strong VLMs still miss many visual details, highlighting caption representation as a critical bottleneck. Experiments show that CodecCap significantly surpasses direct captioning with the same underlying VLMs, suggesting keyframe-residual captioning a way for high-fidelity video-language supervision. We further use CodecCap to construct CodecVDC-100K, a large-scale dense captioning dataset with anchor, residual, scene-level, and video-level supervision.

3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic and efficient shape completion framework that augments geometric reconstruction with voxel-aligned semantic priors distilled from DINO features. First, we construct multi-view DINO feature volumes aligned with ShapeNet data and train a student network to predict dense semantic features directly from incomplete shapes. These predicted features capture global structure and part-aware semantic context while remaining aligned with the underlying geometry. We then integrate these distilled features into a completion network, where geometric and semantic voxel representations are fused through voxel state-space modeling. To enable efficient long-range reasoning without sacrificing resolution, we introduce a multi-scale voxel Mamba module that refines the fused features by combining full-grid and chunk-wise sequence modeling. Experiments on unseen ShapeNet categories and ScanNet objects show that DinoComplete achieves stronger completion quality than prior deterministic and generative based completion methods while using fewer parameters, requiring lower memory, and achieving faster inference. Our results demonstrate that distilling semantic priors from visual foundation models improves generalization and robustness in 3D shape completion.

The problem of object pose and shape estimation has seen key advancements lately. Encoder-decoder (e.g., SAM3D, LRM, CRISP) and diffusion-based models (e.g., InstantMesh, Zero123, SceneComplete) have shown category-agnostic shape encoding capacity and open-set generalizability. In this work, we ask the question: Are the object pose and shape estimation methods mature enough, such that when used with antipodal grasp sampling, can outperform the end-to-end grasp synthesis methods? We explore this question in detail by scoping our study to parallel jaw grippers, 7-DoF grasps, and single-view RGB(-D) image as input. We implement and compare a state-of-the-art, end-to-end grasp synthesis method and three modular methods, which first estimate the object pose and shape for all objects in the scene, and generate grasps using antipodal sampling. We observe that the modular methods outperform the end-to-end method in all our experiments. The modular methods are able to synthesize plenty of grasps, even for small objects, where the end-to-end methods fail. The effectiveness of the modular methods is contingent on the accuracy of the pose and shape estimation, and suffers partial degradation in cluttered scenes - a limitation of the existing pose and shape estimation methods. We also analyze the failure modes and run-times for the three modular methods, which use two different ways of object pose and shape estimation: one based on an encoder-decoder model, while another a diffusion model. Finally, we demonstrate that the single-view object pose and shape estimation methods can be augmented with vision-language models to yield language-conditioned grasps from just single-view RGB-D image as input. We notice comparable performance to the state-of-the-art LERF-TOGO baseline.

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often struggle in scenarios that demand fine-grained understanding of semantic and visual structural information within video frames. Text-to-image diffusion models are well known for their ability to generate images that accurately reflect the semantics and structures described in the input prompt, demonstrating a strong grasp of visual semantics and structures. Building on this capability, we approach the unsupervised tracking from a new perspective by exploiting the rich semantic knowledge encoded in pretrained text-to-image diffusion models. To adapt the diffusion models, which are originally developed for image generation, to the tracking task, we reinterpret the models as a bridge between text and image modalities. This connection is realized through the cross-attention mechanism: when both text and an image are input into the models, they highlight the regions of the image that are semantically aligned with the text in the cross-attention maps. We therefore learn a prompt that represents the tracking target and activates its corresponding region in the cross-attention map for each frame, which enables object tracking with the diffusion model. Specifically, our method Diff-Tracking is composed of two main components: an initial prompt learner and an online prompt updater. The initial prompt learner generates a prompt that captures the target object in the first frame, allowing the diffusion model to identify the target. The online prompt updater refines the prompt based on motion information, enabling consistent tracking across video frames. We evaluate our approach on six challenging tracking datasets demonstrate the effectiveness of our approach.

In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction more challenging than in images. Existing methods impose statistical mappings across noisy variants via noise or optimal transport, but suffer from correspondence ambiguity. In this work, we propose Self-Induced Mirror-Point Consistency (SIMPC) to learn deterministic correspondences between points and the underlying surface in an unsupervised manner. For each noisy point, SIMPC generates a mirror-point on the opposite side of the underlying surface, guided by geometric priors during the denoising process. By encouraging consistency between the denoising targets of the original point and its mirror counterpart, SIMPC effectively localizes the position of underlying surface. Extensive experiments on synthetic and real-world datasets demonstrate that SIMPC significantly outperforms state-of-the-art unsupervised methods and surpasses several strong supervised counterparts.

Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate. We observe that this limitation stems from the absence of reliable high-order temporal cues -- velocity and acceleration -- which are essential for reconstructing motion that exhibits realistic momentum, timing, and high-frequency detail. We introduce HTD-Refine, a post-processing framework that augments existing Human Motion Recovery (HMR) pipelines using explicitly estimated high-order temporal dynamics. At the core of our system is PVA-Net, a temporal transformer that infers per-joint 2D positions, 3D velocities, and 3D accelerations directly from a monocular video. These predicted dynamics serve as soft yet informative constraints in a global optimization procedure that refines world-space trajectories, significantly reducing jitter, suppressing over-smoothing, and restoring physically plausible motion. Extensive experiments on challenging in-the-wild benchmarks show that HTD-Refine consistently improves state-of-the-art HMR methods, yielding more accurate global trajectories and substantially more natural motion dynamics. Our results highlight the critical role of high-order temporal modeling in advancing monocular human motion recovery.

Accurate road segmentation from aerial imagery is fundamental to many geospatial applications. However, existing datasets often suffer from limited scene diversity, low semantic granularity, and poor structural continuity, restricting their generalization across environments. To address these challenges, we introduce WorldRoadSeg-360K, the largest and most diverse road segmentation dataset to date, comprising 366,947 high-resolution images collected from 38 countries and 223 cities across various terrains and continents. WorldRoadSeg-360K serves as a comprehensive benchmark and reveals key challenges in handling diverse and structurally complex scenes. Automated approaches often struggle to preserve road connectivity, while current interactive methods lack efficient, topology-sensitive tools for real-world road editing. To this end, we present RoadGIE, establishing a novel interactive paradigm for road extraction in remote sensing. Unlike prior point- or box-based prompting strategies, RoadGIE supports connectivity-aware prompts, including clicks and scribbles, which inherently align with the topology of road networks. To improve structural consistency and mitigate performance degradation during iterative interactions, RoadGIE integrates an expert-guided prompting strategy and adapts the skeleton-based recall loss for interactive scenarios. RoadGIE achieves state-of-the-art performance in both segmentation accuracy and topological consistency on WorldRoadSeg-360K and other benchmarks, while maintaining efficient operation with only 3.7M parameters. The code are publicly available at: https://github.com/chaineypung/RoadGIE

Image geo-localization aims to determine where a photograph was taken, a task that often requires more than recognizing visible landmarks. Human experts typically solve it through an iterative workflow: they inspect informative regions, form location hypotheses, seek external evidence, and revise their judgments as new clues appear. Existing methods only partially capture this process: direct prediction methods bypass evidence acquisition altogether, while retrieval-augmented methods introduce external evidence but usually provide limited supervision on the intermediate decisions of where to search, how to query, and how to filter noisy results. We present REVERSE, a framework that reinforces the interplay between evidence search and verification to enable multi-turn agentic reasoning. REVERSE teaches three intermediate decisions: where to look, what to query, and what evidence to trust. To support this, we construct tool-grounded trajectories with annotated region selections, search observations, and geo-informative evidence labels, and introduce process rewards for visual grounding, query utility, and evidence discrimination. An offline search cache makes retrieval observations stable and reusable during reinforcement learning, enabling dense supervision over noisy search results. With a 4B model, REVERSE outperforms strong retrieval-augmented baselines and rivals substantially larger models on Im2GPS3k and YFCC4k. Code is available at https://github.com/yonglleee/REVERSE.

Public datasets such as DLC-2021, SynID, and KID34K have significantly contributed to research on presentation attack detection for identity documents, including screen replay attacks. However, evaluation of out-of-domain (OOD) robustness remains insufficiently explored, especially under realistic domain shifts. In this work, we introduce Receipt Replay OOD, a small out-of-domain benchmark for screen replay detection. Receipts share several characteristics with identity documents, including planar geometry, curved corners, wear-and-tear artifacts, and text or logo patterns, while avoiding personally identifiable information constraints commonly associated with identity documents. We evaluate document replay detection models under cross-domain conditions and demonstrate the impact of domain shift on generalization performance. The dataset is publicly available.

Semantic mapping methods are increasingly used as intermediate scene representations for downstream robotic reasoning and manipulation, yet their evaluation is still largely tied to fixed benchmark datasets with limited coverage of manipulation-relevant corner cases. In this work, we extend OSMa-Bench toward controllable benchmarking with prompt-generated synthetic indoor scenes. Our pipeline automatically generates scene descriptions, synthesizes corresponding environments with SceneSmith, and adapts the resulting assets into an OSMa-Bench-compatible simulation format. This adaptation requires a nontrivial intermediate layer, including semantic normalization, material and texture repair, shader fallback policies, floor handling, navigation setup, and controlled lighting configuration. A key advantage of the proposed setup is that the original scene-generation prompt is known in advance and can therefore serve as an auxiliary semantic specification of the intended scene. We use this property to extend the VQA component of OSMa-Bench with a prompt-grounded question category. The resulting framework supports targeted stress-testing of semantic scene representations under conditions such as clutter, small objects, partial occlusions, and lighting variation, and makes benchmarking more extensible and better aligned with downstream manipulation requirements. Our code is available at https://github.com/be2rlab/OSMa-Bench-v2.

State estimation is a fundamental problem in control and signal processing, for which the Kalman Filter provides an optimal solution under linear dynamics, Gaussian noise, and known noise covariances. However, these assumptions often fail in realistic sensing settings such as Doppler radar and LiDAR. In these cases, the optimal estimator is inherently nonlinear, which leads to systematic performance degradation. This creates a performance gap that cannot be eliminated by tuning the noise covariance parameters (i.e., the process and measurement noise in the Kalman Filter) alone. To address this limitation, we propose Kalman Evolve, a framework for discovering improved filtering algorithms by jointly optimizing both noise parameters and the update structure. Our approach leverages large language models (LLMs) as a structured prior over program space, enabling the generation of interpretable, non-affine modifications to the classical Kalman filter while preserving its recursive form. We provide analytical results establishing the suboptimality of affine estimators under common nonlinear sensing models, motivating the need for structure-aware updates. Across a range of synthetic and real-world tracking benchmarks, including Doppler radar, LiDAR-based localization, and pedestrian tracking, the discovered algorithms consistently improve over strong baselines such as the Optimized Kalman Filter, achieving up to 12\% reduction in RMSE. These results suggest that optimizing the structure of the Kalman filter, rather than only its parameters, provides a practical and interpretable way to improve state estimation.

Human motion generation has made tremendous progress in recent years, with state-of-the-art approaches surpassing ground truth data in leading evaluation benchmarks. However, visual inspection of the generated motions paints a different picture. Even state-of-the-art approaches generate motions frequently containing self-intersections, i.e., body parts interpenetrating, which are strong artifacts, severely limiting the perceived motion quality. We introduce a novel loss, which explicitly penalizes self-intersections, to the training of human motion generation methods. We base our loss on a sphere proxy of human geometry, which allows us to calculate a self-intersection loss 98% faster and uses 83% less memory than comparable methods based on triangular meshes. The loss is agnostic to the specific approach, and we add it to the training of the recent human motion generation methods human motion diffusion model (MDM) and MoMask. Our extensive experiments show a reduction of self-intersections in generated motions of up to 49% while improving other evaluation metrics. The code is available at https://github.com/boschresearch/humansphereproxy .

Existing Multi-Turn Composed Image Retrieval (MTCIR) datasets lack dialogue-history consistency and are restricted to the fashion domain. To address these limitations, we construct CIRCLED by extending FashionIQ, CIRR, and CIRCO. In CIRCLED, the query at each turn progressively approaches the target image. Data are generated via a CIReVL-based retrieval pipeline and curated with multiple filters on retrieval success, turn length, consistency, and information redundancy to ensure quality. In total, we collect 22,608 multi-turn sessions across nine subsets, substantially exceeding Multi-turn FashionIQ (11,505 sessions) in both scale and generality. We further apply multiple baseline methods and quantitatively assess retrieval accuracy on CIRCLED. Our work provides a practical, high-quality benchmark to facilitate future research on multi-turn CIR. The dataset and code are publicly available at https://huggingface.co/datasets/tk1441/CIRCLED and https://github.com/mti-lab/circled.

We present HICNet, a reference-guided exposure correction framework. A lightweight, content-agnostic encoder distills each image into a compact illumination embedding capturing regional brightness, edge contrast, and higher-order luminance moments. The embedding difference between a source and its reference drives a multi-scale modulation network that combines FiLM-based global adjustment with Photometric Channel Rebalancing for fine-grained, illumination-aware spectral gating, producing exposure-matched outputs while faithfully preserving scene details. A cross-batch contrastive loss orders the illumination manifold, bolstering robustness to diverse lighting conditions. Trained without ground truth or intrinsic decomposition, HICNet attains better accuracy on public benchmarks and generalizes well to entirely unseen scenes.

Neural cellular automata (NCA) provide a lightweight alternative to encoder-decoder segmentation networks. However, it can be difficult to decide when a prediction should be trusted. Here, we study uncertainty estimation for NCA-based medical image segmentation without modifying the underlying architecture or retraining the model. Our approach is motivated by viewing the NCA as a dynamical system where convergent attractors correspond to confident predictions. Concretely, we propose resilience, a simple measure that leverages the intrinsic iterative structure of NCAs by probing the stability of the final prediction under small perturbations of the automaton state. Predictions that return to the same solution are deemed confident, while those that change substantially are flagged as uncertain. We evaluate uncertainty by its ability to predict segmentation quality using selective prediction metrics ($Δ$Dice@90 and AURC) and ranking metrics (AUROC and AUPRC). Across multiple medical segmentation benchmarks, resilience identifies failure cases more reliably than baselines, improving trust and safety in NCA-based models.

Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that integrates visual semantics with multi-view geometric reasoning. Unlike conventional approaches that rely heavily on sequential frames for temporal tracking, our method leverages zero-shot detection and segmentation together with structure-from-motion reconstruction to establish stable cross-view correspondences. A 3D-driven association mechanism replaces traditional 2D multi-object tracking, using geometric consistency to guide identity preservation across wide-baseline viewpoints and varying imaging conditions. By combining 2D texture cues with global 3D context, the proposed pipeline is well-suited for scalable street-level processing and can be used for a variety of object types. Experiments demonstrate substantially improved coverage of ground-truth sequences and more robust identity retention compared to state-of-the-art 2D-only tracking methods, achieving a 22% performance gain in challenging urban scenarios.

Benchmarks that reflect the diversity and complexity of real-world documents are essential for accurately evaluating Automatic Text Recognition (ATR) systems, especially Vision-Large Language Models (vLLMs). Although recent models demonstrate impressive performance, they are often evaluated on datasets containing modern, printed texts mostly written in English, which limits their relevance to many practical applications. Therefore, selecting a model for a specific use case requires evaluating it on data that matches the target documents. This highlights the importance of representative benchmarks for real-world applications. In this paper, we introduce METATR (v1.0), a multilingual, evolving benchmark designed to evaluate ATR models across a wide range of documents, facilitating meaningful model comparison and selection. The benchmark was designed to maximize diversity by including documents from various public collections. These documents cover 29 languages and include texts with multiple scripts and layouts. Beyond the dataset itself, METATR defines a standardized prompting and normalization methodology and establishes a dynamic evaluation framework. This approach is intended to produce reproducible results while remaining extensible over time. We evaluated a wide range of state-of-the-art systems, including open-source models and closed-source models. Results are reported across various dimensions, including performance at the dataset and language levels, robustness to handwritten documents, and computational efficiency. Our findings show that, although proprietary models achieve the most consistent performance, substantial variability persists across scripts and layouts. Overall, METATR provides a multidimensional, practitioner-oriented framework for assessing multilingual ATR in real-world conditions and tracking progress as the field evolves.

Humans constantly reason about 3D proximity, the relations between their body and surrounding objects, to guide perception and action in daily life. Whether multimodal large language models (MLLMs) can perform such embodied 3D reasoning remains unclear. To this end, we introduce EgoProx, a benchmark for egocentric 3D proximity reasoning. We organize our tasks along a cognitive chain, covering intention, exploration, exploitation, and chain-of-actions reasoning. We also design an agent based data engine that produces diverse and consistent QA pairs at scale. We benchmark prevailing MLLMs on EgoProx and conduct additional analyses with dataset specific and task specific instruction tuning. We observe large cross-domain gains, indicating that current MLLMs contain some spatial knowledge; however, they still struggle to effectively leverage it for spatial reasoning VQA.

We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect interpretation. In this paper, we reformulate the task of model interpretation and the interpretation principles for model interpretation results to demonstrate the importance of the baseline. We further unify gradient-based methods, Integrated Gradients (IG) methods, and Taylor expansion, clarifying the connections among them and explicitly identifying the baseline for each method. On this basis, we analyze the flaws and errors in related model interpretation methods (IG, LayerCAM, ODAM, Difference Map). We advocate evaluating the quality of model interpretation results precisely through the attribution error between the attribution result and the attribution target, rather than adopting flawed evaluation methods, such as those based on marginal-effect or the assumption of perfect model performance. We revise IG and develope a model interpretation method with a clear and reasonable baseline, achieving better results. Our method supports model interpretation based on features from any layer. Interpretation based on features from different layers are all reasonable, and the differences among these results reflect varying degrees of feature extraction at different feature extraction stages.

Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask generation. Prior training-free instances of this recipe consistently trail fine-tuned and reinforcement-learning (RL)-tuned specialists, and it has been unclear whether the gap comes from the VLM's grounding, SAM's capacity, or the prompt. We show that the gap is dominated by prompt ambiguity: a VLM-proposed bounding box (bbox) leaves SAM to guess which pixels inside the bbox belong to the object the expression denotes. Interior points are the natural disambiguator, but where they fall matters; prior work relies on naively sampled points that land on boundaries, distractors, and background clutter, and can even hurt performance compared to the bbox alone. Supervised and RL-tuned methods close this gap by training a VLM to predict better points; we show that this training is unnecessary. At a matched budget of five interior points, replacing naive sampling with stable, informative point selection improves cumulative Intersection-over-Union (cIoU) by 12-18 points across RefCOCO/+/g, with every model fixed. We turn this observation into PinPoint, a deterministic, training-free point selector that fuses four visual cues into a consensus map, selects compact, spatially diverse points away from boundaries, and uses the frozen VLM to label each point. Without any task-specific training, PinPoint matches supervised and RL-tuned specialists on the same stack while issuing only two VLM calls per query.

This dataset provides high-resolution, annotated video sequences of shredded E40-grade steel and copper scrap on a conveyor belt. Captured in a controlled laboratory environment, the data reflects the industrial post-magnetic sorting stage, where manual intervention is typically required to remove copper contaminants. The dataset comprises 24,297 labeled frames across five subsets, featuring 396 steel and 101 copper objects categorized by size. It supports the development of machine learning models for material classification, object detection, and instance segmentation. Variations in object spacing and density are included to simulate realistic industrial sorting conditions. Ground truth annotations include pixel-wise segmentation masks and material classes. This dataset serves as a benchmark for evaluating automated sorting algorithms aiming to identify copper impurities within complex, heterogeneous steel scrap streams.

Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps remain in existing thinking-with-video systems. (i) Sampling density is not a learnable decision: existing methods may let the model decide where to look, but the per-window frame rate is largely fixed. As a result, fine-grained evidence is often recovered through repeated retrieval calls, which increases inference context length and training difficulty. (ii) Retrieval and answer generation are usually optimized with a single trajectory-level advantage, so the "where to look" tokens and the "how to answer" tokens receive the same credit even when one is correct and the other is not. To address these gaps, we present DynFrame, a framework that emits the temporal window and the sampling density as native tokens within a single autoregressive pass. This learnable span-density retrieval enables acquiring multi-granularity evidence with a single retrieval step. Based on the above tokenized retrieval interface, we further introduce Segment-Decoupled GRPO (SD-GRPO), which splits each rollout at the retrieval boundary and assigns role-specific token-level advantages, separately crediting the sampling decision and the answer. Trained on the curated DM-CoT-74k and DM-RL-45k, DynFrame-4B is competitive with strong 7B-8B baselines across six benchmarks (NExT-GQA, Charades-STA, ActivityNet-MR, Video-MME, MLVU, LVBench), and DynFrame-8B sets new state-of-the-art on most metrics. Code is available at https://github.com/zhangguanghao523/DynFrame.

Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfectly clean training sets is impractical. However, existing methods are sensitive to contamination, suffering significant performance degradation as the noise ratio increases. In this paper, we propose Memory-Distilled Selection (MeDS), a training algorithm based on data selection. MeDS constructs an ensemble of partial memories via random subsampling, where the resulting sparsity acts as a low-pass filter that captures nominal patterns across a wide range of noise ratios, enabling coarse-level identification of contaminated samples. The aggregated distances to the bootstrapped memories are then distilled into a reconstruction score network, which is subsequently fine-tuned on clean data filtered using scores from the distilled model, enabling fine-grained localization of anomalies. MeDS is robust across a wide range of noise ratios without requiring noise-ratio-specific hyperparameter tuning, achieving 99.16\% image-level AUROC on MVTecAD at a 40\% noise ratio, and attaining state-of-the-art performance on both VisA and Real-IAD under noisy settings. We thoroughly verify the efficacy of MeDS on industrial AD benchmarks under noisy data scenarios, accompanied by in-depth empirical analyses.

Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language models (VLMs) has enabled zero-shot OOD detection without access to in-distribution (ID) training data; in this setting, existing methods commonly treat text embeddings of class names as class prototypes. In this paper, we challenge the widely adopted text-as-prototype paradigm by theoretically showing that off-the-shelf textual prototypes are generally misaligned with the optimal visual prototypes, yielding an intrinsic modality gap that cannot be eliminated by prompt engineering alone. To mitigate this gap under the post-hoc constraint, this paper presents an online pseudo-supervised framework that directly learns class prototypes in the visual feature space using unlabeled test-time data streams and soft predictions from the pre-trained VLMs. We provide theoretical guarantees for the convergence of the online optimization procedure. Extensive experiments empirically demonstrate that our method achieves a new state of the art across a variety of OOD detection setups.

Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, the core carriers of visual information, are optimized only implicitly as part of the context, leading to coarse-grained visual understanding. Prior works attempt to supervise visual inputs but inevitably rely on auxiliary components such as additional decoders or forward passes, because visual tokens lack readily interpretable labels. This limits their practical applicability. In this work, we propose \textbf{D}irect \textbf{V}ision \textbf{S}upervised \textbf{F}ine-\textbf{T}uning (DV-SFT), which constructs explicit, token-level supervision for visual tokens and trains them through the same next-token prediction objective used for text. Specifically, we exploit the direct vision--text correspondence in OCR-related scenarios and automatically label each visual token with the word in its corresponding image patch. DV-SFT treats the MLLM as a black box, requiring no architectural modifications or additional forward passes. Extensive experiments demonstrate the superiority of direct vision supervision. DV-SFT consistently outperforms standard SFT across three in-domain and four out-of-domain benchmarks. Further analyses show that vision supervision effectively enhances fine-grained visual understanding and achieves higher multimodal alignment efficiency.

Collaborative perception improves 3D object detection by enabling agents to share complementary observations, but most existing methods assume fixed or known collaborator encoder configurations, limiting deployment in practice. In this work, we consider an open-world setting in which auxiliary agents with unseen configurations may appear after deployment, such as different LiDAR beam counts or encoder architectures. To address this challenge, we propose ALF, a collaborative perception framework that enables zero-adaptation collaboration with unseen agent configurations by lifting lightweight box-level messages into ego-compatible auxiliary features. ALF converts auxiliary box-level messages into pseudo-BEV maps and synthesizes ego-compatible latent features by combining object-centric cues with scene context from the ego feature. On V2X-Real, under a zero-shot evaluation across 64 case studies, ALF outperforms the strongest prior baseline by 35.91% in relative mAP@0.7 while requiring only 120 bytes per agent per frame (approximately 9.6 Kbps bandwidth at 10 Hz).

Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) encoders extend this setting to three modalities. Such encoders can produce a joint (T,V,A) embedding whenever all three modalities are available, but standard pairwise InfoNCE objectives leave this signal unused during training. We close this gap with fusion-as-teacher distillation, which treats a stop-gradient copy of the fused embedding as a teacher signal for the single-modal embeddings, paired with a Tuple-InfoNCE term that supervises the fused embedding directly. We instantiate this objective as OmniRetriever-7B. Across six zero-shot retrieval benchmarks, OmniRetriever-7B surpasses the closed-source Gemini Embedding 2 by 13.3-18.0 R@1 on Clotho and SoundDescs, and reaches the contemporary zero-shot specialist band of open video-text encoders on MSR-VTT and MSVD. To stress-test joint representations, we further release OmniRetriever-Bench, a 12-direction AVT retrieval benchmark totaling 3782 triples; on it OmniRetriever-7B attains AVG-all 34.84, improving over Gemini Embedding 2 by 1.72 and over the best prior open-source AVT method by 8.03.

We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while achieving substantially higher inference efficiency on high-resolution images. At the core of our approach is Post-Training Attention Search, a post-training acceleration framework that converts pre-trained full-attention ViTs into efficient hybrid-attention variants by identifying and replacing redundant full-attention blocks with linear or window-attention blocks. By inheriting the MLP and attention weights from the base model, Post-Training Attention Search efficiently explores the architectural design space through three key steps: (1) optimizing the linear-attention block design; (2) finding the best combination of linear-attention and window-attention blocks; and (3) identifying and preserving critical full-attention blocks. We evaluate JetViT on two representative high-resolution vision foundation models, DINOv3 and DepthAnythingV2. On the NVIDIA H100 GPU, JetViT achieves up to 1.79x higher throughput and up to 44.81% lower latency without sacrificing accuracy. We will release our code and accelerated ViT models soon.

Liver surface landmark detection is a fundamental prerequisite for anatomical guidance in laparoscopic liver surgery. However, it remains unreliable in practice due to two pervasive challenges: illumination attenuation in underexposed regions and the structural mismatch between pixel-wise localization and continuous curvilinear geometry. To address these limitations, we propose A2ONet, an attenuation-resilient alternating optimization network for robust liver landmark detection. To mitigate illumination attenuation, A2ONet embraces an illumination field compensation (IFC) block that adaptively enhances dark regions while preserving structural consistency. Meanwhile, we introduce a lightweight frequency-orientation selective filter (FOSF) to suppress repetitive texture interference and preserve salient curvilinear cues. Building upon these resilient representations, we design an alternating seg-curve optimization (ASCO) decoder that iteratively couples dense segmentation with explicit curve modeling, enabling mutual guidance to optimize both structural continuity and endpoint localization. Extensive evaluations on L3D-2K, L3D, and P2ILF demonstrate consistent improvements over competitive methods, establishing a more reliable foundation for intraoperative anatomy guidance. Our code will be available at https://github.com/hyperiondk115/A2ONet.

Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fails under lowlight due to noise, color shifts, and unreliable correspondence. We propose DelowlightSplat, a lowlight-aware feed-forward Gaussian splatting framework for clean novel-view rendering. We build a controllable multi-view lowlight benchmark by degrading only context views while keeping target views clean. We introduce a lightweight Lowlight Adapter for residual enhancement to improve matchability, and couple it with cost-volume-based multi-view inference to directly predict clean 3D Gaussians. Experiments show that DelowlightSplat significantly outperforms previous feed-forward method and two-stage pipeline under lowlight conditions.

Volumetric Reasoning Segmentation (VRS) aims to segment a target region in a 3D medical scan from a free-form clinical query, where the referent is often implicit and requires both medical knowledge and volume-grounded reasoning. Existing methods typically rely on specialized segmentation tokens to connect language with mask decoding, but this coupling collapses the decision process into opaque latent representations, limiting interpretability and generalization to diverse narrative expressions. In this paper, we present MedVol-R1, a reinforcement learning-based framework for VRS that explicitly decouples evidence grounding from volumetric delineation: the LVLM grounds clinical reasoning to a verifiable 2D evidence anchor (key axial slice and 2D bounding boxes), which is then propagated into a coherent 3D mask by a frozen MedSAM2 module. We train MedVol-R1 with cold-start supervised fine-tuning followed by GRPO, guided by a multi-component reward that encourages informative evidence selection, accurate 2D spatial grounding, and cross-slice volumetric coherence, without requiring costly chain-of-thought annotations. Experiments on CT-ORG, AbdomenCT-1K, and KiTS23 from the M3D-Seg benchmark demonstrate that MedVol-R1 consistently outperforms strong baselines and achieves state-of-the-art performance, with reinforcement learning providing clear gains over pure supervised fine-tuning.

While 3D Gaussian Splatting has achieved remarkable success in photorealistic novel view synthesis, its pursuit of fast and high-fidelity 3D reconstruction has long been constrained by a trade-off between geometric accuracy and optimization efficiency. Methods specialized in image rendering converge quickly at the cost of imperfect geometry caused by superfluous primitives overfitting training views, while methods integrating neural signed-distance field (SDF) for better geometry incur prohibitive training costs. In this paper, we attempt to strike a better trade-off by tethering scaffold-anchored Gaussians to a jointly optimized sparse voxel scaffold. This hybrid Gaussian-Voxel representation explicitly confines anchored Gaussians to a narrow band around surfaces defined by voxelized SDFs, which effectively improves representation efficiency and condenses floating Gaussians without sacrificing geometry quality. An implicit surface tethering loss further pulls individual Gaussian primitives closer to SDF-induced surfaces in a mutually regularized manner for improved reconstruction accuracy. Extensive experiments on diverse real-world indoor scenes from ScanNet++, ScanNetv2, and DeepBlending datasets demonstrate that our method achieves state-of-the-art surface reconstruction quality as well as superior novel view synthesis against leading baselines, while maintaining fast training convergence and real-time rendering. Code will be available at https://github.com/duzh11/VoxelGS.

Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks do not fully isolate audio visual association in noisy user generated videos. We introduce UGC-AVQA, a public UGC benchmark with 1,000 videos and 4,816 QA pairs, where an audio removal test ensures that benchmark questions require both acoustic and visual evidence. To reduce inference cost, we propose OMAC, a training free plug in compression method that preserves salient visual memory and temporally grounded audio anchors. To further make compact models robust to compressed inputs, we introduce O-MARC, a compression distillation framework for learning with memory compressed multimodal contexts. On Qwen2.5-Omni-3B, O-MARC improves the average score across four benchmarks to 45.8, outperforming full token inference at 44.1 and OmniZip at 41.0. OMAC also keeps inference efficient, reducing latency by 34.6\% (1.53$\times$ speedup) and memory by 34.7\% compared with full token inference.

Referring 3D Gaussian Splatting (R3DGS), which utilizes natural language for 3D object segmentation, has emerged as a crucial capability for embodied AI. However, existing methods typically rely on expensive per-scene manual annotation and per-view pseudo mask generation, which suffer from multi-view inconsistency and poor generalization to varying query specificities. To address this, we present TrackRef3D, a fully automatic pipeline that achieves open-world referring segmentation in 3D Gaussian Splatting (3DGS) without manual annotation by introducing a multi-view consistent track-then-label paradigm that fundamentally decouples object discovery from semantic grounding. Specifically, we propose a Trajectory-Aware Semantic Consensus Module (TSCM) which aggregates cross-view predictions via synonymous clustering and trajectory-aware voting to establish a canonical semantic identity, thereby ensuring multi-view consistency. Furthermore, we employ a visibility-aware description generation strategy to mitigate ambiguity and propose a Hybrid Training Strategy (HTS) that jointly optimizes coarse category semantics and fine-grained referential cues to ensure robustness under varying query specificities using a multi-positive contrastive objective. Extensive experiments on benchmarks demonstrate that TrackRef3D achieves state-of-the-art performance.

Style transfer with pre-trained diffusion models has advanced rapidly, but a core question remains underexplored: where in the model should style injection be strongest? StyleID, the leading training-free method, uses a single global parameter (gamma) uniformly across all layers and timesteps, which forces a fixed tradeoff between style quality and content preservation. We show this tradeoff is unnecessarily rigid. We systematically explore four dimensions of control: varying style injection strength across decoder layers, across denoising timesteps, and scheduling ControlNet geometric conditioning along both axes. The pattern is consistent everywhere: decreasing schedules, with stronger structural signal injection in shallower layers and earlier timesteps, reliably outperform the reverse. Beyond direction, schedule shape matters: cosine and square-root timestep schedules outperform linear. Most importantly, we find that gamma scheduling and ControlNet conditioning are nearly independent. The resulting combined configurations expand the Pareto frontier, offering superior tradeoffs between style fidelity and content preservation compared to any single baseline setting. Our best balanced configuration achieves ArtFID of 27.036 versus StyleID's 28.801 - a 6.1% relative improvement, with consistent gains across the full style-content tradeoff frontier. Results are validated across 35 configurations totaling over 28,000 stylized images using four complementary metrics. These findings generalize across SD backbones with identical rank ordering. All modifications are training-free, parameter-free, and require only a few lines of scheduling code; code is available at https://github.com/ameyskulkarni/scheduled_style_injection.

Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without incurring high computational cost remains a fundamental challenge, as existing approaches face a critical speed-fidelity trade-off. In this work, we introduce Recursive Flow Matching (RecFM), a generative framework for forecasting complex spatiotemporal dynamics. RecFM enforces self-consistency to align trajectories across discretization scales, reducing discretization errors and improving performance across metrics for physics-based tasks. To our knowledge, this is the first method to achieve high-fidelity one- and few-step (2-4 step) dynamic generation for scientific systems with performance comparable to state-of-the-art multi-step solvers. Across challenging scientific benchmarks, RecFM achieves up to a 20$\times$ speedup over leading diffusion-based emulators while improving predictive accuracy. Furthermore, RecFM reduces mean squared error by over 15% compared to vanilla flow matching, offering a scalable and efficient solution for real-time scientific emulation.

Automated industrial inspection requires both precise defect localization and structured maintenance report generation; in current practice these tasks are handled separately, with linguistic interpretation left to human experts. This paper describes a decoupled, edge-deployable pipeline for wind turbine blade inspection built from three components that each handle a distinct sub-task. The Eyes a YOLO26-x-obb oriented bounding-box detector localizes defects at dataset-native resolution. The Bridge a deterministic, parameter-free encoding module maps each detected bounding box to grid-referenced spatial tokens embedded in a structured prompt. The Brain a 4-bit quantized Qwen-2.5-1.5B model adapted with Quantized Low-Rank Adaptation (QLoRA) on 947 synthetically generated maintenance reports generates a structured JSON report from that prompt. Retrieval-Augmented Fine-Tuning (RAFT) further grounds each recommendation in indexed maintenance procedures. Five ablation experiments, scored by BLEU-4, ROUGE-L, Hallucination Rate (HR), and an LLM-as-a-Judge rubric, compare the pipeline against a monolithic vision-language model (VLM) baseline and against partial configurations in which one component is removed. The complete system achieves BLEU-4 0.41, HR=4%, and Expert Score = 8.6/10 compared with 0.07, 65%, and 3.3/10 for the zero-shot VLM baseline. The QLoRA-adapted 1.5B model generates higher-quality reports than a 671B-parameter generalist API model given identical detection evidence, at 47 tokens per second on a single T4-class GPU. The results show that purpose-built decoupled architecture with a small domain-specific training corpus outperforms a generalist end-to-end model on this structured generation task.

Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challenge: single-shot extrapolation preserves an anchor but lacks cinematic structure, while multi-shot storytelling imposes structure yet remains free to invent its visual states rather than continue an observed one. We define Multi-Shot Video Extrapolation (MSVE), a task that extends an observed frame or clip into a sequence of cinematically structured shots while preserving anchor state and advancing narrative intent. This setting operates under the finite per-call generation budget of short-video models. We identify three coupled bottlenecks: (1) global planners over-specify unsupported details from full screenplays; (2) shot-level prompts dilute task-relevant state when carrying the complete story; and (3) temporal chaining turns generated frames into a lossy memory in which identity, scene, object, and action state decay. MSVE reveals that long-video failure is not merely a limitation of context length, but a failure of context allocation. We propose Recursive Context Allocation (ReCA), an inference-time framework that allocates context hierarchically across planning and generation. ReCA recursively decomposes MSVE into context-bounded subproblems, invokes frozen generators at leaf nodes, and propagates structured state updates across time. To evaluate this setting, we further propose MSVE-Bench and NB-Q, a source-grounded protocol with prompts purpose-built for 3 to 5 minute long-video generation, a regime not addressed by existing short-clip benchmarks. Compared to previous methods, ReCA improves average normalized score by 8 to 16 percent over the strongest competing controller and improves multi-shot consistency metrics by 28 to 43 percent. View the project page at https://reca.vmv.re.

Maritime intelligent transportation systems (MITS) are essential for ensuring navigation safety and efficiency in busy waterways. However, accurate vessel trajectory prediction remains challenging due to the limitations of single-source data. Automatic identification system (AIS) data is often sparse or unavailable for small vessels, while closed-circuit television (CCTV) data alone cannot fully capture dynamic vessel behavior. To mitigate these challenges, we propose a cross-modal interaction-based vessel trajectory prediction (named CmIVTP) framework to model the intricate interactions between vessel dynamics and environmental constraints. Specifically, we introduce a target-aware scene encoder to extract scene semantic features, effectively capturing vessel-environment interactions and enhancing trajectory prediction accuracy. In addition, we propose a cross-modal interaction transformer, which integrates AIS-derived motion features, CCTV-based environmental features, and scene representations. It leverages cross-modal attention mechanisms to simultaneously capture intra-modal semantics and inter-modal interactions, ensuring dynamically consistent and environmentally feasible predictions. Furthermore, we construct a vessel group trajectory bank by clustering historical AIS trajectories into representative motion patterns, providing an efficient and scalable approach for candidate trajectory generation. Additionally, we introduce the maritime multimodal dataset plus (named Maritime-MmD$^+$), a large-scale dataset that synchronizes AIS data and CCTV video data, providing robust support for multimodal trajectory prediction research. Extensive experiments demonstrate that CmIVTP achieves better performance on multimodal-driven vessel trajectory prediction benchmarks. The code resources for this work can be available at https://github.com/LouisYxLu/CmIVTP.

While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual challenges. In contrast, human-like thought typically involves long-horizon reasoning with an interleaved visual-textual chain-of-thought (VT-CoT). To bridge this gap, we introduce InterSketch, an interleaved reasoning model to enhance the VT-CoT capability via self-correcting and stepwise reward mechanisms. InterSketch dynamically generates intermediate visual sketches using external tools and interleaves them with textual reasoning, enabling effective perception and logical reasoning over long-horizon visual understanding tasks. Specifically, in the first cold-start stage, we propose a synthesized high-quality interleaved VT-CoT dataset and include a reflection mechanism to enable the model's capability in multi-turn interleaved reasoning and self-correction. In the subsequent reinforcement learning (RL) stage, we design a stepwise reward mechanism to mitigate the sparsity of reward signals inherent in end-only supervision over long-horizon reasoning. Extensive experiments on visual reasoning benchmarks demonstrate the effectiveness of InterSketch, even outperforming proprietary models such as Gemini-3-Pro.

Confirming Alzheimer's disease (AD) typically relies on positron emission tomography (PET), which remains costly and invasive, motivating the use of structural MRI-based prescreening. Deep learning on non-Euclidean manifolds, particularly brain cortical surfaces, faces significant challenges due to the data's spherical topology. Recent surface models have enabled learning from cortical surface data; however, imposing face-based uniform patches often causes duplicate vertices at patch boundaries. In general, many surface-based models are limited in their awareness of the region of interest (ROI), which can result in non-cortical regions, such as the medial wall, being included. We propose a cortical surface tokenization that performs ROI-preserving, vertex-based, variable-sized patch partitioning. We refer to these cortical surface patches as cortical supervertices (CSVs). Building on this representation, we design the CSV Vision Transformer (CSV-ViT), a variable-size patch-tolerant Vision Transformer that uses padding and a mask-aware patch embedding. We used T1-weighted MRI and evaluated our framework by classifying AD-related status into three categories: AD diagnosis, amyloid positivity, and tau positivity. Across the experiments, CSV-ViT achieved higher classification performance than recent surface-based models. The results suggest that the proposed CSV-ViT may support MRI-based prediction of AD-related status prior to PET or CSF confirmation.

Mean Deviation (MD) is a critical metric for assessing visual field loss in ophthalmology. While previous work has focused solely on predicting MD from Optical Coherence Tomography (OCT), it is intuitive to assume that combining OCT with another imaging of fundus photography (FP) could improve performance, as two ophthalmic medical imaging provide complementary information. This is particularly expected when sophisticated multi-objective optimization is applied, as documented in common multimodal classification. Surprisingly, our investigations reveal that multimodal fusion in this medical imaging scenario performs worse than unimodal model. Through detailed analysis, we identify the root cause as a coupled imbalance between data distribution and modality learning conflict. This imbalance distorts the optimization landscape, leading to unstable training. To address this challenge, we propose the method of Rebalanced MultiModal Mean Deviation Regression (Re-M3Dr), a novel multimodal regression framework. We enhance unimodal representation through adaptive margin based supervised contrastive learning. Then, our framework stabilizes the joint optimization with the sharpness-aware gradient modulation. Experimental results on both public and private clinical datasets show average 29\% reduction in MSE compared to SOTA multimodal learning methods, demonstrating the superiority of Re-M3Dr. The code is available in the supplementary materials.

Vision-Language Navigation (VLN) requires an agent to navigate 3D environments following natural language instructions. During navigation, existing agents commonly encounter perceptual uncertainty, such as insufficient evidence for reliable grounding or ambiguity in interpreting spatial cues, yet they typically ignore such information when predicting actions. In this work, we explicitly model three forms of perceptual uncertainty (i.e., geometric, semantic, and appearance uncertainty) and integrate them into the agent's observation space to enable informed decision-making. Concretely, our agent first constructs a Semantic Gaussian Map (SGM), composed of differentiable 3D Gaussian primitives initialized from panoramic observations, that encodes both the geometric structure and semantic content of the environment. On top of SGM, geometric uncertainty is estimated through variational perturbations of Gaussian position and scale to assess structural reliability; semantic uncertainty is captured by perturbing Gaussian semantic attributes to reveal ambiguous interpretations; and appearance uncertainty is characterized by Fisher Information, which measures the sensitivity of rendered observations to Gaussian-level variations. These uncertainties are incorporated into SGM, extending it into a unified 3D Value Map, which grounds them as affordances and constraints that support reliable navigation. Comprehensive evaluations across multiple VLN benchmarks show the effectiveness of our agent.

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial attacks, particularly those exploiting both modalities, remains underexplored, posing risks to critical applications like autonomous driving and content moderation. Existing attacks focus on single modalities or require impractical white-box access, limiting their real-world relevance. In this paper, we introduce Multi-Modal Adversarial Synergy, a groundbreaking framework that crafts universal, black-box multi-modal attacks against LVLMs. MMAS simultaneously generates a texture scale-constrained universal adversarial perturbation for images and a learnable prompt perturbation for text, optimized jointly using only model queries. The image perturbation leverages wavelet-based texture constraints to ensure imperceptibility and robustness across diverse visual inputs. The text perturbation, constrained by an L-norm in the embedding space, maintains semantic coherence while steering outputs toward a target. A novel cross-modal regularization term aligns the perturbations' gradient directions, enhancing their synergistic impact and transferability across tasks and models. Extensive experiments show the strong universal adversarial capabilities of our proposed attack with prevalent LVLMs.

Vision-language navigation (VLN) requires an agent to traverse complex 3D environments based on natural language instructions, necessitating a thorough scene understanding. While existing works equip agents with various scene representations to enhance spatial awareness, they often neglect the complex 3D geometry and rich semantics in VLN scenarios, limiting the ability to generalize across diverse and unseen environments. To address these challenges, this work proposes a 3D Gaussian Map that represents the environment as a set of differentiable 3D Gaussians and accordingly develops a navigation strategy for VLN. Specifically, Egocentric Scene Map is constructed online by initializing 3D Gaussians from sparse pseudo-lidar point clouds, providing informative geometric priors for scene understanding. Each Gaussian primitive is further enriched through Open-Set Semantic Grouping operation, which groups 3D Gaussians based on their membership in object instances or stuff categories within the open world, resulting in a unified 3D Gaussian Map. Building on this map, Multi-Level Action Prediction strategy, which combines spatial-semantic cues at multiple granularities, is designed to assist agents in decision-making. Extensive experiments conducted on three public benchmarks (i.e., R2R, R4R, and REVERIE) validate the effectiveness of our method.

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise comparisons. This pairwise reduction is limiting when training data naturally contains multiple candidate images for the same prompt, and when continuous reward scores can provide richer information than a single winner-loser label. To address these limitations, we propose Diffusion LAIR, a reward-aware listwise preference optimization method for diffusion models. For each prompt, LAIR converts reward scores across a group of candidate images into centered advantage weights, then optimizes an advantage-weighted regression objective on the implicit reward, defined as the denoising-loss improvement of the current model over a fixed reference model, with a quadratic penalty that regularizes the magnitude of the implicit reward. The resulting objective uses all candidates simultaneously rather than selecting pairs, and remains conservative by explicitly controlling the magnitude of the implicit reward. The LAIR objective admits a bounded closed-form optimum in implicit-reward space, clarifying how the regularization strength controls the magnitude of the preference update. Experiments show that Diffusion LAIR outperforms strong preference optimization baselines on SD1.5 and SDXL across text-to-image generation, compositional generation, and image editing benchmarks.

Despite advances in audio-driven video generation, achieving commercial-grade stability remains challenging. We present LongCat-Video-Avatar 1.5, an upgraded open-source framework prioritizing systematic engineering and production-readiness over architectural novelty. By upgrading the audio encoder to Whisper Large and meticulously scaling our training recipes, v1.5 achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency. Through rigorous data curation and RLHF Training, the model readily generalizes to stylized domains such as anime and animals, and natively handles complex real-world conditions, such as multi-person interactions and object handling. Furthermore, addressing the practical demands of industrial deployment, we employ advanced step distillation to accelerate inference to an optimal 8 NFE, achieving a favorable trade-off between serving efficiency and visual fidelity. The superiority of our approach is validated through extensive quantitative metrics and a rigorous human evaluation conducted on a comprehensive benchmark of over 500 diverse test cases. Results show that v1.5 achieves competitive or superior performance compared to leading closed-source systems (e.g., HeyGen, OmniHuman 1.5, Kling Avatar 2.0) across human-likeness ratings and expert-level quality assessments on our benchmark. With its open-source release, LongCat-Video-Avatar 1.5 narrows the gap between academic research prototypes and commercial-grade deployment.

We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline video understanding or text-prompted streaming QA, OmniInteract preserves the original audio-visual stream and requires models to process it online, without access to future content. User queries and ambient sounds are embedded in the audio track, requiring models to detect multimodal triggers, decide when to respond, and answer while the stream unfolds. OmniInteract contains 250 videos with 1,430 temporally grounded response slots: 1,062 1Q1A slots across real-time, proactive, and nested scenarios, and 368 1QnA slots for continuous task monitoring and step guidance. Each slot includes a trigger, response window, and target answer. We evaluate response correctness, timing, invalid outputs, interruption handling, and context continuity using Interaction-Aware Quality-Timeliness F1, Interruption Diagnostic Suite, and Nested Chain Completion Score. Experiments show that current models remain weak in streaming interaction, with the best overall IA-QTF1 reaching only 0.368 and the best 1QnA IA-QTF1 only 0.052. Further study on mathematical reasoning in full-duplex settings shows that offline capability does not necessarily transfer to online interaction. Code and datasets will be made publicly accessible at https://github.com/Lucky-Lance/OmniInteract.

Medical video diagnosis involves inferring clinical decisions from dynamic tissue responses throughout examination processes. Existing methods rely on an end-to-end learning paradigm that i) focuses on appearance rather than pathology, ii) lacks clinical priors, and iii) reasons solely from observations without counterfactual comparison. This work introduces MedVCR, a counterfactual reasoning framework that mimics clinical diagnostic thinking. MedVCR comprises three components: a Counterfactual Generator that synthesizes tissue evolution under specified pathological states via a diffusion-based manner; a Counterfactual Representation Learning module that encodes diagnostic knowledge through clinical rules (i.e., temporal consistency, pathological separability, and counterfactual alignment); and a Dual Diagnostic Prediction strategy that integrates video-level assessment with frame-level counterfactual analysis. MedVCR is evaluated under both fully supervised (e.g., colposcopy) and weakly supervised (e.g., colonoscopy) video diagnosis settings, yielding 2.6%-10.2% performance gains compared with leading baselines. Comprehensive ablation studies further validate the effectiveness of each component. The code will be released.

We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end within a few hours on a single NVIDIA RTX 4080 GPU. SDPG estimates policy gradients via random perturbations of trajectory rollouts, requiring orders of magnitude fewer batch-rendered environments and substantially reducing compute and memory overhead. On visual MuJoCo benchmarks, SDPG consistently outperforms baseline methods in training time, memory usage, and rewards. Finally, to support future research, we introduce a suite of realistic visual robotics benchmarks spanning dexterous manipulation, challenging locomotion, and demonstrate effective sim-to-real transfer on physical hardware.

Vision-based metric distance and area measurement remains challenging in large-scale outdoor environments due to long-range sensing, camera zoom, and unstable imaging conditions. This work studies planar metric measurement in a real-world reservoir monitoring scenario using PTZ cameras and compares three representative approaches: geometry-based monocular ranging, image stitching with birds-eye-view transformation, and stereo-based ranging using two jointly calibrated monocular cameras. For monocular ranging, planar localization models are derived from camera geometry and the effect of camera pitch angle is analyzed. Image stitching is investigated for large-area mapping, while a stereo-based scheme is developed for long-range measurement without dedicated stereo hardware. Experiments show clear trade-offs: monocular ranging achieves meter-level accuracy under sufficiently large pitch angles, stereo-based ranging achieves decimeter-level accuracy with reduced sensitivity to pitch variations, and image stitching is effective for small-scale scenes but degrades in stability and scalability as scene size increases.

Generative posterior sampling using diffusion models has emerged as a dominant paradigm for solving inverse problems in imaging, which usually consists of three main components: data consistency (DC) guidance, classifier-free guidance (CFG) and stochasticity. While prior arts have focused on how to develop each or all components, less attention has given to how to schedule them, leading to heuristically fixed or partially adjusted suboptimal schedules. In this work, we argue that the interactions among all three components in terms of scheduling are crucial for significantly improved performance in solving inverse problems in imaging. Our analysis shows that aggressive CFG early in sampling conflict with DC guidance, while stochasticity brings the trajectory back to higher-probability regions. Based on these findings, we propose Triadic Dynamics Aware Posterior Sampling (TriPS), which reformulates posterior sampling as a time-varying control problem and optimizes schedules following a triadic trend of decreasing DC and stochasticity scales alongside increasing CFG scale. TriPS achieves this through two strategies: template-based search over functional priors for reliable baseline schedules, and Group Relative Policy Optimization (GRPO)-based reinforcement learning for more flexible temporal curves. Experiments demonstrate TriPS outperforms state-of-the-art baselines in data fidelity and perceptual realism.

Multi-Modal Diffusion Transformers (MM-DiTs) encode rich representations for training-free concept grounding, but existing attention-based methods often produce overlapping activations on visually confusable concepts, a failure mode we call concept leakage, where target responses spill over to non-target objects. To address this issue, we propose AnchorDiff, a training-free grounding method that decouples semantic localization from structural refinement. AnchorDiff selects a high-confidence anchor from concept-to-image attention map and propagates it as a one-hot seed over a hybrid graph derived from image-to-image self-attention. The graph uses output-space similarity for dense within-object propagation and a row-wise attention gate to suppress cross-object connections. Additionally, we introduce the Multi-Concept Confusion Dataset, which contains images with multiple visually similar concepts and separate masks, enabling explicit evaluation of concept leakage. Experiments show that AnchorDiff achieves strong grounding performance on ImageNet-Segmentation and PascalVOC, while substantially reducing concept leakage on our Multi-Concept Confusion Dataset.

Sparse-LiDAR-prompted depth foundation models (PromptDA, Prior Depth Anything, DMD3C) have shown strong results on indoor scenes or within KITTI's standard 80-meter evaluation cap. However, two limitations remain: (i) systematic distance-stratified evaluation in long-range driving regimes (50-150 m) is largely absent; (ii) prior approaches built on disparity-based foundations rely on pre-interpolated dense priors, leaving truly sparse LiDAR injection on point-map foundations (e.g., MoGe-2, NeurIPS 2025) unexplored. We present SLIM (Sparse-LiDAR Injected Monocular geometry), the first adaptation of MoGe-2 to accept truly sparse LiDAR input. SLIM integrates a partial-convolution sparse encoder with a multi-scale fusion neck that fuses LiDAR features into the point-map decoder at five scales. We adopt density-agnostic training (random injection ratio in [0.005, 0.30]) so a single model serves diverse input densities. On Virtual KITTI and CARLA, SLIM reduces the absolute relative error of the MoGe-2 baseline by approximately 39-51% at 100-150 m. Ablation across six injection ratios shows partial-convolution injection improves both AbsRel and RMSE on Virtual KITTI in all six settings; on CARLA, AbsRel improves in five of six settings (one near-tie at 0.015 differs by 0.0013), and RMSE is comparable across encoders, with partial-convolution improving in three settings (by up to 0.31 unit) and losing by at most 0.11 unit in the other three.

Producing presentation slides automatically entails coordinating narrative structure with page-level graphic design under strict spatial constraints. For such structured multimodal tasks, a well-organized design process is essential to ensure the final quality of slides. Existing approaches rely on fixed templates or directly emit executable code, thereby both limiting the creative layout-design capabilities of LLMs and bypassing the essential slide-page design step. To address these limitations, this paper (1) proposes a hierarchical slides generation workflow, DeepSlides, that systematically organizes slide design tasks without any predefined template or style, decoupling slide-page design from implementation; (2) introduces SlideDesign, a dataset tailored specifically for slides generation tasks; and (3) presents a multi-agent reinforcement learning training paradigm and trains a couple of models, SlideQwens, for slide design and implementation. Experimental results demonstrate that our proposed framework outperforms baseline methods on evaluated metrics and achieves superior performance in human preference evaluations. The dataset and code are available at https://github.com/sxswz213/DeepSlides.

Modern GANs often introduce adversarial supervision on intermediate generator outputs and interpret the resulting multi-stage synthesis as coarse-to-fine hierarchical generation. In this work, we challenge this interpretation. We argue that standard scale-wise adversarial supervision does not construct a proper coarse-to-fine hierarchy: each intermediate image is independently pushed toward the real distribution at its own resolution, but this scale-wise realism does not ensure that outputs across stages represent the identical generated sample. Moreover, the scale-specific image produced at each stage is not used as an explicit refinement target for the subsequent stage. Therefore, its adversarial loss can improve a scale-specific output without constraining later stages to preserve the same sample trajectory, allowing them to move toward a different sample rather than refine the previous output. We refer to this problem as a cross-scale trajectory misalignment problem. To resolve it, we propose CAT, a Cross-scale Aligned Transformer for multi-scale adversarial generation. CAT keeps the discriminator scale-wise, so each intermediate output is evaluated at its own resolution, while adding a simple generator-side consistency regularization that aligns intermediate outputs with the final output. On class-conditional ImageNet-256, CAT-H/2 achieves an FID-50K of 1.56 with one-step inference after only 60 training epochs, outperforming strong one-step GAN and diffusion/flow baselines.

Underwater scene reconstruction is essential for immersive exploration of aquatic environments, yet remains challenging due to complex participating-media effects such as absorption and scattering, as well as the limited field of view (FoV) of conventional cameras. Although combining panoramic imaging with 3D Gaussian Splatting (3DGS) offers a promising direction for photorealistic underwater rendering, traditional 3DGS struggles with both spherical projection distortion and underwater medium degradation. In this paper, we propose \textbf{Underwater360}, a physics-informed omnidirectional 3DGS framework for underwater panoramic scene reconstruction. First, we introduce an Omnidirectional Gaussian Splatting module that performs ray casting directly in spherical camera space instead of relying on 2D projection approximations, thereby reducing geometric distortions under 360$^\circ$ FoV. Second, we design a physics-based appearance-medium modeling architecture with pose-conditioned appearance embeddings to explicitly decouple intrinsic scene radiance from depth-dependent backscatter and attenuation, enabling physically grounded scene appearance restoration. Finally, we establish a new panoramic underwater benchmark dataset containing both synthetic and real-world scenes. Extensive experiments demonstrate that Underwater360 achieves superior performance in underwater novel view synthesis and scene appearance restoration, delivering improved rendering quality and cross-view consistency in complex underwater environments. The code and datasets are released at https://github.com/SwcK423/Underwater360

This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks have overlooked two indispensable issues: 1) Coarse-grained cross-modal learning: previous methods solely capture the global video-level alignment with the query, failing to model the detailed consistency between video frames and query words for accurately grounding the moment boundaries. 2) Complex moment proposals: their performance severely relies on the quality of proposals, which are also time-consuming and complicated for selection. To this end, in this paper, we make the first attempt to tackle this task from a novel game perspective, which effectively learns the uncertain relationship between each vision-language pair with diverse granularity and flexible combination for multi-level cross-modal interaction.Specifically, we creatively model each video frame and query word as game players with multivariate cooperative game theory to learn their contribution to the cross-modal similarity score. By quantifying the trend of frame-word cooperation within a coalition via the game-theoretic interaction, we are able to value all uncertain but possible correspondence between frames and words. Finally, instead of using moment proposals, we utilize the learned query-guided frame-wise scores for better moment localization.Experiments show that our method achieves superior performance on both Charades-STA and ActivityNet Caption datasets.

The rapid evolution of generative models has precipitated a proliferation of fabricated content, posing significant challenges to existing Synthetic Image Detection (SID) methods. Capitalizing on advancements in vision-language models (e.g., CLIP), recent attempts have leveraged learnable textual prompts to identify synthetic images. However, they still leverage static prompt as a fixed boundary for real and fake images, failing to adapt to the varying types of forgery that emerge during inference. To overcome this issue, we propose **HydraPrompt**, an asymmetric prompting framework that dynamically adjusts the category centers by aligning with fine-grained image cues. Specifically, we propose an Asymmetric Prompt Adapter (**APA**): (1) for authentic category, we introduce a single set of prompts to capture the consistent representative patterns, which serves as a unified anchor for real content. While (2) for fake category, we construct sample-adaptive prompts that specialize in capturing diverse cues from different samples, enabling adaptive modeling of forgery image variations. To increase pronounced discriminability within different synthetic images, we further introduce a Conditional Supervised Contrastive (**CSC**) objective, which compacts the authentic representations while capturing fine-grained forgery clues. Extensive experiments on popular SID benchmarks demonstrate the state-of-the-art performance of our framework.

Deploying Vision-Language Models on resource-constrained hardware typically requires INT8 quantization, but in joint-embedding architectures such as CLIP this introduces a failure mode distinct from quantized CNN classifiers: activation noise accumulated across transformer blocks perturbs the direction of the multimodal embedding, eroding the cosine alignment on which zero-shot retrieval depends. We characterize this as Quantization-Induced Representation Collapse (QIRC) and quantify it on INT8 CLIP ViT-B/32, where the layer-wise noise-to-signal ratio grows from below 10% in shallow blocks to 52% at Layer 11. We propose LRA-EE (Layer-wise Representation-Aware Early Exit), which bypasses noise-saturated deep layers via Spatio-Semantic Aggregation (replacing the immature shallow [CLS] with a global patch-token average), a learned multi-feature gate (confidence, top-2 margin, spatial-activation variance), and Layer-adaptive Confidence Thresholding calibrated to each layer's Information-to-Noise Ratio. On ImageNet-1K zero-shot classification, LRA-EE reduces FLOPs by 13.4% and improves Top-1 accuracy by +2.44%p (58.72% -> 61.16%) over the INT8 baseline. A four-quadrant decomposition isolates the Rescue Effect: 9.5% of samples are correctly classified at shallow exits but lost to noise at full depth, against only 7.1% suffering the inverse.

Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typically restricted to pure spatial localization, lacking the high-level capacity to reason about semantic targets or complex social contexts. Furthermore, these models often process individuals sequentially, requiring redundant computations over the same scene image for multi-person inference. While recent Vision-Language Models (VLMs) offer the exceptional semantic reasoning needed to address gaze-related semantic tasks, their reliance on discrete text generation inherently limits precision in continuous spatial tasks like gaze localization. To bridge this gap, we propose OmniGF, a unified vision-language framework that adapts foundational VLMs for highly scalable multi-person gaze reasoning. The model adopts a dual-branch decoding strategy: a structured language branch generates discrete reasoning states, while a continuous spatial branch directly taps into the VLM's dense hidden states. Supervising these extracted representations with high-resolution gaze target heatmaps effectively overcomes the spatial bottleneck of text-only coordinate generation. Furthermore, to explicitly ground the model in multi-person scenes, we augment the input with head embeddings encoded from cropped head images, providing fine-grained appearance and orientation cues for all individuals simultaneously. By modeling all individuals and leveraging the strong semantic capability of VLMs, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning. Extensive experiments demonstrate that our framework establishes new state-of-the-art performance across multiple standard benchmarks. Code is available at https://github.com/cvlab-stonybrook/omnigf.

Object re-identification (ReID) in egocentric kitchen videos is challenging due to rapid viewpoint changes, frequent occlusions, cluttered scenes, and large intra-class appearance variations. Objects may leave and re-enter the field of view, and the large diversity of instances with limited annotations makes supervised ReID difficult to scale, motivating zero-shot approaches. We study zero-shot object ReID on the EPIC-Kitchens benchmark, where the goal is to match active food and kitchen-tool instances across frames using only pre-trained visual features. We first evaluate five state-of-the-art feature extractors, including Vision-Language Models (VLMs) - CLIP, DINOv2, DreamSim, I-JEPA, and SAM3 - and show that zero-shot methods fail, with the best baseline achieving only 45.3% mAP. We then propose an Enhanced SAM3 ReID Pipeline, a zero-shot multi-stage method built around SAM3 segmentation as the core component. Stage 1 uses SAM3 to suppress background clutter. Stage 2 fuses embeddings from SAM3, DINOv2, and CLIP into a single L2-normalized descriptor. Stage 3 augments cosine similarity with mask-shape IoU for geometric consistency, and Stage 4 applies k-reciprocal re-ranking. The full pipeline improves performance by 7.5% mAP to 52.8%.

Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefore necessary, but compact 3D encoders tend to lose fine structural cues (small lesions and sharp boundaries) as downsampling repeats across multi-resolution stages. We propose Detail Consistent Distillation (DCD), a stage-wise distillation framework that preserves structural detail across scales by aligning teacher-student features in a wavelet-decomposed representation. At each encoder stage, DCD distills directional detail components in the wavelet domain while leaving the coarse approximation comparatively unconstrained, avoiding over-regularization of global semantics. DCD is used only during training and introduces no inference-time overhead. Experiments on the BraTS 2024 and ISLES 2022 benchmarks demonstrate that our approach achieves superior performance in MRI segmentation using 3D multi-modal data. Code and implementation details for DCD are publicly available at https://github.com/ClinicaAlpha/DCD-3D-MedSeg.

We present a multi-modal classification framework that fuses satellite and street-level imagery through a Perceiver IO architecture operating on spatial patch tokens from a shared DINOv2 backbone. The design naturally handles a variable number of street-level views per building without padding or fixed-size pooling, and jointly predicts multi-label roof element and roof material classes. We construct a large-scale dataset of 32,135 buildings (61,672 segments) spanning ten countries, pairing satellite images with up to eight street-level views per segment and evaluating four masking strategies for isolating the target building. We propose an RGB-M masking strategy that appends the building footprint mask as a fourth input channel, providing a soft spatial prior that outperforms hard cropping across both modalities. The Perceiver IO fusion model improves over all other fusion strategies and yields substantial per-class gains for attributes visible from street level (e.g., +11.3 AP for slate, +1.3 AP for dormers), though the satellite-only baseline retains a slight advantage in macro-averaged mAP for classes that are predominantly visible from above. These results establish a scalable, flexible architecture for multi-modal building inspection that can accommodate heterogeneous inputs and multiple output tasks.

Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on fine-grained perception benchmarks. However, such scores do not necessarily imply faithful use of visual evidence. Prior studies have identified three shortcuts that inflate benchmark performance. First, linguistic priors and lexical cues in questions often enable models to infer plausible answers without seeing the image. Second, coarse global semantics from the visual encoder can bypass fine-grained local details. Third, in some ``think-with-images'' benchmarks, corrupting the intermediate images returned by visual tools barely affects the final answer. These findings suggest that higher input resolution or larger question pools alone do not elicit genuine active visual search. To address this, we introduce VisualNeedle, a challenging, information-dense, and fine-grained benchmark for scenes where critical evidence is spatially constrained to minute regions and not discernible at a glance. We further propose a counterfactual crop-black setting, which replaces crops returned by tools with black images of the same size, to test whether tool-enabled performance truly relies on intermediate visual evidence. We evaluate 9 promninent MLLMs across three settings: no-tool, standard tool-enabled, and crop-black. No-tool accuracy stays below 20\%, and the best tool-enabled model reaches only 56.01\%, still trailing the 63.00% human majority-vote accuracy. These results reveal persistent limitations in fine-grained visual search, while the crop-black ablation confirms that success on VisualNeedle hinges on genuine intermediate visual evidence.

Hepatocellular carcinoma (HCC) is biologically heterogeneous, shaped by the interplay between hepatic functional reserve and tumor-related oncologic factors; thus, similar survival outcomes may reflect fundamentally different underlying biological processes. Prognostic modeling in HCC is informed by rich multimodal information from multiparametric MRI and radiology reports from routine clinical practice. Existing prognostic vision-language models (VLMs) learn a single entangled latent representation that blends hepatic and tumor-related factors, limiting both accuracy and biological interpretability. We present BioFact-MoE, a biologically factorized Mixture of Experts (MoE) framework that explicitly decomposes liver and tumor factors via biologically supervised experts within a residual MoE survival architecture. On a HCC cohort of N=588 patients (pretrained on 4,582 3D MRI image-report pairs), BioFact-MoE consistently improves survival prediction over all baselines across time horizons, achieving 12-, 18-, and 24-month AUCs of 75.33%, 75.85%, and 73.96%. Beyond scalar risk prediction, gated expert weights enable phenotype-aware risk stratification. Pathway-informed gating uncovers clinically meaningful treatment-associated survival heterogeneity. In held-out validation, hepatic and tumor embeddings show selective associations with liver function and tumor burden markers, respectively (p<0.05), without supervision. The code is available at https://github.com/jy-639/BioFact-MoE.

We present a method for jointly predicting instance-level roof segment masks together with three continuous geometric attributes -- building height, roof slope, and roof azimuth -- from a single aerial orthophoto. Our approach extends Mask R-CNN with a dedicated attribute regression branch and introduces two key innovations: a conditional azimuth loss that suppresses supervision for flat roof segments where azimuth labels are inherently noisy, and a log-normalized height representation that addresses the heavily skewed distribution of building heights. We train and evaluate on a large-scale dataset of Dutch aerial images paired with automatically derived ground truth from 3DBAG, a nationwide LiDAR-based 3D building dataset. Using a DINOv3 ConvNeXt-Base backbone, our method achieves a mean absolute error of approximately 4 degrees for roof slope, 7 degrees for azimuth, and 1 meter for building height, with an instance segmentation AP$_{50}$ of 0.566. The predicted per-segment masks and attributes are sufficient to reconstruct simplified 3D building models (LoD2) from a single overhead image, requiring expensive 3D reference data only for training.

Different visual patterns appear with different frequencies in the world: e.g., beach balls appear on sand more often than they do on a road. These statistics are reflected in vision datasets, and as a result trained models more easily recognize objects in common scenarios. However, recognizing a beach ball on a road may arguably be even more important than recognizing it on sand. We study how to mitigate this discrepancy. Since collecting uncommon images in the real world may be difficult, we explore whether generating images with less frequent contexts can serve as effective training augmentation. A key challenge is guiding generations to remain close to the original dataset distribution while creating diverse images with uncommon contexts. We introduce Decoupling Contextual Patterns with Generations (DecoupleGen), a method that personalizes text-to-image diffusion models to facilitate coherent synthesis of images with rare contexts while preserving original visual details. The generated images contain semantically meaningful content and remain visually aligned with the original datasets. We further apply verification constraints to ensure relevance of the augmented data. We evaluate our approach on object classification and recognition tasks on complex scene datasets. Our experiments demonstrate consistent improvements over previous approaches, and our analyses identify factors underlying these improvements.

Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks, nevertheless, do not assume a realistic threat model, i.e. they either assume access to the model weights, or result in gibberish adversarial prompts that could be easily detected even through naive rule-based safeguarding. We aim to address this gap in this paper. We introduce BEAP, a black-box, embedding-aware adversarial prompting attack that leverages a large language model (LLM) to iteratively generate effective adversarial prompts and exploit such hidden vulnerabilities. BEAP performs an embedding-aware search in text space, combining multiple reward signals: unlearned concept presence, text-image alignment, and image quality, to refine generated prompts. Unlike previous attack methods, BEAP keeps its prompts undetectable to safety filters while producing high-quality images. Extensive experiments show that BEAP improves the Attack Success Rate (ASR) by more than 60% over prior methods, while requiring only an average of fifteen prompts per successful attack. Warning: This paper contains model outputs that may be offensive or upsetting in nature.

Radars are an ideal complement to cameras: both are inexpensive, solid-state sensors, with cameras offering fine angular resolution, while radars provide metric depth and robustness under adverse weather. However, radar data is more difficult to interpret than camera images and varies significantly between sensors, necessitating increased reliance on simulation for prototyping sensors and processing pipelines. Recent work treating radar reconstruction as a novel view synthesis problem has shown great promise in reconstructing radar-relevant geometry and simulating low-level radar data. However, such methods are constrained by the low spatial resolution of the underlying radar. To address this, we propose a unified differentiable renderer, RadarSim, which leverages the high angular resolution of RGB cameras to generate Doppler radar range images from a camera-initialized neural field. Using a novel data set of calibrated radar camera recordings from a custom hand-held rig, we demonstrate that RadarSim produces sharper geometry and Doppler range frames than radar-only reconstructions.

Controllable and physically grounded egocentric video generation is essential for embodied agents to reason about how their own and others' actions manifest and change the world. Compared to generic video synthesis, egocentric generation is especially challenging: the camera is tightly coupled to the actor, leading to rapid viewpoint changes and frequent self-occlusions; the underlying actions are subtle, articulated, and often only partially visible; and both the people and the scene state must evolve consistently with the specified controls. We present E$^3$C, a controllable video diffusion framework for egocentric generation that builds structured and compact conditions disentangling persistent scene structure from human-driven dynamics. From context frames, E$^3$C constructs a semi-dense point cloud-based 3D memory and augments each point with appearance descriptors from video-VAE features. Rendering this memory into target viewpoints produces conditioning aligned with the target frames. Human dynamics are modeled separately. The observed people in the scene are controlled by skeleton renderings (exo human control), while the camera wearer is specified by their 3D body joints and 6DoF wrist motion (ego human control). To preserve ego human control when the wearer's body parts are invisible, we introduce an ego motion encoder that produces persistent cross-attention tokens. Experiments on Nymeria show that E$^3$C improves visual fidelity, camera-motion accuracy, object consistency, and ego & exo human control over strong baselines, while also enabling intuitive scene editing.

Accurate classification of sleep stages is crucial for diagnosing sleep disorders and automating this process can significantly enhance clinical assessments. This study aims to explore the use of a self-supervised model (more specifically, an adapted version of mulEEG) combined with a Linear SVM classifier to improve sleep stage classification. \textbf{Methods:} The mulEEG model, which learns electroencephalogram signal representations in a self-supervised manner, was simplified here by replacing ResNet-50 with 1D-convolutions used as time series encoder by a ResNet-18 backbone. Two other adaptations were conducted: the first one evaluated different configurations of the model and data volume for training, while the second tested the effectiveness of time series features, spectrogram features, and their concatenation as inputs to a Linear SVM classifier. \textbf{Results:} The results showed that reducing the volume of data offered a better cost-benefit ratio compared to simplifying the model. Using the concatenated features with ResNet-18 also outperformed the linear evaluations of the original mulEEG model, achieving higher classification performance. \textbf{Conclusions:} Simplifying the mulEEG model to extract features and pairing it with a robust classifier leads to more efficient and accurate sleep stage classification. This approach holds promise for improving clinical sleep assessments and can be extended to other biological signal classification tasks.

Skin cancer is a common and fast rising malignancy worldwide. Early detection is critical for improving outcomes. Deep learning models trained on dermoscopic and clinical images can support automated and fast triage. However, many studies evaluate only a limited set of architectures. Experimental setups also vary across studies. In this paper, we present a unified evaluation of twelve deep learning models for binary skin cancer detection on the PAD-UFES-20 dataset. The models span four families: convolutional neural networks (CNN), vision transformers (ViT), hybrid convolution transformer backbones, and vision language models (VLM). Performance is assessed using AUC, the maximum F1 score with its precision and recall, and sensitivity at 80% specificity, reflecting screening oriented requirements. Our results show that well tuned CNNs already provide strong baselines, but transformer based families consistently improve discrimination. Hybrid models (MaxViT Tiny, CoAtNet0) and a SigLIP based VLM achieve the best overall trade off between ranking performance and clinically relevant operating points, while CLIP based model offers high precision. The full codebase for all experiments is publicly released. Together, these findings offer practical guidance on which model families are most suitable for real world deployment in skin cancer screening and establish a reproducible reference point for future work on PAD-UFES-20.

Masked autoencoders (MAE) have shown great promise in medical image classification. However, the random masking strategy employed by traditional MAEs may overlook critical areas in medical images, where even subtle changes can indicate disease. To address this limitation, we propose a novel approach that utilizes a multifractal measure (Renyi entropy) to optimize the masking strategy. Our method, termed Multifractal-Optimized Masked Autoencoder (MO-MAE), employs a multifractal analysis to identify regions of high complexity and information content. By focusing the masking process on these areas, MO-MAE ensures that the model learns to reconstruct the most diagnostically relevant features. This approach is particularly beneficial for medical imaging, where fine-grained inspection of tissue structures is crucial for accurate diagnosis. We evaluate MO-MAE on several medical datasets covering various diseases, including MedMNIST and COVID-CT. Our results demonstrate that MO-MAE achieves promising performance, surpassing other basiline and state-of-the-art models. The proposed method also adds minimum computational overhead as the computation of the proposed measure is straightforward. Our findings suggest that the multifractal-optimized masking strategy enhances the model's ability to capture and reconstruct complex tissue structures, leading to more accurate and efficient medical image representation. The proposed MO-MAE framework offers a promising direction for improving the accuracy and efficiency of deep learning models in medical image analysis, potentially advancing the field of computer-aided diagnosis.

Modern deep learning offers powerful tools for automated retinal screening, but it remains unclear how different visual model families compare in realistic multi-disease settings and under domain shift. In this work, we benchmark twelve architectures across four model families: convolutional neural networks, vision transformers, hybrid CNN-transformer backbones, and vision-language models, using the Retinal Fundus Multi-disease Image Dataset (RFMiD). We evaluate two tasks: binary screening for any retinal disease and multi-label classification across 28 disease classes. Using standardized training, calibration, and evaluation protocols, we report AUC, F1, precision, recall, and sensitivity at a clinically relevant operating point with specificity near 80%. On RFMiD, all architectures perform well on binary screening, with AUC above 84%, but attention-based models perform best. SwinTiny and the hybrid CoAtNet0 and MaxViTTiny models achieve the strongest binary screening results and improve macro and micro F1 in the multi-label setting. Vision-language models, including CLIP ViT-B/16 and SigLIP-Base384, are competitive with CNN baselines but do not surpass the best transformer and hybrid backbones. In external validation on Messidor-2 for referable diabetic retinopathy, AUC ranges from 66.8% to 84.7%, with hybrid and transformer models again showing strong performance. These results provide a reproducible reference for model selection in multi-disease retinal screening and guide future automated screening tools for clinical deployment.

Semantic segmentation in complex environments such as urban driving scenes remains challenging under adverse lighting conditions, where RGB images alone provide insufficient information. RGB-Thermal fusion leverages the complementary strengths of visible and infrared imagery to improve scene understanding; however, effectively integrating these heterogeneous modalities at varying levels of feature abstraction remains an open problem. In this paper, we propose a multi-modal fusion architecture built upon dual ConvNeXt V2 backbones that employs stage-wise, modality-adaptive fusion strategies. For early-stage features, we introduce a Frequency-Based Fusion Module that decomposes infrared features into low- and high-frequency components via Gaussian filtering, applies dual-branch spatial attention to selectively emphasize thermal patterns and fine-grained boundaries, and integrates them with RGB features through a confidence-gated residual mechanism. For late-stage features, we design a semantic fusion module with cross-modal attention and multi-scale depthwise convolutions to capture semantic correspondences across modalities. The fused features are decoded via a PANet-style bidirectional decoder with deep supervision. Experiments on MFNet and PST900 demonstrate that our lightest variant achieves 61.73\% and 86.24\% mIoU, respectively, with only 35.43M parameters, outperforming recent methods while using substantially fewer parameters and lower computational cost. Code is available at https://github.com/ismailemrecntz/VISIBLE-INFRARED-SENSOR-FUSION

Chunk-wise autoregressive video diffusion models rely on a KV cache of previously generated chunks to avoid redundant computation, but this cache quickly becomes a memory bottleneck as videos grow longer. Methods that quantize the KV cache to low bitwidths reduce memory pressure but degrade video quality. We show that a key driver of this degradation is a systematic bias in attention weights: due to the convexity of the exponential in softmax attention, quantization noise inflates the contribution of cached keys, a phenomenon we call the Jensen bias. This effect causes quantized keys to steal attention mass from the unquantized current chunk. We derive a per-attention-score correction that removes this bias in expectation, computed on the fly from the quantization step sizes of the cached keys and the query norm. Using a second-order Taylor approximation, the additional computational overhead is negligible, and no additional memory is needed alongside the cache. Evaluated on MAGI-1, SkyReels-V2, and HY-WorldPlay at INT2 quantization, our correction recovers most of the quality lost to aggressive quantization, reaching near-BF16 video quality, and can outperform INT4 quantization while using 50% less memory.

Museums are important sites for the dissemination of culture and art. They are institutions rooted in history and tradition; their exhibitions are often designed to highlight these aspects. Recently, a new approach is being explored in the field: emotion-based exhibitions. These exhibitions are designed specifically to elicit emotions in the visitors, in order to maximize engagement, and as a way to democratize access to art and attract a wider, more diverse audience. To do so, the emotional content of the artworks must first be extracted, however, manually annotating the artworks by experts is a prohibitively labor-intensive process, and risks introducing the personal bias of curators. To assist the museum curators in their design of these exhibitions, we wish to develop a tool that can predict the emotional response evoked by a work of art. In this article, we leverage a continuous bi-dimensional emotion space to enhance emotion representations and the training process of deep learning models. Drawing inspiration from existing categorical and dimensional emotion representations, we introduce a new representation, Dimensional Distribution Emotion State (DDES), along with a pipeline for multi-dataset training. We show that DDES provides multiple advantages compared to widely used representations while exhibiting similar baseline performance.

Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned generation and rarely support unified evaluation across text, image, and video conditioning modalities. Moreover, they provide limited insight into how identity consistency, narrative coherence, and audio-visual alignment degrade over extended temporal horizons. To bridge this gap, we introduce LongAV-Compass, a systematic benchmark for minute-long audio-visual generation. LongAV-Compass contains 284 curated test cases spanning text-to-audio-video (T2AV), image-to-audio-video (I2AV), and video-to-audio-video (V2AV), organized by application scenario and generation complexity. The benchmark combines taxonomy-guided benchmark construction with a unified evaluation framework that integrates MLLM-assisted assessment with complementary perceptual and multimodal metrics, including DINO-v2, ArcFace, CLIP, and ImageBind. The framework evaluates more than 20 fine-grained dimensions covering within-segment quality, cross-segment consistency, global narrative coherence, semantic alignment, and audio-visual synchronization. Through experiments on 11 representative models together with human-alignment validation, LongAV-Compass provides a diagnostic testbed for analyzing the limitations of current systems in sustaining coherent, semantically aligned, and temporally consistent minute-scale audio-visual generation across diverse input modalities.

Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable models. 3D Human motion, however, has lagged behind, constrained by an unsatisfying choice between small, high-fidelity motion capture datasets and large-scale in-the-wild collections dominated by static or low-quality sequences. We introduce RoMo, a rich, large-scale, carefully curated dataset of in-the-wild human motions that resolves these tradeoffs. To ensure quality, we introduce a taxonomy-aware filtering pipeline that aggressively removes static and artifact-prone sequences. Every sequence is annotated with detailed captions and organized by a novel three-level semantic taxonomy. This hierarchical structure enables fine-grained, per-category evaluation, that reveals model strengths and weaknesses obscured by global metrics. We demonstrate that models trained on RoMo achieve state-of-the-art fidelity and diversity while gaining a superior understanding of complex, subtle text prompts. Finally, we release the Motion Toolbox to standardize metrics, data conversion, and visualization, establishing a foundation for reproducible and interpretable motion generation research.

In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmental constraints across city-scale outdoor domains. We introduce Sentinel Challenge, a benchmark where multiple decentralized embodied agents must communicate in natural language to agree on a mutually safe and convenient meeting point within large, city-scale outdoor environments. Each agent must then navigate safely while avoiding dynamic sentinels patrolling the area, using a tool that provides coarse spatial information. To address this, we propose CoSaR (Cooperative Spatial Reasoning and Planning), a framework that bridges the high-level communication and planning abilities of foundation models with the precision of classical spatial navigation algorithms. CoSaR enables agents to exchange situational updates, reason over evolving spatial constraints, and collaboratively replan trajectories. Evaluated across 14 city-level scenes with 3-5 agents, CoSaR consistently leads to faster gathering, shorter path lengths, and improved safety. Our results demonstrate that integrating dynamic communication with spatial reasoning is essential for robust multi-agent cooperation. By formalizing this new setting and providing a scalable benchmark, we aim to build a foundation for advancing cooperative spatial intelligence in embodied multi-agent systems. Code and challenge are available at https://github.com/UMass-Embodied-AGI/Sentinel.

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality interference, allowing irrelevant channels to distract the model. To address this issue, we present a unified multimodal video understanding framework, named UniMVU, that performs instruction-aware fusion across video, audio, depth map, or any other modality inputs via two levels of dynamic gating: inner-modality gates emphasize salient regions within each modality, whereas modality-level gates re-weight whole streams; both are conditioned on the text instruction to adaptively balance modality importance. Our UniMVU combines cross-modal self-attention with instruction-driven inner-modality gating module and a modality-level gating module with control token; for time-aligned streams we further adopt a fast-to-slow fusion scheme that reduces redundancy. Across six benchmarks (AVQA, AVSD, Music-AVQA, ScanQA, SQA3D and MVBench), our UniMVU achieves consistent gains over static-fusion baselines achieving gains as high as 13.5 in terms of CIDEr metric. Further, our analysis shows that the gating mechanism aligns with the human-interpretable modality relevance, and ablations show the contributions of inner-modality and modality-level gating. Our UniMVU provides a simple, unified recipe for instruction-aware multimodal video understanding that scales to diverse modalities without hand-crafted fusion rules.

Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging conditions, whereas real-world observations often contain degradations that differ significantly from such settings. Improving robustness for multi-view 3D reconstruction under degraded conditions therefore remains an important challenge. We present Geometry-Aware Representation Denoising (GARD), a novel framework that performs diffusion-based multi-view restoration directly in the feature space of a feed-forward 3D reconstruction model. This design exploits the geometry-aware feature representations of the 3D reconstructor to effectively recover accurate scene geometry. Furthermore, by employing an additional RGB image decoder, the refined representations can also be used to restore high-quality RGB images, thereby enabling the simultaneous recovery of 3D scene geometry and high-quality imagery. Comprehensive experiments on the Depth Anything 3 (DA3) benchmark demonstrate the effectiveness of the proposed GARD framework.

Open surface components prevail in real industrial 3D content and support rendering, physical simulation and geometric editing. Garments serve as a typical open surface type, with numerous existing generation methods leveraging sewing patterns to generate 2D panels and stitch them into 3D shapes. Such domain-specific designs lack scalability and cannot generalize to shoes and accessories. Common field-based 3D generators prioritize watertight meshes and tend to create flawed double-layer structures on open surfaces. Though Trellis2 adopts field-free representation, its open surface results still contain normal and topology errors. We present AnySurf, a unified framework generating open, closed and hybrid 3D surfaces with accurate face orientation. Built on directed-edge enhanced Flexible Dual Grid (FDG-D), our representation retains normal direction information via oriented grid edges. We also propose ROS-FT post-training and a lightweight DE-Adapter with merely 1% extra parameters, facilitating directed edge learning while preserving original generation performance. We further construct Outfit3D dataset containing industrial garments and closed accessories. Our work transforms garment modeling into a universal 3D generation task. Experimental results demonstrate superior mesh quality and better practicality for downstream applications.

While 3D generation is progressing rapidly, recent work has often focused on obtaining high-resolution assets, leaving user experience and deployability as afterthoughts. We present AssetGen, a 3D generator that focuses instead on these two aspects. Given one reference image, in 30 seconds it produces a high-quality mesh with baked normals, a color texture, and a controlled polygon budget suitable for real-time rendering, including mobile use cases. The AssetGen Flash variant further reduces latency to 14 seconds for interactive and agentic creation loops. Our model generates the object geometry with a coarse-to-refine VecSet framework, which implements mesh simplification, cleaning, and normal baking on the GPU, and a fast parallel UV unwrapping. It then generates textures in a multi-view fashion, followed by backprojection and 3D inpainting. Model distillation, kernel optimization, and pipeline parallelization are co-designed to accelerate the system end-to-end. We introduce numerous automated and blind human evaluations and demonstrate competitive visual quality against leading commercial solutions in 30 seconds and preview-quality results in less than 15 seconds. The final result is a system that supports AI-assisted, deployable 3D content creation in interactive workflows.

Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a central challenge in computer vision, with many open problems yet to be solved. Recent advances in feedforward 3D reconstruction have made significant strides in overcoming persistent failure cases of classical SfM methods, particularly in scenarios characterized by low texture, limited overlap, and symmetries. However, while feedforward approaches excel in these challenging conditions, they often face limitations regarding scalability, accuracy, or robustness, and typically fall short of classical methods in standard reconstruction settings. In this work, we systematically analyze these limitations and propose a new Structure-from-Motion pipeline by combining the respective strengths of classical and feedforward methods. Extensive experiments across multiple datasets show the benefits of our approach, achieving state-of-the-art results across a wide range of scenarios. We share our system as an open-source implementation at https://github.com/colmap/gluemap.

3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint optimization. To overcome this limitation, we propose to address these two tasks within a unified framework, which allows their mutual dependencies to be effectively exploited. Building on this idea, we propose MuNet, a mutualistic network for joint 3D human mesh recovery and 3D clothed human reconstruction from single images. First, we adopt 2-manifold graphs as a unified representation for all 3D models, enabling consistent modeling across 3D human mesh recovery and clothed human reconstruction. Second, we design an end-to-end graph convolutional network that progressively deforms an initial graph into a 3D human mesh and refines it into a detailed 3D clothed human model. Third, we introduce a mutualistic mechanism that allows reciprocal interaction between the two tasks {during training}, where 3D human mesh recovery provides guidance for 3D clothed human reconstruction, and reconstruction feedback refines the 3D human mesh recovery. We extensively evaluate MuNet on six benchmark datasets for 3D human mesh recovery and 3D clothed human reconstruction, including Human3.6M, 3DPW, MPI-INF-3DHP, THuman2.0, CAPE, and RenderPeople. Experimental results demonstrate that MuNet achieves state-of-the-art performance on both tasks across all datasets. The code of MuNet is released for research purposes at https://github.com/starVisionTeam/MuNet.

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique opportunity to model motion with fine temporal precision. However, the scarcity of temporally dense ground-truth annotations limits the effectiveness of supervised learning, while contrast maximization (CM) frameworks, focused on sharpening the Image of Warped Events (IWE), often neglect temporal continuity and structural coherence, leading to distorted trajectories under complex motion. To overcome these challenges, we propose a hybrid-supervised framework for continuous-time optical flow estimation, grounded in the principle of Spatio-temporal Structural Consistency (STSC). This paradigm jointly enforces local structural stability and trajectory continuity, ensuring physically coherent motion across time. To further enhance representation and robustness, we design a bidirectionally complementary multi-scale architecture and employ a curriculum-guided hybrid training strategy, enabling a smooth transition from supervised point constraints to self-supervised manifold regularization. Comprehensive experiments across multiple benchmarks show that our method achieves state-of-the-art performance in both continuous-time and standard optical flow estimation, demonstrating the effectiveness of the proposed learning paradigm.

Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weighted flow matching loss that preserves image structure across continuous enhancement strengths. ControlLight allows users to edit real-world degraded low-light images toward satisfactory enhancement results by flexibly controlling the strength while preserving visual consistency and realism. Extensive experiments show that ControlLight achieves state-of-the-art performance against existing low-light enhancement approaches while demonstrating strong continuous controllability and generalization to real-world scenarios.

Track materialization converts raw video into reusable object tracks that downstream queries can run against without rerunning tracking, but extracting those tracks efficiently and with high fidelity remains expensive. Prior systems reduce cost through temporal frame sampling, erasing the inter-frame motion that fine-grained tracking requires. In stationary video, however, large portions of each frame contain no objects of interest, and the remaining regions tolerate different sampling rates. We present Tetris, a track-extraction system that decomposes videos into a tile-based polyomino data model, enabling fine-grained spatiotemporal pruning that reduces detector calls with minimal fidelity loss. Tetris runs three operators upstream of the user-provided detector: a classifier identifies relevant tiles and groups them into polyominoes, an integer linear program (ILP) prunes redundant polyominoes under a user-specified accuracy constraint, and a packer assembles the survivors into canvases that minimize detector calls. Across 7 stationary-video datasets, Tetris stays within a 5% tracking accuracy loss of a full-frame, every-frame reference pipeline, whereas prior systems exceed this bound on 3 of the 7 datasets. At this 5% bound, Tetris achieves up to 17.4x higher throughput than prior systems and up to 68.8x higher than the reference pipeline. The project page is at https://tetris-db.github.io .

Inverse problems in partial differential equations (PDEs) involve estimating the physical parameters of a system from observed spatiotemporal solution fields. Neural networks are well-suited for PDE parameter estimation due to their capability to model function-to-function space transformations. While existing benchmarks of machine learning methods for PDEs primarily focus on the forward problem, there are no similar comprehensive studies and benchmark datasets on PDE inverse problems, i.e., mapping solution fields to underlying physical parameters. We fill this gap by introducing PDEInvBench, a comprehensive benchmark dataset consisting of numerical simulations for both time-dependent and time-independent PDEs across a wide range of physical behaviors and parameters. Our dataset includes evaluation splits that assess performance in both in-distribution and various out-of-distribution settings. Using our benchmark dataset, we comprehensively explore the design space of neural networks for PDE inverse problems along three key dimensions: (1) optimization procedures, analyzing the role of supervised, self-supervised, and test-time training objectives on performance, (2) problem representations, where we study the value of architectural choices with different inductive biases and various conditioning strategies, and (3) scaling, which we perform with respect to both model and data size. Our experiments reveal several practical insights: 1) neural networks perform best with a two-stage training procedure: initial supervision with PDE parameters followed by test-time fine-tuning using the PDE residual, 2) incorporating PDE derivatives as input features consistently improves accuracy, and 3) increasing the diversity of initial conditions in the training data yields greater performance gains than expanding the range of PDE parameters. We make our dataset and codebase publicly available.

Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score (DRS), which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy (DRP), an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone (Z-Image), DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step.

Lane detection stands as a crucial perception task in autonomous driving and advanced driver assistance systems. However, existing methods still degrade in complex real scenarios due to two major limitations. First, classification confidence only characterizes the categorical existence of lane priors and has no strong correlation with geometric quality. If threshold filtering and NMS are conducted merely based on this confidence, the model tends to retain lane priors with high confidence while eliminating those with lower confidence but superior geometric representation. Secondly, the regression modules in existing methods weaken correlations among sampling points, hindering fine-grained optimization of distant, high-curvature and complex-topology lanes and causing underfitting. To address these issues, we propose Geometric Fidelity and Spatial Refinement (GFSR), a framework consisting of LaneIoU-guided Confidence Calibration (LCC) and Adaptive Gated Location Refinement (AGLR). Specifically, LCC adopts LaneIoU as soft supervision to explicitly estimate the geometric fidelity of lane priors, which is further fused with classification confidence to construct the Collaborative Reliability Index (CRI). This index guides lane prior filtering, effectively retaining those with high classification confidence and favorable geometric quality. Meanwhile, cooperating with regression heads in each refinement stage, AGLR predicts sampling point lateral offsets and adopts a gating mechanism to adaptively regulate correction magnitude, strengthen inter-point correlations and boost model adaptability as well as robustness toward complex lane scenarios. Extensive experiments on CULane and CurveLanes demonstrate that our GFSR achieves state-of-the-art performance on CULane, with F1_50 and F1_75 scores of 81.46% and 65.01%, and reaches 87.35% F1_50 on CurveLanes.

Understanding and monitoring human behavior in metro stations play an important role in supporting suicide prevention efforts, where early identification of high-risk situations can enable timely intervention. This requires assessing suicide risk from a surveillance video by jointly reasoning about the behavior of each passenger, his/her spatial context, and temporal dynamics. However, this assessment using videos captured by surveillance cameras is challenging, as it demands accurate perception of human motion, understanding of platform geometry, and aggregation of heterogeneous behavioral cues over time. In this work, we formalize the task of Suicide Risk Assessment (SRA) in metro stations and introduce the first interpretable framework that addresses this challenge. Unlike approaches that focus on isolated subtasks or attempt to infer intent directly, our formulation assesses suicide risk from accumulated evidence by incorporating person tracking, activity recognition, semantic segmentation of the platform, and trajectory-driven risk heatmap modeling. By formalizing SRA as a distinct task and benchmarking a complete operational pipeline achieving 83.2% ROC-AUC on real surveillance data, this work highlights the complexity of suicide risk assessment and opens new directions for research on interpretable AI systems for social good.

Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain, especially for reasoning-intensive multimodal tasks where questions, answers, and feedback signals must be carefully designed. This motivates self-evolving learning, where a model improves itself through a dual-role closed loop: a questioner autonomously poses questions and a solver learns to solve them. However, we observe that current VLM self-evolving methods still face three major challenges: coarse-grained role alternation delays the interaction between question generation and solver adaptation; generated questions can progressively degrade in quality; and question types may collapse toward a narrow distribution. These issues limit the efficiency and reliability of self-evolution. Thus, we propose \textbf{RISE}, a reliable self-evolving framework for vision-language models. RISE is built on three complementary designs: fine-grained role alternation, which shortens the feedback loop between the questioner and the solver to improve efficiency; a quality supervisor, which improves question validity and pseudo-label reliability; and skill-aware dynamic balancing, which mitigates mode collapse and maintains broad skill coverage during evolution. Together, these components enable more reliable and effective self-evolution from unlabeled images. Experiments on two VLM backbones across seven benchmarks show that RISE consistently improves the base models, yielding broad and sustained gains. Our code is publicly available at https://github.com/AMAP-ML/RISE.

Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness uncontrolled. Recent robust DD methods improve robustness, yet they often suffer from a poor accuracy-robustness trade-off because they (i) treat all adversarially perturbed examples uniformly, despite robust risk being dominated by near-zero robust margins, and (ii) do not explicitly increase inter-class separation in the decision boundary where attacks concentrate. We present Contrastive Curriculum for Robust Dataset Distillation (C$^2$R), a framework that couples an attack-aware curriculum with a contrastive robustness objective. From a robust-margin perspective, we derive a perturbation score that approximates each sample's robust hinge, enabling a curriculum that prioritizes the smallest-margin adversaries that most directly drive robust error. In parallel, a class-balanced contrastive robustness loss enforces adversarial invariance while explicitly widening boundary separation across classes. Experiments on CIFAR-10/100, Tiny-ImageNet, and multiple ImageNet-1K subsets under six attacks show that C$^2$R achieves the best robust accuracy, outperforming prior robust DD by $2.8$% on average.

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A key reason is that most existing approaches treat next-frame prediction purely as a token generation problem, without considering the persistence of tokens across time. We introduce Identifiable Token Correspondence (ITC), a decoding step for token-based transformer world models that formulates next-frame prediction as a structured assignment problem with latent token correspondence variables: each next-frame token is explained either by copying a token from the previous frame or by generating a new one. ITC leaves the transformer architecture and training procedure unchanged and can be added on top of existing backbones. Our experiments show state-of-the-art performance on 4 challenging benchmarks. The proposed method achieves a return of 72.5% and a score of 35.6% on the Craftax-classic benchmark, significantly surpassing the previous best of 67.4% and 27.9%. We release our source code on https://github.com/snu-mllab/Identifiable-Token-Correspondence.

Pneumonia remains a leading global cause of morbidity and mortality, particularly in low-resource settings where access to imaging, laboratory testing, and specialist care is limited. Clinical assessment relies on heterogeneous evidence, including symptoms, respiratory patterns, spoken descriptions, and chest imaging, making frontline screening inherently multimodal. However, many existing computational approaches remain unimodal and focus primarily on radiographs. In this work, we present MultiSense-Pneumo, a multimodal research prototype for pneumonia-oriented screening and triage support that integrates structured symptom descriptors, cough audio, spoken language, and chest radiographs. The system combines deterministic symptom triage, LightGBM-based acoustic classification, domain-adversarial radiograph analysis using ResNet-18, transformer-based speech recognition, and an interpretable late-fusion operator. Each modality is transformed into a normalized concern signal and aggregated into a unified screening estimate. The fusion weights are hand-specified and are treated as heuristic, interpretable parameters rather than learned or clinically optimized values. MultiSense-Pneumo is implemented with offline execution in mind on standard laptop-class hardware, but it is not presented as a deployment-validated or clinically validated diagnostic system. Experimental results demonstrate strong component-level performance of the radiograph pathway under synthetic domain shifts, while also highlighting important limitations, especially reduced abnormal-class recall for cough acoustics and the absence of paired end-to-end multimodal patient evaluation. MultiSense-Pneumo is therefore intended as a framework and component-level prototype for screening and triage research.

Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce \textit{VT-Bench}, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models (VLMs), and tool-augmented methods, highlighting substantial challenges of visual-tabular learning. We believe VT-Bench will stimulate the community to build more powerful multi-modal vision-tabular foundation models. Benchmark: https://github.com/Ziyi-Jia990/VT-Bench

Optimal Transport (OT) offers a powerful framework for finding correspondences between distributions and addressing matching and alignment problems in various areas of computer vision, including shape analysis, image generation, and multimodal tasks. The computation cost of OT, however, hinders its scalability. Slice-based transport plans have recently shown promise for reducing the computational cost by leveraging the closed-form solutions of 1D OT problems. These methods optimize a one-dimensional projection (slice) to obtain a conditional transport plan that minimizes the transport cost in the ambient space. While efficient, these methods leave open the question of whether learned optimal slicers can transfer to new distribution pairs under distributional shift. Understanding this transferability is crucial in settings with evolving data or repeated OT computations across closely related distributions. In this paper, we study the min-Sliced Transport Plan (min-STP) framework and investigate the transferability of optimized slicers: can a slicer trained on one distribution pair yield effective transport plans for new, unseen pairs? Theoretically, we show that optimized slicers remain close under slight perturbations of the data distributions, enabling efficient transfer across related tasks. To further improve scalability, we introduce a minibatch formulation of min-STP and provide statistical guarantees on its accuracy. Empirically, we demonstrate that the transferable min-STP achieves strong one-shot matching performance and facilitates amortized training for point cloud alignment and flow-based generative modeling.

Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query-key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the rest of the model. Across a suite of multimodal benchmarks, RAVE improves over standard attention by an average of 3 points, with the largest gains on perception-intensive tasks -- including multilingual OCR, chart understanding, document VQA, and scene text VQA -- where accurate visual grounding is critical.

The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant challenges for direct continuous supervised fine-tuning. For example, applying the commonly used fine-tuning technique would compromise their inherent few-step inference capability. To address this, we propose D-OPSD, a novel training paradigm for step-distilled diffusion models that enables on-policy learning during supervised fine-tuning. We first find that the modern diffusion models, where the LLM/VLM serves as the encoder, can inherit its encoder's in-context capabilities. This enables us to formulate the training as an on-policy self-distillation process. Specifically, during training, we make the model act as both the teacher and the student with different contexts, where the student is conditioned only on the text feature, while the teacher is conditioned on the multimodal feature of both the text prompt and the target image. Training minimizes the two predicted distributions over the student's own roll-outs. By optimizing on the model's own trajectory and under its own supervision, D-OPSD enables the model to learn new concepts, styles, etc., without sacrificing the original few-step capacity.

Vision-language pretraining has driven much of the recent progress in medical image representation learning, but this paradigm is constrained by the availability of paired image-text data and by the reporting bias of clinical narratives. We ask whether competitive radiology encoders can be learned without any language supervision. We introduce RadJEPA, a self-supervised framework built on a Joint Embedding Predictive Architecture and pretrained on approximately 840K unlabeled chest X-ray images. The model learns to predict latent representations of masked target regions from a visible context region, an objective that differs from both image-text contrastive pretraining and DINO-style self-distillation by explicitly modelling conditional structure in representation space. We evaluate RadJEPA primarily on radiology report generation with a frozen Vicuna-7B decoder, and additionally substitute its encoder into four widely used vision-language backbones (MedLLaVA, Qwen-2.5, BLIP-2, and Phi-4). For completeness we also report disease classification and semantic segmentation results. Across two datasets and four metrics, RadJEPA matches or exceeds the strongest image-only and vision-language baselines while using a ViT-B/14 backbone at 224 x 224 resolution.

Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited availability of egocentric training data and its inherent partial observability of humans' physical actions. In contrast, exocentric video is abundant and reveals body poses well, but lacks direct alignment with an agent's action space -- and is not egocentric. We propose a method to bridge this gap by extracting structured body pose from exocentric video as a representation of action and transforming the exocentric video to egocentric video, informed by a human kinematics prior. This process unlocks the integration of in-the-wild exocentric data for egocentric world model training. We show that training whole-body action-conditioned egocentric world models with our converted data significantly improves both prediction quality and downstream planning performance, where we infer the sequence of body poses needed to achieve a visual goal state. Our approach paves the way to enlist arbitrary in-the-wild videos for building powerful egocentric world models, furthering applications in robot planning and augmented-reality guidance.

Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs. To distill such capabilities into compact think-answer VLMs, a primary objective is to improve the student's ability to utilize visual evidence throughout its reasoning trace, as long think-answer traces suffer from visual forgetting issues. To this end, we introduce a novel think-answer distillation framework that encourages the student to anchor its thinking on visual information by masking the student's salient reasoning prefixes. To compensate for such masked textual cues, the student is encouraged to rely more on visual evidence as an alternative source of information during distillation. Our masking strategies include: 1) token-wise salient reasoning-prefix masking, which masks high-influence reasoning prefixes selectively for each next-token prediction, and 2) self-paced masking budget scheduling, which gradually increases the masking scale according to distillation difficulty, measured by the discrepancy between teacher--student distributions. In the distillation phase, the student is guided by our salient reasoning-prefix mask, which blocks both future tokens and salient reasoning cues, in place of the standard causal mask used for auto-regressive language modeling. Experimental results show that our approach outperforms recent open-source VLMs, VLM distillation, and self-distillation methods on multimodal reasoning benchmarks, while further analyzes confirm enhanced visual utilization along the student thinking process.

In recent years, computer vision has witnessed remarkable progress, fueled by the development of innovative architectures such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), diffusion-based architectures, Vision Transformers (ViTs), and, more recently, Vision-Language Models (VLMs). This progress has undeniably contributed to creating increasingly realistic and diverse visual content. However, such advancements in image generation also raise concerns about potential misuse in areas such as misinformation, identity theft, and threats to privacy and security. In parallel, Mamba-based architectures have emerged as versatile tools for a range of image analysis tasks, including classification, segmentation, medical imaging, object detection, and image restoration, in this rapidly evolving field. However, their potential for identifying AI-generated images remains relatively unexplored compared to established techniques. This study provides a systematic evaluation and comparative analysis of Vision Mamba models for AI-generated image detection. We benchmark multiple Vision Mamba variants against representative CNNs, ViTs, and VLM-based detectors across diverse datasets and synthetic image sources, focusing on key metrics such as accuracy, efficiency, and generalizability across diverse image types and generative models. Through this comprehensive analysis, we aim to elucidate Vision Mamba's strengths and limitations relative to established methodologies in terms of applicability, accuracy, and efficiency in detecting AI-generated images. Overall, our findings highlight both the promise and current limitations of Vision Mamba as a component in systems designed to distinguish authentic from AI-generated visual content. This research is crucial for enhancing detection in an age where distinguishing between real and AI-generated content is a major challenge.

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods fall into two paradigms, each with inherent limitations: decoupled encoders suffer from modality gaps when processing instructions and visual content independently, while unified vision-language encoders lose fine-grained spatial details by relying solely on final-layer representations. We observe that VLM layers encode complementary information hierarchically -- early layers capture localized spatial details essential for precise editing, while deeper layers encode global semantics for instruction comprehension. Building on this insight, we present MiVE (Multiscale Vision-language features for reference-guided video Editing), a framework that repurposes VLMs as multiscale feature extractors. MiVE extracts hierarchical features from Qwen3-VL and integrates them into a unified self-attention Diffusion Transformer, eliminating the modality mismatch inherent in cross-attention designs. Experiments demonstrate that MiVE achieves state-of-the-art performance by ranking highest in human preference, outperforming both academic methods and commercial systems.

Synapses are densely packed submicron structures that dynamically reorganize during learning and memory formation. Longitudinal \textit{in vivo} imaging of fluorescently tagged synaptic receptors offers a promising opportunity to study large-scale synaptic dynamics and how these processes are disrupted in neurological disease. However, in vivo imaging with 2-photon microscopy uses low laser power and therefore suffers from low signal-to-noise ratio (SNR) and high shot noise, nonlinear tissue motion between days, nonstationary fluctuations in synaptic fluorescence, and significant blur induced by the microscope point spread function (PSF). Together, these factors make it challenging to detect and track synapses, especially in regions with high synaptic density. This paper presents a novel template-based framework for modeling synapses as varying luminance point sources that move under a nonlinear tissue deformation. Taking a unified Bayesian approach, we apply this model to microscopy data by deriving a posterior that incorporates a diffeomorphic mapping for domain warping, a Gaussian point spread function for the imaging process, and a Poisson observation model for raw photon counts. The Bayesian solution simultaneously: (1) Constructs a probabilistic template of synapse locations, (2) denoises and deconvolves the image data, (3) infers fluorescence intensities, (4) performs diffeomorphic image registration to correct for tissue motion, and (5) provides confidence regions for these parameter estimates. We demonstrate the framework on both a 2D+t simulated dataset and a 3D+t longitudinal \textit{in vivo} microscopy dataset of fluorescent synapses imaged in a mouse over two weeks.

Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible relation phrases beyond a fixed predicate set. Existing methods usually treat annotated triplets as positives and all unannotated object-pair relations as negatives. However, scene graph annotations are inherently incomplete: many valid relations are missing, and the same interaction can be described at different granularities, e.g., \textit{on}, \textit{standing on}, \textit{resting on}, and \textit{supported by}. This issue becomes more severe in open-vocabulary SGG due to the much larger relation space. We propose \textbf{ReLIC-SGG}, a relation-incompleteness-aware framework that treats unannotated relations as latent variables rather than definite negatives. ReLIC-SGG builds a semantic relation lattice to model similarity, entailment, and contradiction among open-vocabulary predicates, and uses it to infer missing positive relations from visual-language compatibility, graph context, and semantic consistency. A positive-unlabeled graph learning objective further reduces false-negative supervision, while lattice-guided decoding produces compact and semantically consistent scene graphs. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that ReLIC-SGG improves rare and unseen predicate recognition and better recovers missing relations.

Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses signals like spatial structure, exact appearance, and glyph shape. We propose \textbf{\emph{visual-to-visual} (V2V)} generation, in which the user conditions a generative model with a visual specification page rather than a text prompt. The page is not an edit target, but a visual document that specifies the desired output. We introduce \textbf{V2V-Zero}, a training-free framework that exposes this interface in existing vision-language model (VLM) conditioned generators by replacing text-only conditioning with final-layer hidden states extracted from visual pages, exploiting the fact that the frozen VLM already maps both text and images into the generator's conditioning space. On GenEval, V2V-Zero reaches 0.85 with a frozen Qwen-Image backbone, closely matching its optimized text-to-image performance without fine-tuning. To evaluate the broader V2V space, we introduce \textbf{Simple-V2V Bench}, spanning seven visual-conditioning tasks and seven models, including GPT Image 2, Nano Banana 2, Seedream 5.0 Lite, open-weight baselines, and a video extension. V2V-Zero scores 32.7/100, outperforming evaluated open-weight image baselines and revealing a clear capability hierarchy: attribute binding is strong, content generation is unreliable, and structural control remains hard even for commercial systems. A HunyuanVideo-1.5 extension scores 20.2/100, showing the interface transfers beyond images. Mechanistic analysis shows the default reasoning path is primarily visually routed, with 95.0\% of conditioning-token attention mass on visual-page hidden states.

Structural MRI-to-amyloid PET synthesis has been proposed as a non-invasive alternative for amyloid assessment in Alzheimer's disease (AD). However, reported performance of identical models varies widely across studies, and increasingly complex architectures have not led to consistent gains. This inconsistency is thought to be caused by a fundamental biological ambiguity: MRI captures neurodegeneration, while PET measures amyloid pathology - two processes that are often temporally decoupled in AD. As a result, similar MRI patterns may correspond to different amyloid states, creating ambiguous one-to-many mappings. MRI-to-amyloid PET synthesis may therefore be intrinsically ill-posed; however, this idea has yet to be tested scientifically. The aim of this work is to test this hypothesis through two controlled experiments. We first control the training distribution by stratifying paired MRI-PET data by amyloid and neurodegeneration status. Using two standard synthesis models under a controlled design, we show that biologically unambiguous mappings are learnable in isolation, but performance collapses when data ambiguity is introduced. This demonstrates that ambiguity in the data distribution, rather than architectural capacity, constrains performance. Second, we show that introducing orthogonal biological information in the form of plasma biomarkers resolves this ambiguity. When multimodal inputs are incorporated, performance improves and stability is restored. Together, these findings suggest that limited and inconsistent performance in MRI-to-amyloid PET synthesis is explained by intrinsic biological ambiguity, and that stable, meaningful progress requires multimodal integration rather than architectural complexity.

Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible and fine-grained relation phrases beyond a fixed predicate vocabulary. While recent vision-language models greatly expand the semantic coverage of SGG, they also introduce a critical reliability issue: predicted relations may be driven by language priors or object co-occurrence rather than grounded visual evidence. In this paper, we propose an evidence-rounded open-vocabulary SGG framework based on counterfactual relation verification. Instead of directly accepting plausible relation proposals, our method verifies whether each candidate relation is supported by relation-pecific visual, geometric, and contextual evidence. Specifically, we first generate open-vocabulary relation candidates with a vision-language proposer, then decompose predicate phrases into soft evidence bases such as support, contact, containment, depth and state. A relation-conditioned evidence encoder extracts predicate-relevant cues, while a counterfactual verifier tests whether the relation score decreases when necessary vidence is removed and remains stable under irrelevant perturbations. We further introduce contradiction-aware predicate learning and graph-level preference optimization to improve fine-grained discrimination and global graph consistency. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that our method consistently improves standard recall-based metrics, unseen predicate generalization, and counterfactual grounding quality. These results demonstrate that moving from relation generation to relation verification leads to more reliable, interpretable, and evidence-grounded scene graphs.

Feature-map knowledge distillation (KD) transfers internal representations well between comparably sized Vision Transformers (ViTs), but it often fails in compression. We revisit this failure and uncover a paradox. Sample-wise SVD shows that each image is highly compressible, which seems to suggest that a narrow student with a linear projector should match the teacher "in principle". However, a dataset-level view contradicts this intuition: PCA shows that the teacher is a union of low-rank subspaces with significant subspace rotation across inputs. We further introduce token-level Spectral Energy Patterns (SEP) and find an architecture-invariant encoding law: tokens spread energy broadly across channel modes even when they live in low-rank subspace, creating a bandwidth mismatch. We refer to this combined phenomenon as an encoding mismatch. We propose two minimal remedies, Lift or WideLast: (i) Lift retains a lightweight lifting projector at inference to provide wider channel, or (ii) WideLast widens only the student's last block, enabling an input-dependent expansion. On ImageNet-1K, these fixes revive feature KD for ViT compression, improving DeiT-Tiny distilled from CaiT-S24 from 74.86% to 77.53%/78.23% top-1 accuracy, and they also strengthen students trained without distillation. Our analyses clarify when and why feature-map KD fails and then how to fix it. Code and raw data are provided in https://github.com/thy960112/From-Per-Image-Low-Rank-to-Encoding-Mismatch.

In the Industrial Internet of Things (IIoT), enabling intelligent, real-time Printed Circuit Board (PCB) defect inspection is critical for ensuring product reliability. However, existing IIoT-based visual inspection systems face two compounding challenges: scarce and imbalanced defect samples that limit model training, and insufficient feature representation under complex circuit backgrounds. Existing generation methods rely on single-modality conditions with coarse structural control, while detection methods improve architectures without addressing the data bottleneck. To resolve both challenges jointly, we propose a generation-assisted PCB defect inspection framework that integrates controlled defect synthesis with task-specific defect detection within an IIoT-enabled pipeline. On the generation side, a Multi-modal Condition Generator extracts complementary edge, depth, and text conditions in parallel. A ScaleEncoder then embeds these conditions into the diffusion U-Net at four resolutions, and a Condition Modulation applies FiLM-style spatially-adaptive modulation at each scale, enabling structurally aligned and defect-aware sample synthesis to augment the scarce IIoT dataset. On the detection side, an Inverted Residual Shift Attention couples self-attention with shift-wise convolution to jointly capture global context and local texture, and a Cross-level Complementary Fusion Block generates pixel-level gates for selective cross-level feature fusion. The synthesized samples directly enrich the detection training set, so that improvements in generation compound with improvements in detection. Extensive experiments on DsPCBSD+ demonstrate that UniPCB achieves mAP@0.5 of 98.0% and mAP@0.5:0.95 of 61.8% on defect detection, surpassing all compared methods, while the generation branch attains an FID of 129.61 and SSIM of 0.619, outperforming existing conditional generation approaches.

Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only for Gaussian initialization or depth supervision, while the rich scene information contained in point clouds, such as reflectance, and the complementarity between LiDAR and RGB have not been fully exploited, leading to degradation in challenging self-driving scenes, such as those with high ego-motion and complex lighting. To address these issues, we propose a robust and efficient LiDAR-reflectance-guided Salient Gaussian Splatting method (LR-SGS) for self-driving scenes, which introduces a structure-aware Salient Gaussian representation, initialized from geometric and reflectance feature points extracted from LiDAR and refined through a salient transform and improved density control to capture edge and planar structures. Furthermore, we calibrate LiDAR intensity into reflectance and attach it to each Gaussian as a lighting-invariant material channel, jointly aligned with RGB to enforce boundary consistency. Extensive experiments on the Waymo Open Dataset demonstrate that LR-SGS achieves superior reconstruction performance with fewer Gaussians and shorter training time. In particular, on Complex Lighting scenes, our method surpasses OmniRe by 1.18 dB PSNR.

We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs' ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.

Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high computational costs and limit scalability. We propose World-R1, a framework that aligns video generation with 3D constraints through reinforcement learning. To facilitate this alignment, we introduce a specialized pure text dataset tailored for world simulation. Utilizing Flow-GRPO, we optimize the model using feedback from pre-trained 3D foundation models and vision-language models to enforce structural coherence without altering the underlying architecture. We further employ a periodic decoupled training strategy to balance rigid geometric consistency with dynamic scene fluidity. Extensive evaluations reveal that our approach significantly enhances 3D consistency while preserving the original visual quality of the foundation model, effectively bridging the gap between video generation and scalable world simulation.

Adapting CLIP for videos has gained popularity due to its semantic and rich representation. While CLIP is a good starting point, it typically undergoes post-pretraining (contrastive finetuning) on large video narration or caption datasets (e.g. HowTo100M, WebVid2.5M). However, such narrations or captions often lack comprehensive information needed to represent a video holistically. As the learning signal from text is sparse, the visual learning is inefficient and adaptation requires millions of samples to post-pretrain. In this work, we ask: is it possible to efficiently adapt CLIP for general and holistic video understanding? We use videos labeled with structured and dense Semantic Role Labels (SRLs) that capture actions, people or objects, their attributes, adverbs (manner), and location in a structured format representing the entire video in a holistic way. We generate rule-based captions from SRLs and demonstrate that simple contrastive finetuning on a mere 23k video-caption pairs is adequate to learn powerful, transferable representations applicable across a diverse range of video understanding tasks that require varying levels of perceptual granularity. Our adapted CLIP model, SRL-CLIP, exhibits comparable or superior performance on zero-shot text-to-video retrieval compared to state-of-the-art models that possess 4-8x more parameters and are post-pretrained on up to 6000x more data. SRL-CLIP surpasses CLIP on multiple video benchmarks, underscoring the efficient learning and improved representations.

Accurate transcription of handwritten mathematics is crucial for educational AI systems, yet current benchmarks fail to evaluate this capability properly. Most prior studies focus on single-line expressions and rely on lexical metrics such as BLEU, which fail to assess the semantic reasoning across multi-line student solutions. In this paper, we present the first systematic study of multi-line handwritten math Optical Character Recognition (OCR), revealing a critical failure mode of Vision-Language Models (VLMs): over-correction. Instead of faithfully transcribing a student's work, these models often "fix" errors, thereby hiding the very mistakes an educational assessment aims to detect. To address this, we propose PINK (Penalized INK-based score), a semantic evaluation metric that leverages a Large Language Model (LLM) for rubric-based grading and explicitly penalizes over-correction. Our comprehensive evaluation of 15 state-of-the-art VLMs on the FERMAT dataset reveals substantial ranking reversals compared to BLEU: models like GPT-4o are heavily penalized for aggressive over-correction, whereas Gemini 2.5 Flash emerges as the most faithful transcriber. Furthermore, human expert studies show that PINK aligns significantly better with human judgment (55.0% preference over BLEU's 39.5%), providing a more reliable evaluation framework for handwritten math OCR in educational settings.

Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, yet such data is scarce. Real-world capture is costly and limited to controlled settings, while existing synthetic datasets rely on simple geometric heuristics, ignoring rich scene context. In contrast, 2D foundation models trained at internet scale have acquired commonsense knowledge of human-environment interactions. To transfer this knowledge to 3D, we introduce InHabit, an automatic and scalable data generator for populating 3D scenes with interacting humans. InHabit follows a render-generate-lift principle: given a rendered 3D scene, a vision-language model proposes contextually meaningful actions, an image-editing model inserts a human, and an optimization procedure lifts the edited result into physically plausible SMPL-X bodies aligned with the scene geometry. Applied to Habitat-Matterport3D, InHabit produces InHabitants, the first large-scale photorealistic 3D human-scene interaction dataset, with 78K samples across $\sim$800 building-scale scenes with complete 3D geometry, SMPL-X bodies, and images. Augmenting standard training data with InHabitants improves RGB-based 3D human-scene reconstruction and contact estimation, and in a perceptual user study our data is preferred in 78% of cases over prior art.

At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely constructed through manual engineering: developers must carefully design workflows, write prompts for each step, and repeatedly revise the logic as requirements evolve -- making development costly, time-consuming, and error-prone. To study whether large language models can automate this multi-round interaction process, we introduce Chat2Workflow, a benchmark for generating executable visual workflows directly from natural language, and propose a robust agentic baseline to improve performance. The benchmark is built from a large collection of real-world business workflows, with each instance designed so that the generated workflow can be transformed and directly deployed to practical workflow platforms such as Dify and Coze. Experimental results show that while state-of-the-art language models can often capture high-level intent, they struggle to generate correct, stable, and executable workflows, especially given complex and evolving requirements. Although our agentic baseline yields up to 6.05% resolve rate gains, the remaining real-world gap positions Chat2Workflow as a foundation for advancing industrial-grade automation. Code is available at https://github.com/zjunlp/Chat2Workflow.

Visual prompted object detection enables interactive and flexible definition of target categories, thereby facilitating open-vocabulary detection. Since visual prompts are derived directly from image features, they often outperform text prompts in recognizing rare categories. Nevertheless, research on visual prompted detection has been largely overlooked, and it is typically treated as a byproduct of training text prompted detectors, which hinders its development. To fully unlock the potential of visual-prompted detection, we investigate the reasons why its performance is suboptimal and reveal that the underlying issue lies in the absence of global discriminability in visual prompts. Motivated by these observations, we propose DETR-ViP, a robust object detection framework that yields class-distinguishable visual prompts. On top of basic image-text contrastive learning, DETR-ViP incorporates global prompt integration and visual-textual prompt relation distillation to learn more discriminative prompt representations. In addition, DETR-ViP employs a selective fusion strategy that ensures stable and robust detection. Extensive experiments on COCO, LVIS, ODinW, and Roboflow100 demonstrate that DETR-ViP achieves substantially higher performance in visual prompt detection compared to other state-of-the-art counterparts. A series of ablation studies and analyses further validate the effectiveness of the proposed improvements and shed light on the underlying reasons for the enhanced detection capability of visual prompts.

With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced significantly. However, despite the inherent reasoning capabilities of unified MLLMs for self-reflection and self-refinement, their use in text-to-image generation remains largely underexplored. Meanwhile, existing multimodal reasoning-based image generation methods mostly rely on prompt augmentation or holistic image-text alignment judgments, without fine-grained reflection and refinement of detailed prompt attributes, leading to limited fine-grained control. To address this limitation, we propose FiRe, a Fine-grained Multimodal Reasoning method for enhanced image generation by MLLM. In specific, FiRe performs a fine-grained multi-step reasoning by first decomposing the prompt into key visual requirements and then self-judging their satisfaction in the generated image, followed by localized refinement according to self-generated precise feedback. In addition, to further strengthen the MLLM's multimodal reasoning ability, we introduce FiRe-GRPO, a reinforcement learning method tailored to FiRe. Since standard Group Relative Policy Optimization (GRPO) suffers from sparse, outcome-based rewards in multi-step reasoning, we formulate our reasoning process as a step-level decision-making problem, design step-specific rewards, and compute step-level advantages for granular credit assignment within GRPO. Extensive experiments demonstrate that FiRe consistently outperforms competitive text-to-image baselines, including existing reasoning-based methods, with particularly substantial gains on compositional text-to-image benchmarks.

Bird's-eye-view (BEV) representations are the dominant paradigm for 3D perception in autonomous driving, providing a unified spatial canvas where detection and segmentation features are geometrically registered to the same physical coordinate system. However, existing radar-camera fusion methods treat these tasks in isolation, missing the opportunity for cross-task feature sharing: object-level geometric cues from detection can sharpen segmentation, while dense road-layout context from segmentation can anchor detection. We propose \textbf{CTAB} (Cross-Task Attention Bridge), a bidirectional module that exchanges features between detection and segmentation branches via multi-scale deformable attention in shared BEV space. CTAB is integrated into a multi-task framework with an Instance Normalization-based segmentation decoder and learnable BEV upsampling to provide a more detailed BEV representation. On nuScenes, CTAB improves segmentation on 7 classes over the joint multi-task baseline at essentially neutral detection. On a 4-class subset (drivable area, pedestrian crossing, walkway, vehicle), our joint multi-task model achieves 51.0 mIoU-4 while simultaneously providing competitive 3D detection.

Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer from slow inference due to sequential decoding, and non-autoregressive unified models suffer from weak generalization due to limited pretrained backbones. We introduce the second-generation Meissonic: Muddit, a unified discrete diffusion transformer that enables fast and parallel generation across both text and image modalities. Unlike prior unified diffusion models trained from scratch, Muddit integrates strong visual priors from a pretrained text-to-image backbone with a lightweight text decoder, enabling flexible and high-quality multimodal generation under a unified architecture. Empirical results show that Muddit achieves competitive or superior performance compared to significantly larger autoregressive models in both quality and efficiency. The work highlights the potential of purely discrete diffusion, when equipped with strong visual priors, as a scalable and effective backbone for unified generation.

AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free, treat degradation robustness as a byproduct of data augmentation rather than an explicit training objective. In this work, we propose Degradation-Consistent Paired Training (DCPT), a simple yet effective training strategy that explicitly enforces robustness through paired consistency constraints. For each training image, we construct a clean view and a degraded view, then impose two constraints: a feature consistency loss that minimizes the cosine distance between clean and degraded representations, and a prediction consistency loss based on symmetric KL divergence that aligns output distributions across views. DCPT adds zero additional parameters and zero inference overhead. Experiments on the Synthbuster benchmark (9 generators, 8 degradation conditions) demonstrate that DCPT improves the degraded-condition average accuracy by 9.1 percentage points compared to an identical baseline without paired training, while sacrificing only 0.9% clean accuracy. The improvement is most pronounced under JPEG compression (+15.7% to +17.9%). Ablation further reveals that adding architectural components leads to overfitting on limited training data, confirming that training objective improvement is more effective than architectural augmentation for degradation robustness.

With the emergence of 3D foundation models, there is growing interest in fine-tuning them for downstream tasks, where LoRA is the dominant fine-tuning paradigm. As 3D datasets exhibit distinct variations in texture, geometry, camera motion, and lighting, there are interesting fundamental questions: 1) Are there LoRA subspaces associated with each type of variation? 2) Are these subspaces disentangled (i.e., orthogonal to each other)? 3) How do we compute them effectively? This paper provides answers to all these questions. We introduce a robust approach that generates synthetic datasets with controlled variations, fine-tunes a LoRA adapter on each dataset, and extracts a LoRA sub-space associated with each type of variation. We show that these subspaces are approximately disentangled. Integrating them leads to a reduced LoRA subspace that enables efficient LoRA fine-tuning with improved prediction accuracy for downstream tasks. In particular, we show that such a reduced LoRA subspace, despite being derived entirely from synthetic data, generalizes to real datasets. An ablation study validates the effectiveness of the choices in our approach.

Content moderation systems classify images as safe or unsafe but lack spatial grounding and interpretability: they cannot explain what sensitive behavior was detected, who is involved, or where it occurs. We introduce the Sensitive Benchmark (SenBen), the first large-scale scene graph benchmark for sensitive content, comprising 13,999 frames from 157 movies annotated with Visual Genome-style scene graphs (25 object classes, 28 attributes including affective states such as pain, fear, aggression, and distress, 14 predicates) and 16 sensitivity tags across 5 categories. We distill a frontier VLM into a compact 241M student model using a multi-task recipe that addresses vocabulary imbalance in autoregressive scene graph generation through suffix-based object identity, Vocabulary-Aware Recall (VAR) Loss, and a decoupled Query2Label tag head with asymmetric loss, yielding a +6.4 percentage point improvement in SenBen Recall over standard cross-entropy training. On grounded scene graph metrics, our student model outperforms all evaluated VLMs except Gemini models and all commercial safety APIs, while achieving the highest object detection and captioning scores across all models, at $7.6\times$ faster inference and $16\times$ less GPU memory.

Every year, millions of patients pass through emergency departments and intensive care units, where clinicians must make high-stakes decisions under time pressure and uncertainty. Machine learning could support prediction of deterioration, triage, and rare critical outcomes, but clinical data are often severely imbalanced, biasing models toward majority classes and reducing predictive performance. Developing robust and efficient models for imbalanced clinical tabular data therefore remains an important challenge. We evaluated six model families on imbalanced tabular data from the MIMIC-IV-ED and eICU databases: Decision Tree, Random Forest, XGBoost, TabNet, TabICL, and TabPFN v2.6. Trainable models were optimized using Bayesian hyperparameter tuning, while foundation models were evaluated in their pretrained inference regime without task-specific reweighting. Models were assessed using Macro F1-score, robustness to increasing imbalance, and computational scalability across seven clinical prediction tasks. Results differed across datasets. On MIMIC-IV-ED, TabPFN v2.6 and TabICL achieved the strongest average Macro F1 ranks, with XGBoost remaining competitive. On eICU, XGBoost consistently performed best, followed by other tree-based methods, while foundation models achieved intermediate performance. Across both datasets, TabNet showed the largest degradation under increasing imbalance and the highest computational cost. Training-time analysis showed that tree-based methods scaled most favorably with dataset size, while foundation models offered low per-task adaptation cost. These findings suggest that no single model family dominates across all clinical settings. However, tabular foundation models are narrowing the performance gap with strong classical baselines while offering a distinct efficiency-performance trade-off that may benefit resource-constrained clinical environments.

Weakly supervised object detection (WSOD) has attracted significant attention in recent years, as it does not require box-level annotations. State-of-the-art methods generally adopt a multi-module network, which employs WSDDN as the multiple instance detection network module and uses multiple instance refinement modules to refine performance. However, these approaches suffer from three key limitations. First, existing methods tend to generate pseudo GT boxes that either focus only on discriminative parts, failing to capture the whole object, or cover the entire object but fail to distinguish between adjacent intra-class instances. Second, the foundational WSDDN architecture lacks a crucial background class representation for each proposal and exhibits a large semantic gap between its branches. Third, prior methods discard ignored proposals during optimization, leading to slow convergence. To address these challenges, we propose the Dual-thresholded heAtmap-guided proposal clustering and Negative Certainty supervision with Enhanced base network (DANCE) method for WSOD. Specifically, we first devise a heatmap-guided proposal selector (HGPS) algorithm, which utilizes dual thresholds on heatmaps to pre-select proposals, enabling pseudo GT boxes to both capture the full object extent and distinguish between adjacent intra-class instances. We then construct a weakly supervised basic detection network (WSBDN), which augments each proposal with a background class representation and uses heatmaps for pre-supervision to bridge the semantic gap between matrices. At last, we introduce a negative certainty supervision (NCS) loss on ignored proposals to accelerate convergence. Extensive experiments on the challenging PASCAL VOC and MS COCO datasets demonstrate the effectiveness and superiority of our method. Our code is publicly available at https://github.com/gyl2565309278/DANCE.

3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering, greatly advancing VR/AR applications. Fisheye cameras, with their wider field of view (FOV), promise high-quality reconstructions from fewer inputs and have recently attracted much attention. However, since 3DGS relies on rasterization, most subsequent works involving fisheye camera inputs first undistort images before training, which introduces two problems: 1) Black borders at image edges cause information loss and negate the fisheye's large FOV advantage; 2) Undistortion's stretch-and-interpolate resampling spreads each pixel's value over a larger area, diluting detail density -- causes 3DGS overfitting these low-frequency zones, producing blur and floating artifacts. In this work, we integrate fisheye camera model into the original 3DGS framework, enabling native fisheye image input for training without preprocessing. Despite correct modeling, we observed that the reconstructed scenes still exhibit floaters at image edges: Distortion increases toward the periphery, and 3DGS's original per-iteration random-selecting-view optimization ignores the cross-view correlations of a Gaussian, leading to extreme shapes (e.g., oversized or elongated) that degrade reconstruction quality. To address this, we introduce a feature-overlap-driven cross-view joint optimization strategy that establishes consistent geometric and photometric constraints across views-a technique equally applicable to existing pinhole-camera-based pipelines. Our DirectFisheye-GS matches or surpasses state-of-the-art performance on public datasets. Project Page: https://yzxqh.github.io/DirectFisheye-GS/ .

Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. However, when used as evaluators in reinforcement learning (RL), today's strongest models often fail under partial observability and distribution shift, enabling policies to exploit perceptual errors rather than solve the task. We introduce SOLE-R1 (Self-Observing LEarner), a video-language reasoning model explicitly designed to serve as the sole reward signal for online RL. Given only raw video observations and a natural-language goal, SOLE-R1 performs per-timestep spatiotemporal chain-of-thought (CoT) reasoning and produces dense estimates of task progress that can be used directly as rewards. To train SOLE-R1, we develop a large-scale video trajectory and reasoning synthesis pipeline that generates temporally grounded CoT traces aligned with continuous progress supervision. This data is combined with foundational spatial and multi-frame temporal reasoning, and used to train the model with a hybrid framework that couples supervised fine-tuning with RL from verifiable rewards. Across four different simulation environments and a real-robot setting, SOLE-R1 enables zero-shot online RL from random initialization: robots learn previously unseen manipulation tasks without ground-truth rewards, success indicators, demonstrations, or task-specific tuning. SOLE-R1 succeeds on 24 unseen tasks and substantially outperforms strong vision-language rewarders, including Robometer, RoboReward, ReWiND, GPT-5, and Gemini-3-Pro, while exhibiting markedly greater robustness to reward hacking. We release all models, data, code, and demos at the anonymous page: https://philip-mit.github.io/sole-r1/

Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overlooked optimization issue in multi-layer feature fusion. Skip pathways introduce direct back-propagation paths from high-level semantic objectives to early visual layers. This mechanism overwrites low-level signals and destabilizes training. To mitigate this gradient interference, we propose Detached Skip-Links, a minimal modification that reuses shallow features in the forward pass while stopping gradients through the skip branch during joint training. This asymmetric design reduces gradient interference, improving stability and convergence without adding learnable parameters. To diagnose whether fine-grained information is preserved and usable by an LLM, we introduce $R$-Probe, which measures pixel-level reconstructability of projected visual tokens using a shallow decoder initialized from the first quarter of the LLM layers. Across multiple ViT backbones and multimodal benchmarks, and at scales up to 7M training samples, our approach consistently improves OCR-centric benchmarks and delivers clear gains on general multimodal tasks.