Moving Object Segmentation (MOS) aims to discover, segment, and track objects that move independently of the camera. Current MOS methods, however, exhibit two fundamental limitations: they rely on pre-computed 2D auxiliary modalities such as optical flow or point trajectories that lack 3D geometric information, and they treat motion as a sequence-level attribute, overlooking the instantaneous motion state of each object. We address both by grounding MOS in 3D space and time, and propose GMOS, a framework that operates directly on RGB video to produce 3D-aware, temporally fine-grained segmentation of multiple moving objects, alongside a foreground--background variant GMOS-S for faster deployment. To support training and evaluation in this regime, we curate GMOS-2K, a dataset of 2,210 real-world videos with per-object temporal motion annotations drawn from five established Video Object Segmentation (VOS) benchmarks, and formalise MOS-I ("I" for instantaneous), a temporally fine-grained evaluation protocol with three complementary metrics. GMOS achieves state-of-the-art results across MOS, MOS-I, and Unsupervised VOS benchmarks, while running significantly faster than prior multi-object MOS methods and supporting online inference for streaming deployment.

Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by changing which tokens occupy the window or how their positions are encoded. The per-head KV layout itself, a dominant contributor to streaming memory and latency, has been mostly left unchanged. In this paper, we present the first study of Multi-Head Latent Attention (MLA) in video diffusion. VideoMLA replaces per-head keys and values with a shared low-rank content latent and a shared decoupled 3D-RoPE positional key, reducing per-token KV memory by 92.7% at every cached layer. We further investigate why MLA succeeds in video diffusion even though the spectral assumption often used to motivate it in language models does not hold: pretrained video attention is not low-rank, with 99%-energy effective rank far above any practical latent dimension. VideoMLA retains quality at compression ratios where direct spectral approximation would predict large reconstruction error. We show that the MLA bottleneck, rather than the pretrained spectrum, determines the effective rank: both spectral and random initialization occupy nearly the full rank budget from initialization, and training preserves this budget while adapting within it. On VBench, VideoMLA matches short-horizon streaming video diffusion baselines, achieves the best overall score at long horizons among evaluated methods, and improves throughput by 1.23x on a single B200.

Autoregressive video diffusion models generate streaming video by producing frames sequentially, conditioning each chunk on previously generated content. These models are structurally anchored to the first frame: its key-value representation occupies a privileged position in the attention cache and serves as the primary scene reference throughout generation. As the cleanest and most error-free position in the cache, this anchor draws disproportionate attention, suppressing video dynamics, and locking scene composition to the initial viewpoint even as the scene naturally evolves. The result is a temporally shallow video in which motion, camera movement, and scene progression are dampened in favor of static consistency. To address this, we replace the static anchor with an adaptive state, a hidden latent that the model denoises alongside content at every chunk but never renders. Rather than referencing a frozen first frame, the model generates its own scene anchor at each step by attending to both the previous state and the current content, producing a reference that evolves with the generated content. Unlike standard video generation, which encodes an absolute notion of time, our formulation treats time as relative: every generation step sees the same positional structure regardless of how far generation has progressed, and the state transition is identical at every chunk. Together, these properties introduce a recurrence into the generation process, where denoising serves as the transition function, and the KV cache serves as the carrier, requiring no external module. Experiments demonstrate that the adaptive state substantially improves video dynamics, enabling richer motion and natural scene progression within generated videos.

Data-driven approaches have revolutionized 3D vision, enabling transformers to effectively reconstruct and generate static 3D objects. However, generating simulative 4D dynamics -- realistic temporal deformations of static objects under various physical conditions -- remains challenging and often ad hoc, despite its importance in building comprehensive 3D world models. Most existing methods assume a predefined physical model and use system identification to estimate parameters, restricting these methods to specific categories and small-scale datasets. We propose that these restrictions can be overcome by learning a data-driven kinematic state parameterization for object-centric physical systems. Specifically, we learn both a latent space representing all possible states of the object and a decoder that maps any sampled latent to a plausibly deformed shape of the object. We refer to this parameterization as Neural Object Kinematics (NeuROK), and learn a transformer-based encoder-decoder model on a curated large-scale 4D dataset. This formulation and the learned model significantly simplify the generation of simulative dynamics since we only need to consider the dynamics within a low-dimensional latent space from the Lagrangian mechanics' perspective in classical physics. We demonstrate the effectiveness and generality of this neural simulation framework across diverse dynamic object types, showing clear advantages over prior works. Project page: https://chen-geng.com/neurok

As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistical temporal patterns? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present YoCausal, a two-level benchmark inspired by the Violation of Expectation (VoE) paradigm from cognitive science. By temporally reversing real-world videos at zero cost as natural counterfactual samples, YoCausal establishes an arbitrarily extensible evaluation protocol. Level 1 introduces the Reverse Surprise Index (RSI), quantifying arrow-of-time perception via denoising loss. Level 2 introduces the Causality Cognition Index (CCI), which leverages a VLM to stratify datasets into causal and non-causal subsets, disentangling genuine causal reasoning from temporal bias. Evaluation of 13 state-of-the-art VDMs reveals that perceiving the arrow of time does not imply understanding causality, and a significant gap persists relative to human-level causal cognition.

We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches.

Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet images captioned by a state-of-the-art vision-language model, including 100M training, 200K validation, and 1M test examples. Moreover, all GPIC images are permissively licensed for both research and commercial use. GPIC is safety-filtered, deduplicated, and centrally hosted on Hugging Face. We provide a benchmarking protocol for generative modeling on GPIC. Finally, we provide a reference baseline for pixel-space flow matching on GPIC. Our dataset, benchmark, and models are available at https://huggingface.co/datasets/stanford-vision-lab/gpic. Evaluation toolkit and code are available at https://gpic.stanford.edu

Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical processes. Existing evaluations emphasize perceptual realism and overlook physical correctness under controlled interventions. In this paper, we introduce FlatSounds, a benchmark that audits the physical reasoning of V2A models through: 1) controlled counterfactual pairs in which a single physical factor is varied, and 2) single-video pattern tests that probe internal consistency and directional trends. These settings test whether the generated audio correctly reflects specific physical properties and timings. Our evaluation of state-of-the-art models reveals a consistent trade-off: models rely more on text captions than the visual stream to infer physics and semantics. Captions generally improve physical and semantic accuracy, but paradoxically degrade temporal alignment. Our results highlight the need to move beyond audio quality toward learning physical processes directly from pixels. Finally, we find that our physics-based metrics correlate strongly with human preference tests on our own data. Project webpage: https://research.nvidia.com/labs/cosmos-lab/flatsounds/

Reconstructing physically stable 3D scenes from a single RGB image enables casual images to be converted into simulation-ready digital assets for applications such as immersive interaction and content creation. However, existing single-image reconstruction methods fall short in capturing the physical structure of a scene. As a result, they often produce geometrically plausible but physically inconsistent results, including object floating and penetration, which lead to unstable behavior in physics simulations. Image-conditioned scene generation methods improve physical plausibility but often rely on strong scene priors, yielding plausible yet inaccurate object arrangements that fail to match the input image. We propose REST3D, a single-image reconstruction framework that can reconstruct physically stable 3D scenes by integrating physical scene understanding with physics-constrained refinement. We first introduce an agentic physical scene understanding technique that constructs a scene-tree representation capturing object physical states and inter-object relationships from a gravity-support perspective, providing a structural prior for reconstruction. Leveraging this structure, we initialize the scene using image-to-3D models, followed by scene-tree-guided alignment and physics-constrained optimization to resolve physical violations while preserving visual consistency with the input image. Experiments show that our method significantly reduces physical errors and improves simulation stability on both synthetic and real-world datasets while maintaining strong reconstruction quality. We further demonstrate the reconstructed scenes in VR-based human-object interaction, showing their potential for immersive applications.

Diffusion models achieve state-of-the-art image synthesis, with their generative trajectories fundamentally exhibiting a spectral bias, resolving low-frequency global structures early and high-frequency fine details later. Conventional stochastic differential equation (SDE) solvers fail to account for this dynamic, naively injecting uniform white noise throughout the entire process and misusing the finite energy budget. In this work, we establish a mathematical framework that reconsiders SDE inference as a targeted, frequency-decoupled energy transfer. Leveraging this framework, we introduce Colored Noise Sampling (CNS), a novel, training-free stochastic solver. Rather than injecting uniform white noise, CNS utilizes a dynamic, timestep- and frequency-dependent schedule that more efficiently allocates injected energy toward structurally unresolved frequency bands. By actively exploiting the model's inherent spectral bias, CNS systematically steers the generated distribution toward the true data manifold. Extensive experiments demonstrate that CNS significantly outperforms standard ODE and SDE baselines as a strictly plug-and-play, inference-time sampler substitution across diverse architectures (SiT, JiT, FLUX). Compared to standard sampling on ImageNet-256, CNS achieves substantial unguided FID reductions, improving from 8.26 to 6.27 on SiT-XL/2, 32.39 to 26.69 on JiT-B/16, and 11.88 to 8.31 on JiT-H/16, while yielding consistent relative FID improvements with Classifier-Free Guidance. Project page is available at https://hadardavidson.github.io/CNS/.

Efficient and robust 3D scene representation is crucial in autonomous driving, robotics, and related fields. While RGB images provide valuable content for 3D reconstruction, other modalities like thermal or depth can enable additional information on the environment. Lately, novel view synthesis methods like 3D Gaussian Splatting have started using multiple modalities to further boost their performance. But fusing or combining multimodal data can make the process slower and can bring in additional challenges. Therefore, our project aims to use single modality based on thermal infrared domain, by removing the reliance on visible light as much as possible. This single modality can be expected to be faster as it does not rely on multimodal data. We propose a method, Thermal-to-Depth Gaussian Splatting (TDg), that uses only thermal images and depth estimation in its architecture to derive the radiance fields. Our TDg method outperforms the MSMG (Multiple Single-Modal Gaussians) baseline in most cases on our test datasets, RGBT-Scenes and ThermalMix. On average, the rendering quality metrics such as learned perceptual image patch similarity (LPIPS), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR) of TDg are 1.12%, 0.034%, and 0.01% better than the baseline MSMG values. It also reduces the training time significantly, by 12 mins 47 secs (55% improvement). Overall, our method is successful in deriving these thermal radiance fields, which can ultimately have several applications, such as identifying heat sources critical in surveillance, search or rescue operations, and industrial inspections where temperature is widely used to monitor machines.

Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse attention methods degrade under high sparsity. We show empirically that generation quality is determined not by the sparsity ratio itself, but by how well the sparse mask aligns with the tile-wise geometry of full attention. Based on this insight, we propose Veda, a distilled sparse attention framework that formulates tile selection as an explicit reconstruction problem from full attention. Veda integrates statistics-aware tile scoring with head-aware tiling to reduce estimation error and structural mismatch, enabling aggressive sparsity. A hardware-efficient tile-skipping kernel converts theoretical sparsity into practical wall-clock speedups. Experiments on large video diffusion models, including Waver and Wan2.1, demonstrate substantial acceleration with no noticeable degradation in generation quality. To generate 720P 10-second videos on Waver-T2V-12B, Veda achieves a 5.1$\times$ end-to-end speedup and a 10.5$\times$ self-attention speedup, reducing attention overhead from 92% to 50%. Notably, the gains increase with sequence length, indicating that Veda scales favorably with spatiotemporal resolution across models.

Existing inverse physics methods recover physical parameters from multi-view videos, where geometric constraints across views resolve scale and 3D structure. In monocular settings, however, such constraints are absent, leading to severe scale ambiguity, inaccurate geometry, and weak coupling between appearance optimization and physical simulation. We propose MonoPhysics, a framework for monocular inverse physics estimation of deformable objects using differentiable MPM simulation and 3D Gaussian Splatting, which jointly optimizes geometry, appearance, and physical parameters from a single camera view. We address these challenges through three visual-physical bridges: global scale alignment, physics-aware geometry refinement, and a differentiable position map, which together enable accurate optimization from monocular observations alone. We evaluate on Vid2Sim and our new dataset of elastic and plastic objects, showing that MonoPhysics outperforms existing baselines in monocular settings and achieves performance comparable to multi-view baselines using only a single camera. Our project page is available at https://daniel03c1.github.io/MonoPhysics/

Portrait photography is largely decided before the shutter opens: the subject's pose, the camera configuration, and the lighting devices must be coordinated within the surrounding 3D scene. In contrast, most existing computational methods focus on post-production in 2D image space, such as retouching, relighting, or editing images that already exist; pre-capture photographic planning remains largely unexplored. We introduce 3D aesthetic portrait planning, the task of generating human pose, camera, lighting, and exposure plans that produce visually compelling portraits while satisfying geometric and photometric feasibility in a 3D scene. Our approach builds a Photographic Scene Graph that represents scene affordances, subject-scene relations, and portrait-relevant lighting structure. Built on this representation, we perform aesthetic-guided comparative planning over previous attempts and current viewfinder observations. Experiments across diverse indoor and outdoor scenes show that our method produces portraits preferred by human raters and MLLM evaluators over competitive baselines, while maintaining high physical plausibility. Together, our results suggest a path from post-capture correction toward pre-capture computational portrait planning. Project repository: https://github.com/songrise/Before-the-Shutter

Autoregressive image and video generators are trained with teacher-forced histories but must sample from their own generated prefixes at inference time, making them vulnerable to exposure bias and prefix drift. Existing remedies either modify training or apply sampling-time guidance aimed primarily at external semantic conditions, such as class labels or text prompts, rather than testing whether a next-step prediction provides strong posterior support for the generated prefix itself. We propose Visual Prefix Guidance (VPG), a training-free inference-time guidance method for autoregressive image and video generation. VPG improves next-step prediction by contrasting the model's output under the generated prefix with its output under a corrupted prefix, then extrapolating logits toward candidates that strengthen the posterior support of the generated prefix. Across class-conditional image generation with VAR, text-to-image generation with Infinity, and text-to-video generation with InfinityStar, VPG improves generation quality without retraining the base model, reducing FID on VAR by 0.36 on average and improving benchmark performance on both image and video generation.

Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visual content, remains an open challenge. In this paper, we present Archon, a fully pretrained, human-centric unified multimodal model for holistic avatar generation. Archon unifies seven modalities with modality-specific tokenizers, and a native autoregressive unified multimodal model pretrained on synchronized modalities and 72 diverse tasks to model holistic joint distributions. To address the token explosion challenge in high-fidelity talking videos, we introduce a memory-efficient semantic video reparameterization, achieving 4x token reduction while preserving fine-grained dynamics, coupled with a semantic-driven video diffusion decoder. We further propose a "Thinking in Modality" that decomposes ambiguous cross-modal tasks into stepwise thinking in an alternative chain of modality, progressively enhancing fidelity and controllability. Extensive experiments demonstrate that Archon achieves superior or comparable performance across diverse digital human generation tasks, validating the effectiveness of our unified framework. Project page: https://zju3dv.github.io/archon/.

City-scale 3D surface reconstruction from multiview images for downstream 3D simulation, poses highly challenging problems due to the scale and complexity of urban scenes. Existing city-scale 3D reconstruction methods based on NeRF, Gaussian Splatting etc. often fail to recover 3D meshes ready for simulation due to incomplete/missing geometry and irregular, noisy surfaces. Scaling existing small-scale 3D reconstruction methods to arbitrarily large urban scenes is highly infeasible due to their computational complexity. We present City-Mesh3R, a scalable framework for reconstructing watertight surface meshes directly from large unordered image collections. Unlike recent methods which use global sparse SfM point-cloud initialization followed by a distributed 3D dense reconstruction of large-scale scenes, our method follows an end-to-end images-to-mesh 3D reconstruction approach using a divide-and-conquer strategy. The sparse city map is reconstructed via topological image clustering, cluster-wise independent sparse SfM and map merging, without need for exhaustive image feature matching. Then this map is partitioned spatially to perform geometry-aware camera selection, followed by dense surface reconstruction and surface refinement using curvature-aware adaptive vertex density remeshing. These partition meshes are then stitched together to produce the global mesh of the city. The proposed end-to-end framework is evaluated on city-scale reconstruction datasets. As demonstrated by our qualitative and quantitative results, our proposed method yields high-fidelity watertight 3D meshes with regular geometry, capturing fine surface details, and is suitable for scaling to arbitrarily large scenes owing to the end-to-end processing in a distributed setting.

We present GR3D, a spatial vision language model equipped with three complementary grounding capabilities--explicit 2D grounding, implicit 2D grounding, and monocular 3D grounding--within a single framework. GR3D introduces an implicit grounding mechanism that identifies entity mentions during generation and inserts the corresponding region tokens into the text stream, allowing the model to reference visual evidence on the fly when producing spatial chain-of-thought responses. In parallel, a region-prompted monocular 3D grounding design predicts 3D bounding boxes in the camera view from grounded region queries, supported by intrinsic-aware normalization and dense geometric supervision. Together, these grounding capabilities enable GR3D to decompose complex spatial understanding problems into grounded 2D perception followed by 3D inference. GR3D achieves consistent improvements across grounded and non-grounded spatial benchmarks, demonstrating grounding as an effective inductive bias for strengthening spatial understanding in VLMs. These grounding capabilities collectively enhance general spatial understanding beyond the grounding task itself.

Over the past decades, numerous Image Quality Assessment (IQA) models have emerged, aiming to predict the perceptual quality of images. However, individual models are often biased toward certain types of image content or distortions, depending on the design principle and process. An intuitive idea is to harness the strengths and mitigate the weaknesses of each IQA model, by fusing the scores of multiple models into a stronger one. Here we make one of the first attempts to seek an optimal solution for the idea and propose a general framework for unsupervised IQA score fusion using deep Maximum a Posteriori (MAP) estimation. The proposed model conducts fine-grained uncertainty estimation at the score level to increase the accuracy and reduce the uncertainty in fused predictions. Comprehensive experiments demonstrate the superiority of the proposed model over individual IQA models and other fusion methods. It also exhibits an interesting capability of rejecting ``bad" models in the fusion process.

We address the task of generating physically accurate and visually faithful 4D Human-Object Interaction (HOI). Given a static 3D human and target object represented as 3D Gaussian Splats (3DGS), our goal is to synthesize dynamic scenes where the human actively engages with the object through actions, such as punching or kicking, in accordance with a given input text. To this end, we introduce PhyGenHOI, a novel framework that couples generative human motion with an explicit physical object simulation. We model the human as a semantic agent driven by a Motion Diffusion Model (MDM) and the object as a physical agent simulated via the Material Point Method (MPM), utilizing 3D Gaussians as a unified, differentiable representation. We supervise their interaction through three coupled mechanisms: (1) A Windowed Attraction Loss that temporally synchronizes generative motion to intercept the object; (2) A Contact-Driven Re-simulation step that triggers physically consistent momentum transfer upon impact; and (3) A Masked Video-SDS objective that injects video-based priors to enhance contact fidelity. Experiments show PhyGenHOI generates physically consistent 4D HOI across diverse actions, humans, and objects, outperforming baselines. Project page and videos: https://omerbenishu.github.io/PhyGenHOI/

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its rendered-image counterpart should leave model performance essentially unaffected. In practice, however, such modality substitution induces dramatic performance degradation. We attribute this "carrier sensitivity" issue to an inherent bias in current training corpora. Across prevalent datasets such as image captioning, VQA, OCR, and web-sourced interleaved data, text and images are typically organized into distinct and asymmetric roles, with text serving as linguistic queries and images as visual references. Such data bias leads VLMs to exhibit distinct preferences for information acquisition across different modalities. Consequently, VLMs fail to align representations of semantically equivalent content across textual and visual carriers, making model reasoning fragile under modality substitution. To address this, we propose Local Modality Substitution (LoMo), a lightweight, architecture-agnostic data curation paradigm designed to provide supervision for cross-modal representational invariance between semantically equivalent text and image carriers. LoMo achieves this by reformulating single-modality prompts into seamlessly interleaved multimodal sequences. It dynamically selects target text spans and recasts them as rendered images, thereby preserving the same semantics across "text, visual, text" carriers. Extensive experiments across 13 diverse multimodal benchmarks demonstrate that LoMo significantly improves overall multimodal reasoning and yields deeper cross-modal fusion. Specifically, it delivers consistent gains across foundational models, improving over standard SFT by 2.67 points on LLaVA-OneVision-1.5-8B and 2.82 points on Qwen3.5-9B.

Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable, causal, and low-latency rollout, which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In this work, we present minWM, a full-stack open-source framework for building real-time interactive video world models. minWM provides an end-to-end pipeline that converts existing bidirectional T2V/TI2V video foundation models into camera-controllable few-step autoregressive world models. Specifically, minWM first fine-tunes a bidirectional video diffusion model with camera control, and then applies the Causal Forcing / Causal Forcing++ pipeline, including AR diffusion training, causal ODE or causal consistency distillation, and asymmetric DMD, to distill it into a few-step autoregressive generator for low-latency rollout. The framework is modular and architecture-extensible: we instantiate it on representative open backbones, including Wan2.1-T2V-1.3B and HY1.5-TI2V-8B, covering both cross-attention-based condition injection and MMDiT-style architectures. minWM also supports adapting existing video world models, such as HY-WorldPlay, to new data distributions, training recipes, and latency targets. Beyond releasing runnable scripts, checkpoints, documentation, and inference code, we provide practical ablations on camera trajectory quality, controllability training steps, and minimal batch-size requirements. We hope minWM serves as a reproducible and extensible recipe for building and adapting real-time interactive video world models. Project Page: [https://github.com/shengshu-ai/minWM](https://github.com/shengshu-ai/minWM)

Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used for such memory updates, existing studies mainly rely on qualitative downstream evaluations, leaving the quantitative capacity limits and underlying dynamics of exact parametric memory largely unexplored. To bridge this gap, we employ LoRA as a controlled memory capacity probe within the latent space to systematically quantify exact parametric memory. We introduce the Parametric Memory Law, a robust power law linking loss reduction Delta L to effective parameters and sequence length. At the token level, fine-grained analysis reveals a deterministic phase transition, demonstrating that a prediction probability of p > 0.5 constitutes a sufficient condition for verbatim recall under greedy decoding. Driven by these insights, we introduce MemFT, a threshold-guided optimization strategy that dynamically redistributes the training budget toward sub-threshold tokens. Empirical evaluations demonstrate that MemFT can enhance memory fidelity and efficiency. Code will be released at https://github.com/zjunlp/ParametricMemoryLaw.

We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from Qwen-Image-Layered, we apply Flow-GRPO with LoRA adaptation, sampling multiple candidate decompositions per image, scoring them with a VLM, and optimising the policy from group-relative advantages. The key challenge lies in designing a reliable reward signal: VLMs scoring samples in isolation tend to compress their judgements into a narrow band, leaving GRPO with little within-group variance to learn from. We address this with a two-stage evaluation pipeline that pairs structured per-sample scoring across five edit-centric criteria with a grid-based calibration step in which the VLM re-scores all candidates side-by-side. Stable-Layers produces decompositions with stronger layer separation, fewer blank or artifact-heavy layers, and lower per-layer reconstruction error on the Crello dataset compared to the base model.

Natural human conversation is full-duplex and audio-visual: people simultaneously speak and listen while continuously interpreting and producing nonverbal cues, such as nods, smiles, and gestures. To support successful human-agent interaction, agents must model full-duplex audiovisual conversation; however, existing full-duplex benchmarks evaluate only speech. In this work, we present VideoFDB, the first benchmark to evaluate full-duplex audio-visual-to-audio-visual (AV2AV) conversational agents. VideoFDB contributes (i) 237 dyadic clips spanning 11 nonverbal conversational dynamics from real-world video calls, (ii) a taxonomy separating perception from generation behaviors, and (iii) a rubric-based LM-as-judge evaluation framework with interpretable axes for assessing conversational quality with respect to nonverbal conversational dynamics. Across open- and closed-source vision-speech agents, we find systematic failure modes: captioning collapse and visual-stream ignorance, and we show that current systems exploit vision for explicit visual question answering but not for the streaming joint audiovisual grounding required in natural conversation. We further evaluate cascaded speech-to-avatar systems and find that their architecture fundamentally precludes the production of full-duplex nonverbal cues. As the first benchmark for full-duplex AV2AV interaction, VideoFDB establishes a foundation for systematic evaluation and, we hope, will accelerate the advancement and development of next-generation multimodal conversational agents.

Inverse rendering aims to reconstruct geometry and reflectance of objects from images. Despite recent progress, existing methods often produces inaccurate reconstructions that are sensitive to ambient illumination conditions. Here we introduce an ambient-robust inverse rendering method enabled by active RGB-NIR imaging. Our key insight is to leverage near-infrared (NIR) flash illumination-imperceptible to human observers-to obtain stable point-light shading that is largely invariant to ambient illumination. By using multi-view RGB images illuminated by ambient light and NIR images acquired with active NIR flash illumination, we reconstruct accurate geometry and reflectance by exploiting the complementary benefits of RGB and NIR images via a three-stage inverse rendering method. To enable dense multi-view acquisition, we develop an active imaging system equipped with a RGB-NIR camera and a NIR flash mounted on a mobile base. Using this system, we collect the first multi-view RGB-NIR inverse rendering dataset captured under multiple ambient illumination conditions. Experiments demonstrate that our method outperforms prior approaches, achieving accurate geometry and reflectance estimation across multiple ambient lighting scenarios.

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning steps, and constraints). Rubrics provide a natural interface for this fine-grained supervision, but their effectiveness depends on the execution accuracy during online RL. We propose Reinforcement Learning with Robust Rubric Rewards ($\text{RLR}^3$), extending RLVR from task-level verification to criterion-level verification. $\text{RLR}^3$ routes instance-specific rubrics through two execution paths: an LLM-as-an-extractor paired with a deterministic verifier, or an LLM-as-a-Judge for non-verifiable criteria. To ensure faithful scoring, $\text{RLR}^3$ introduce a minimal exposure strategy that masks ground truths from extractors and images from judges. Furthermore, $\text{RLR}^3$ employs hierarchical aggregation to prioritize essential criteria over additional criteria, and mitigates score saturation within rollout groups. Evaluated on Qwen3-VL-30B-A3B across 15 benchmarks, $\text{RLR}^3$ consistently outperforms RLVR, yielding a 4.7-point improvement over the base model and exceeding the official instruct-to-thinking model gap. Controlled audits confirm our deterministic verification and minimal exposure significantly reduce exploitable false positives.

This work addresses the problem of recovering complete, simulatable object geometry from reconstructed real-world scenes, enabling physics-based interaction with objects embedded in the scene. While modern multi-view reconstruction methods can produce visually accurate environments, objects are often incomplete due to occlusions and limited observations, making them unsuitable for physics simulation. To address this limitation, we propose SAM3D-Phys, a framework that integrates scene reconstruction with generative 3D priors of SAM3D to recover physically simulatable objects. Our approach first reconstructs the scene from multi-view images to obtain scene geometry and partial observations of objects. We then leverage SAM3D to infer complete object geometry from these partial observations. To ensure that the recovered objects remain consistent with the reconstructed scene, we restore scene-consistent object states through two complementary strategies: a physics-constrained spatial optimization algorithm that iteratively aligns the recovered object to its original location, and a mask-guided appearance distillation module that refines texture fidelity based on the observed images. By recovering complete object geometry and restoring its pose and appearance within the scene, SAM3D-Phys produces clean object representations suitable for physics-based simulation, enabling simultaneous and physically consistent interactive simulation of multiple objects within a reconstructed scene. Project page: https://chnxindong.github.io/sam3d-phys/

We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575). The corpus comprises 20,898 pages and 499,222 text lines written by 796 writers over six decades, featuring stylistic variation, multilingual content (mostly Latin and Early New High German) as well as meta-information such as writer identity and time. We evaluate BullingerDB on text recognition and writer retrieval. TrOCR, the best performing model, achieves a CER of 9.1%. For writer retrieval, we introduce a temporal nDCG metric to assess time-aware retrieval. While temporally coherent retrieval is achievable, mAP (78.3%) scores indicate challenges due to long-term stylistic variation. With BullingerDB, we aim to establish a new benchmark for multilingual historical text recognition and temporally-aware writer analysis.

Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-answering (VQA) datasets may overfit dataset-specific biases, while integrating specialized 3D visual encoders is often inflexible and cumbersome. In this paper, we argue that genuine spatial understanding should emerge from learning fundamental geometric priors, not only from high-level VQA supervision. We propose GASP (Geometric-Aware Spatial Priors), a framework that injects these priors directly into the LLM's transformer layers. GASP employs a small correspondence head, applied as a deep supervision signal across all layers, and is trained with a dual objective leveraging ground-truth geometry from large-scale video scenes: a contrastive loss on ground-truth point correspondences enforces 2D view-invariance, while a depth consistency supervision resolves 3D geometric ambiguities. Our analysis first provides a diagnostic showing that standard VLMs' internal correspondence matching accuracy is very low (often below 5%). We then demonstrate that our training substantially improves this behavior, boosting peak layer-wise correspondence to over 70% and maintaining over 85% temporal robustness while baselines remain below 5%. These internal improvements translate to significant gains on downstream spatial benchmarks including +18.2% on All-Angles Bench and +29.0% on VSI-Bench, all without training on any 3D VQA data. Our findings indicate that learning from fundamental geometric priors is a promising and generalizable pathway towards VLMs with more reliable 3D spatial reasoning.

With the rapid advancement of diffusion models, talking face generation has made remarkable progress. However, existing diffusion-based methods still require task-specific fine-tuning and large-scale audiovisual datasets, resulting in high computational costs that hinder scalability and accessibility of diffusion-based approaches across the research community. To address this, we propose a finetuning-free paradigm that directly performs talking face generation using the pretrained weights of Stable Diffusion and IP-Adapter. This backbone leverages the visual embedding capability of IP-Adapter to mine lip-related semantics from the pretrained Stable Diffusion. To address the challenges of identity drift, synchronization errors, and temporal instability, we also design three trainable-parameterfree components: (1) the Structurist, which explicitly disentangles and reassembles lip and appearance features to mitigate identity drift and appearance distortion; (2) the Structure Controller, which adaptively refines embeddings based on quasi-monotonic motion trends for precise lip synchronization; and (3) the Noise Sensor, which introduces Gaussian prior to detect and suppress flicker and jitter artifacts and enhance temporal consistency. Experimental results show that our method outperforms existing SOTA approaches in both lip-sync accuracy (at least 0.16 gain in PCLD) and visual fidelity (at least 0.7 improvement in FID), establishing a novel fine-tuning-free diffusion framework for talking face generation.

Self-supervised video Object-Centric Learning (OCL) aims to discover distinct objects and associate them across time, whereas self-supervised Multi-Object Tracking (MOT) focuses on associating pre-defined object detections or segmentations. Although well-established in MOT, Cycle Consistency (CC) cannot naively or explicitly apply to the latent slot space of OCL. Unlike the deterministic and ideal object representations in MOT, OCL slots are inherently stochastic and ambiguous due to non-unique scene decompositions. Enforcing explicit cycle consistency (ECC) on slots imposes rigid mean seeking. This severely penalizes the model for exploring alternative but equally valid decompositions, thereby driving towards feature collapse. To resolve this dilemma, we propose \textit{Implicit Cycle Consistency (ICC)}, which shifts the cycle-consistency constraint from the restrictive slot space to the continuous reconstruction manifold, encouraging slots to reach a soft consensus on collectively interpreting the visual scene rather than forcing rigid point-to-point feature alignment. Extensive experiments on complex video OCL benchmarks demonstrate that ICC avoids feature collapse and outperforms ECC baselines. Our source code, model checkpoints and training logs are provided on https://github.com/Genera1Z/ICC.

We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation methods struggle with complex motions: LLM-based code synthesis fails to express fine, non-rigid Bézier deformations, while Score Distillation Sampling (SDS) provides noisy gradients and often requires category-specific priors like skeletons. In contrast, LiveSVG fits vector geometry directly to an explicitly generated target video. Given an input SVG image and a motion prompt, we generate a previewable target video using a frozen image-to-video model, then fit the original SVG to this video via differentiable rendering. Our fitting stage is skeleton-free, utilizing a dual-level motion representation that combines per-group homographies for coarse articulation with per-path Bézier control-point offsets for local deformations. To resolve color-induced correspondence ambiguities during pixel-wise fitting, we introduce a novel sphere-packing recolorization strategy. We also present ChallengeSVG, a benchmark of complex, multi-object scenes that exposes the limitations of prior work. Evaluations demonstrate that LiveSVG significantly outperforms existing methods on both AniClipart and ChallengeSVG, establishing direct reference-video fitting as a practical, robust route to prompt-aligned and fully editable vector animation.

While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting. In this work, we investigate this extrapolation bottleneck by deconstructing visual counting into three cognitive stages: visual individuation, magnitude awareness, and symbolic mapping. Using synthetic Go boards and linear probes, we demonstrate that visual backbones maintain robust, linearly separable representations of quantity well into the extrapolation regime, ruling out perceptual failure. Furthermore, models retain latent magnitude awareness, successfully performing comparative reasoning on quantities they fail to enumerate. We pinpoint the collapse to the symbolic mapping stage, where the model fails to project valid visual magnitudes onto symbolic tokens. Our findings support a frac tured magnitude hypothesis: VLMs fail to acquire a universal number space, instead learning disjoint, modality-specific statistical manifolds that prevent cross-modal grounding for unseen quantities. Validated on the state-of-the-art foundation model, our results suggest that bridging this gap requires inductive priors enforcing unified representations, as data scaling alone is insufficient.

Change detection (CD) in remote sensing is vital for applications such as urban monitoring and disaster assessment, yet traditional methods struggle with generalization across diverse scenarios. We present OmniCD, a foundational framework that unifies and enhances remote sensing CD through multimodal semantic guidance. OmniCD incorporates image and text prompts -- such as textual descriptions, semantic maps, and geospatial metadata -- into a unified architecture, supporting tasks from binary CD to zero-shot semantic change understanding. The framework integrates a hierarchical scene retrieval module and a change detection module, reinforced by a style disentanglement mechanism for improved cross-domain robustness. We further introduce RSITCD, a large-scale multimodal dataset with 300K+ annotated image-text pairs. Extensive experiments show that OmniCD achieves state-of-the-art performance across benchmarks, demonstrating strong adaptability and setting a solid foundation for general-purpose CD systems in remote sensing.

Predicting a complete spatially correlated field from sparse observations is a fundamental challenge in spatial statistics and environmental modelling. Classical interpolation methods such as Kriging rely on Gaussian process assumptions and variography, which can limit their effectiveness in non-stationary settings and require substantial domain expertise. In this work, we leverage an architecture based on convolutional neural networks (CNNs) for spatial interpolation that is trained and applied on a single partially observed field, without access to external data or prior fields. The model is supervised directly on the observed locations and learns to predict values at unobserved points on the user defined grid. Unlike Kriging, our method does not require explicit covariance modelling or variogram estimation, and it can flexibly capture local spatial patterns in a data-driven manner. This work demonstrates the potential of CNNs for single-instance spatial interpolation under sparse supervision, offering a practical alternative to classical geostatistical methods, and extending the use of CNNs to a new problem domain.

Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a representation-level analysis framework that constructs minimal contrastive pairs to measure how spatial axes are organized and disentangled within VLM embeddings. Our analysis across multiple model families reveals a consistent vertical-distance entanglement: models conflate vertical image position with distance, mirroring the perspective bias of natural photographs. This bias produces a significant accuracy gap between perspective-consistent and counter-heuristic examples, and intensifies under data scaling even as overall benchmark accuracy improves. We further show that models with similar benchmark scores can exhibit different internal representations, and that these differences predict accuracy and robustness across diverse spatial reasoning benchmarks. To isolate this bias from evaluation-set skew, we introduce SpatialTunnel, a synthetic benchmark designed to expose spatial shortcut biases by removing common correlations present in natural images. Experiments confirm that the entanglement is model-intrinsic, and that models with well-separated spatial axes exhibit greater robustness, suggesting that well-structured spatial representations lead to more reliable spatial reasoning across diverse benchmarks. Code and benchmark are available on the project page: https://cheolhong0916.github.io/whyfarlooksup.github.io/.

Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, they require substantial training on large auxiliary datasets to adapt VLMs to anomaly detection, and their inference largely relies on visual-text embedding similarity-based anomaly scores, lacking reasoning abilities to detect complex anomalies that require in-depth contextual understanding. To address this limitation, we propose \textbf{AnomalyAgent}, a novel training-free, agentic framework that leverages the advanced reasoning and generalization capabilities of multimodal large language models (MLLMs) for anomaly detection. The key ingredients include \textbf{1)} a comprehensive anomaly-centric toolset that enables adaptive MLLM-driven, agentic anomaly reasoning in zero-shot settings, and \textbf{2)} a customized memory module that grounds anomaly reasoning with few-shot, in-context reference examples. We extend evaluation beyond the detection of simple anomalies (e.g., surface defects like cracks and dents and clear lesions) in widely used benchmarks to more diverse types of anomalies such as logical/contextual anomalies in logistics and manufacturing settings. Extensive experiment results demonstrate that our AnomalyAgent achieves substantially better performance compared to training-free VLM-based AD and generic agentic methods, highlighting its superior generalization capability in both zero-shot and few-shot anomaly detection settings. The code implementation can be find at this address.

Radiology report generation (RRG) is commonly formulated as a single-path generation task, where a multimodal large language model (MLLM) produces one decoded report as the final output. While recent progress has largely been driven by scaling training data, model capacity, and retrieval mechanisms, improving report quality at inference time remains underexplored. In this work, we observe that fixed radiology MLLMs often generate clinically stronger reports elsewhere in their candidate pool than the one selected by default decoding, suggesting that inference-time decision making remains an overlooked bottleneck. To address this, we propose Clinical Consensus Selection (CCS), a decoder-agnostic inference-time selection framework that samples multiple candidate reports and selects the one with the highest clinical consensus across the rollout pool. CCS unifies text-based utilities with a radiology-adapted utility computed by an image--report-trained multimodal embedder, which measures candidate agreement beyond surface-level textual similarity. Across three datasets and multiple radiology MLLMs, CCS consistently improves inference-time performance over single-path decoding and generic Best-of-N baselines, with particularly clear gains on clinical metrics. Further analysis shows that image-grounded utility forms a selection axis distinct from textual consensus and that substantial headroom remains for improving RRG at inference time.

Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression addresses this by training a single model that can run at multiple visual-token budgets. However, existing approaches struggle under aggressive compression. Spatial-only compression, as in nested pooling, behaves as an imperfect low-pass filter and induces spectral aliasing that obscures fine-grained detail. Query-only compression, as in nested query resampling, replaces explicit grid-aligned tokens with non-local summaries and substantially degrades spatial grounding. To resolve this representational conflict, we introduce PARCEL (Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding), a visual tokenization architecture that dynamically partitions the labor of feature extraction. PARCEL establishes spatial pool tokens as low-frequency layout anchors and conditions elastic query tokens on these anchors through Pool-Conditioned Query Resampling. This encourages query tokens to focus on complementary visual features rather than redundant spatial mapping. Extensive evaluations across 27 benchmarks show that PARCEL improves the performance-efficiency Pareto frontier, consistently outperforming existing matryoshka baselines across visual-token budgets while preserving the "train once, deploy anywhere" paradigm.

Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously evolving generator, making training costly when frequent updates are required, while reverse-KL-style matching can be mode-seeking and conservative for preserving strong motion dynamics. To address these issues, we propose \textbf{Score Gradient Matching Distillation (SGMD)}. SGMD adopts a fake-score perspective by directly optimizing the fake score toward the teacher, while using teacher stop-gradient Fisher as a stable distribution-matching objective. We provide a gradient analysis that motivates this objective choice under ideal tracking. Building on this, SGMD introduces a pair of dual potentials: negative-residual (NR) for outer-loop correction and residual-contraction (RC) for inner-loop tracking. Empirically, compared to DMD2, SGMD achieves an approximately $\sim 3\times$ training speedup and substantially improves motion dynamics for 4-step distilled models while preserving temporal consistency. A human study confirms that SGMD is preferred in motion quality and overall preference, while visual quality and text alignment remain comparable. Code is available at https://github.com/ModelTC/LightX2V.

This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates metric-accurate dense depth maps using a transformer. It outperforms existing approaches across diverse datasets and sparse observations. We achieve this from two key perspectives: (1) leveraging existing monocular foundation models to improve the quality of sparse depth inputs, and (2) reformulating training objectives to better capture geometric structure and metric consistency. Specifically, a Poisson-based depth initialization strategy is first introduced to generate a uniform coarse dense depth map from diverse sparse observations, providing a strong structural prior for the network. Regarding the training objective, we replace the conventional depth head with a point map head that regresses per-pixel 3D coordinates in camera space, enabling the model to directly learn the underlying 3D scene structure instead of performing pixel-wise depth map restoration. Moreover, this design eliminates the need for camera intrinsic parameters, allowing LDCM to naturally produce metric-scaled 3D point maps. Extensive experiments demonstrate that LDCM consistently outperforms state-of-the-art methods across multiple benchmarks and varying sparsity levels in both depth completion and point map estimation, showcasing its effectiveness and strong generalization to unseen data distributions.

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity, different sensing modalities face inherent limitations. 2D images provide rich texture and appearance cues, yet they lack explicit depth and geometric structure. In contrast, 3D point clouds capture accurate spatial geometry but are sparse and contain no texture information. As a result, relying on a single modality restricts the richness of learned representations and weakens generalization. Although recent multi-modal methods that combine 3D point clouds with 2D images have demonstrated strong performance in tasks such as classification and retrieval, they typically depend on large-scale labeled datasets and have not been fully exploited for data-efficient dense prediction. To address these limitations, we propose a novel cross-modal knowledge distillation framework, xModel-KD, for 3D point cloud segmentation. Our method exploits the complementary strengths of 2D texture and 3D geometry by learning unified per-point representations through cross-modal alignment. Specifically, we design a cross-modal fusion encoder trained with a contrastive objective that enforces feature consistency between corresponding 2D and 3D representations across multiple views. By integrating powerful pre-trained backbones with a targeted fusion strategy, the proposed framework effectively transfers appearance cues from images to geometry-aware point features. Experimental results show that cross-modal fusion achieves a 2% absolute improvement in mIoU over a LiDAR-only baseline, demonstrating the benefit of leveraging complementary multi-modal information for scalable and annotation-efficient 3D scene understanding.

Valuable decisions and highly prioritized analysis now depend on applications such as facial biometrics, social media photo tagging, and human robots interactions. However, the ability to successfully deploy such applications is based on their efficiencies on tested use cases taking into consideration possible edge cases. Over the years, lots of generalized solutions have been implemented to mimic human emotions including sarcasm. However, factors such as geographical location or cultural difference have not been explored fully amidst its relevance in resolving ethical issues and improving conversational AI (Artificial Intelligence). In this paper, we seek to address the potential challenges in the usage of conversational AI within Black African society. We develop an emotion prediction model with accuracies ranging between 85% and 96%. Our model combines both speech and image data to detect the seven basic emotions with a focus on also identifying sarcasm. It uses 3-layers of the Convolutional Neural Network in addition to a new Audio-Frame Mean Expression (AFME) algorithm and focuses on model pre-processing and post-processing stages. In the end, our proposed solution contributes to maintaining the credibility of an emotion recognition system in conversational AIs.

Foundation features from self-supervised vision models and text-to-image diffusion models have proven effective for semantic correspondence estimation. However, because these features are learned primarily from 2D image objectives, they lack explicit 3D awareness and often confuse symmetric object sides, repeated parts, and visually similar structures that are distinct in 3D. We introduce a 3D-aware post-training framework that goes beyond available 2D foundation features by incorporating priors from 3D foundation models. Given an image, our method uses SAM3D to estimate object geometry and pose, and refines the pose through render-and-compare optimization. Subsequently, we render PartField descriptors from the reconstructed geometry into the image plane based on the estimated object pose. The resulting geometry-aware feature maps complement DINO and Stable Diffusion features, while geodesic distances on the reconstructed shapes enable reliable filtering of candidate correspondences. We use the filtered matches as supervision to train a lightweight adapter on top of DINO and Stable Diffusion for semantic correspondence. In contrast to prior post-training approaches that require pose annotations and rely on coarse spherical geometry, our method automatically obtains instance-specific 3D structure and uses it to guide correspondence learning. Experiments show that our approach improves semantic correspondence over the prior methods while reducing manual geometric supervision. Code and model can be found at https:/github.com/GenIntel/3D-SC.

Long-form video generation is rapidly moving from short, single-scene synthesis toward minute-long, multi-shot creation with narrative structure, cinematic control, audio, and cross-modal synchronization. However, evaluating such videos remains challenging, since existing benchmarks largely focus on local visual quality, short-horizon temporal consistency, or generic prompt alignment, and provide limited diagnosis of workflow failures and user-dependent preferences. We introduce DirectorBench, a personalized multi-agent diagnostic benchmark for long-form video generation. DirectorBench evaluates generated videos with respect to 80 structured metadata entries, 7 user profiles, and 40 checkpoint criteria across 5 dimensions: script, visual, audio, cross-modal, and stability. Instead of reducing quality to a single aggregate score, DirectorBench localizes checkpoint-level bottlenecks and supports profile-aware evaluation. We evaluate 4 long-form video generation workflows, 6 base LLMs, and 7 user profiles. Across workflows, DirectorBench reveals a between-unit bottleneck: transition quality averages only 0.256 and reaches 0.356 for the best workflow, while prompt-level user demand fulfillment averages 0.71. We further conduct human evaluation with 14 annotators to validate the alignment between DirectorBench and human judgment. The results show that DirectorBench captures human-perceptible quality differences and reveals workflow- and profile-dependent failure modes that are hidden by aggregate scoring. These findings highlight the importance of diagnostic and profile-aware benchmarking for long-form video generation.

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid redundant recomputation across generation steps. Nevertheless, its growth with generation length introduces increasing memory and error accumulation, limiting the scalability of AR models to even longer sequences. Existing KV cache compression methods mitigate this issue by selectively retaining only video tokens deemed important. However, most existing methods assess token importance using short-horizon signals derived from the current or historical generation context, making these methods prone to overlooking tokens that appear unimportant at early steps but later become critical for future frames. In this work, we identify an important property of trained AR video models: although RoPE-modulated queries evolve across autoregressive steps, the underlying canonical pre-RoPE query distribution remains remarkably stable throughout the video generation process. This approximate stationarity implies that future query distributions are estimable from historical statistics, enabling principled future-aware cache decisions without any additional training. Building on this insight, we propose Future Forcing, a training-free future-aware KV cache policy for AR video generation. Specifically, Future Forcing first constructs a future query proxy from historical statistics, then scores KV cache tokens by their importance under this proxy, and finally merges redundant token pairs within the affine subspace induced by the future query. Extensive experiments show that Future Forcing improves long-horizon consistency under limited KV caches, achieving up to 1.49 improvement in subject consistency on VBench-Long for 60s generation over existing AR video KV cache policies.

Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on either dual-tower designs with posterior alignment or fully unified tri-modal designs that mix textual context, audio and video in one shared space. The former weakens fine-grained audio-video co-evolution, while the latter couples semantic conditioning with low-level synchronization. To address these limitations, we propose NAVA, a Native Audio-Visual Alignment framework for joint audio-video generation. NAVA is built upon context-conditioned native audio-visual alignment: it first establishes audio-video correspondence in a dedicated interaction space, and then uses external context to condition the joint denoising process. Specifically, NAVA is instantiated with an Align-then-Fuse MMDiT architecture, which transitions from modality-aware audio-video alignment to modality-shared joint denoising. Furthermore, we introduce Timbre-in-Context Conditioning to associate reference timbre cues with corresponding speech spans to achieve controllable speech timbre. Experiments on Verse-Bench and Seed-TTS, together with a user study, demonstrate that NAVA achieves superior video quality, precise audio-visual synchronization, competitive audio quality, and stronger reference-timbre controllability using only 6.3B parameters.

In this work, we focus on zero-shot 3D style transfer that can generate multi-view consistent stylized views of the 3D scene given an arbitrary style image. We primarily tackle the issue of data scarcity in 3D style transfer, which arises when each model is trained on only a single scene, thereby limiting the number of available content images. This scarcity significantly hampers stylization performance, as model optimization relies on a sufficient number of content-style image pairs to provide supervisory signals. Our core idea is to integrate a decoder pre-trained on large-scale 2D image datasets into the 3D style transfer pipeline, thereby leveraging the prior knowledge encoded in the decoder from learning over numerous content-style image pairs. Our method combines feature Gaussian splatting and deferred stylization, enabling high-quality stylization with the data-sufficient decoder network while ensuring view consistency by unifying view-dependent operations into a view-invariant process. Experiments demonstrate that our Data-Sufficient StyleGaussian (DS-StyleGaussian) model outperforms existing zero-shot 3D style transfer methods in terms of visual quality across various datasets. This work also suggests that 2D pre-training can serve as a strong enhancement for 3D tasks, bridging the data gap between 2D and 3D.

The development of generative artificial intelligence technologies has propelled the visual realism of synthetic images to an unprecedented level. Although current interpretable detection methods based on Large Multimodal Models (LMMs) have made certain progress, they still rely on imitation learning derived from massive volumes of forged data. Consequently, they lack genuine causal reasoning capabilities and are prone to explanatory hallucinations. To overcome this bottleneck, we propose FakeVLM-R1, aiming to endow the model with human-like critical thinking capabilities when performing synthetic detection tasks. Building upon Supervised Fine-Tuning (SFT), this framework integrates Group Relative Policy Optimization (GRPO) with a Critical Thinking Chain-of-Thought (CoT) mechanism. During the inference phase, the model executes a "bidirectional dialectical reasoning" process: while proposing a forgery hypothesis, it must simultaneously invoke physical commonsense to construct an authenticity counter-proof. Furthermore, we constructed the FakeClue++ dataset with high-quality samples, which extensively introduces annotations guided by the physical laws of authentic images, providing a unified authenticity anchor for the model. Experiments confirm that FakeVLM-R1 achieves SOTA performance the evaluated models across multiple benchmarks. It not only achieves high-precision, logically interpretable detection but also resolves the over-rejection bias of existing methods against real images, demonstrating generalization and robustness against perturbations.

Video object removal frequently struggles to simultaneously eliminate target objects and their associated physical effects (e.g., smoke, reflections, light, and ripples) in out-of-domain scenarios due to complex spatiotemporal ambiguities. While existing methods primarily rely on spatial masks, they often fail to capture weakly correlated effects, and the potential of explicit textual guidance remains underexplored. Furthermore, a fundamental optimization conflict exists in removal models between high-level semantic generalization and precise pixel-level background preservation. To address these challenges, we propose GenEraser, a novel framework for generalized and high-fidelity video object and effect removal. First, we introduce a Multi-Conditional Mixture-of-Experts (MC-MoE) paired with Bipartite Text guidance to fully exploit the multimodal priors of Diffusion Transformers, significantly enhancing the identification of complex effects. Second, a Learnable Deep ``CFG'' Fusion mechanism (LD-CFG) is developed to adaptively balance the relative dominance of mask and textual conditions across diverse scenarios. Finally, we propose a Decoupled Expert Architecture, comprising a Locator and a Preserver, to mitigate the inherent trade-off between semantic generalization and pixel alignment. Extensive experiments demonstrate that our GenEraser surpasses recent state-of-the-art approaches, achieving significant quantitative improvements (e.g., $2.16$ dB and $1.44$ dB on the ROSE Benchmark and VOR-Eval, respectively) while maintaining exceptionally robust generalization in open-world scenarios. https://cyqii.github.io/GenEraser.github.io/

Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily depends on reward quality and does not directly address alignment within the diffusion process itself. Recent reward-free approaches such as SoftREPA demonstrate that optimizing soft text tokens via contrastive learning can effectively improve text-image representation alignment, outperforming standard parameter-efficient fine-tuning baselines. However, the contrastive formulation can excessively penalize negative pairs, which manifests as characteristic failure cases such as over-counting and repetition. To address this issue, we propose a lightweight, reward-free post-training method that refines soft tokens by integrating contrastive alignment guidance directly into the score-matching objective of diffusion models. By assigning alignment directions at the score level, our approach mitigates these limitations and yields more coherent and semantically faithful generations. Experiments show that our method matches SoftREPA while substantially improving its failure cases, achieving over 35% improvement in counting accuracy on the GenEval benchmark. Our method is seamlessly applicable to existing diffusion backbones (SD1.5, SDXL, and SD3), and is complementary to existing RL-based diffusion post-training methods. Project page: https://jaayeon.github.io/AGSM

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve high-precision retrieval, they face inherent limitations. First, the coarse-grained nature of dense embeddings tends to obfuscate explicit semantics, failing to leverage structurally salient information. Second, supervised reranking models suffer from generalization bottlenecks, as their performance heavily relies on domain-specific training data. Furthermore, existing benchmarks often lack diverse assessment dimensions and comprehensive relevance annotations, limiting reliable evaluation. To address these challenges, we propose DocRetriever, a plug-and-play framework. It enhances visual retrieval via a layout-aware sparse embedding technique, enabling effective hybrid encoding without the overhead of optical character recognition (OCR). We also introduce a generalizable reranker that leverages reasoning-augmented demonstrations and optimized sampling to improve accuracy in few-shot settings. Finally, we construct a new benchmark, MultiDocR, to enable more rigorous evaluation. Experiments across diverse benchmarks validate DocRetriever's superiority over state-of-the-art methods.

Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with action prediction, while autoregressive text decoding adds too much latency for real-time closed-loop execution. We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency VLA policies. Our bootstrapping philosophy is to guide action with effective visual thinking: VISUALTHINK-VLA bootstraps action prediction through a compact visual-evidence interface that preserves spatial precision while avoiding decoding overhead. Besides, to further improve performance and efficiency, VISUALTHINK-VLA adopts a tailored selective routing mechanism to learn the visual evidence tokens, enabling low-latency inference while preserving high-capacity specialization. We also introduce VisualEvidence-Kit, a supervision-and-audit resource centered on a VisualEvidence-Agent that constructs a 754.7k VLA instructions VisualEvidence-Set for route supervision and counterfactual faithfulness tests. Across multiple benchmarks and real-robot evaluation, VISUALTHINK-VLA achieves the highest success rate on most benchmarks while reducing the multi-second latency of reasoning-augmented baselines to the sub-second regime. For example, on BridgeData V2, it reduces step latency from 8.377,s with ECoT to 0.367,s, achieving a 22.8 times speedup.

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual tokens. Although recent approaches achieve extremely low token retention ratios while maintaining accuracy comparable to full-token baselines, most of them perform compression only at the late stage of prefilling, leaving the efficiency of the vision encoder unoptimized. In this paper, we first show that vision encoding contributes a large portion to the time-to-first-token (TTFT). Therefore, instead of compressing visual tokens only after the vision encoder, performing compression inside the encoder still leaves substantial room for exploration. Based on this insight, we propose EarlyTom, a training-free token compression framework that performs early-stage visual token compression inside the vision encoder, enabling significantly better TTFT reduction and higher throughput. In addition, we introduce a decoupled spatial token selection strategy that improves the overall compression effectiveness. EarlyTom reduces TTFT by up to 2.65x and FLOPs by up to 61% on a single NVIDIA A100 GPU for the LLaVA-OneVision-7B model, while maintaining accuracy comparable to the full-token baseline. These improvements substantially enhance the practicality of deploying Video-LLMs in real-world production scenarios.

We present FRUC, a feed-forward 3D Gaussian splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction frameworks are often hindered by rigid prerequisites, demanding precise spatial calibration and slow per-scene optimization. In this paper, we rethink this task by conceptualizing a distributed multi-vehicle network as a spatio-temporally unstructured ego-centric multi-camera system, where the core challenge lies in enhancing ego-centric occluded geometry through collaboration without degrading the ego's accurately observed visible geometry, while preserving reconstruction efficiency. For efficient reconstruction, FRUC is built upon a visual grounded geometric Transformer backbone to enable one-shot, calibration-free inference from a flexible number of multi-vehicle views. To achieve non-destructive geometric supplementation under uncalibrated cross-agent misalignment, FRUC first introduces an ego-centric causal occlusion field that explicitly derives occlusion evolution as latent priors by modeling agent-wise spatio-temporal correlations. Guided by these occlusion priors, it further formulates cross-agent integration as a deterministic residual denoising process via zero-initialized injection, turning challenging cross-agent fusion into bounded residual learning for robust collaborative blind-spot completion. Through extensive evaluations on the real-world V2XReal and UrbanIng-V2X datasets, FRUC is shown to be a new state-of-the-art for the scene reconstruction of dynamic collaborative driving environments, significantly outperforming existing methods in both rendering quality and efficiency.

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that attribution robustness can arise implicitly from the learning dynamics of standard stochastic gradient descent. We theoretically motivate this effect through connections between parameter-space and input-space curvature, and validate it across architectures, datasets, and attribution methods, with negligible computational overhead. In contrast, we prove that such robustness gains often does not transfer to attention-based attribution under softmax normalization, due to inherent entropy constraints, and we validate this limitation experimentally. Finally, we show that replacing softmax attention with kernel-based attention restores the robustness gains in transformer models. Our results highlight learning dynamics as a principled and practical mechanism for robust explainability, and reveal fundamental limitations of attention-based attribution under normalization.

Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream diagnostic tasks. Hematological cytology is unique in that visual single-cell evaluation is often paired with cytogenetics and molecular genetics for blood cancer diagnosis. In this study, we present a framework to align single white blood cell images with chromosomal aberrations (karyotype) and somatic mutations from targeted gene panels. Our training strategy follows a two-stage approach: (i) self-supervised, vision-only pretraining of a transformer aggregator using an iBOT head on a cohort of over 1500 patients, and (ii) genetic alignment via supervised contrastive loss on acute myeloid leukemia patients. Our genetically aligned patient encoder improves hematological diagnostic tasks, outperforming slide-level histopathology foundation models. Additionally, the model provides off-the-shelf retrieval capabilities for diseases and genetic alterations. Incorporating genetic data into patient encoders increases the quality of patient representations, providing a framework that aligns with clinical diagnostic workflows and paves the way for future multimodal hematology-specific AI. The code and model weights are available at https://github.com/marrlab/GenBloom.

Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. Swin uses local attention to reduce complexity and yields excellent performance for many tasks but still tends to overfit on small datasets. To mitigate this weakness, we propose a novel architecture that further enhances Swin's inductive bias by introducing Inception blocks in the feed-forward layers. The introduction of these multi-branch convolutions enables more direct reasoning over local, multi-scale features within the transformer block. We have also modified the decoder layers in order to capture finer details using fewer parameters. We demonstrate a performance improvement on eleven different medical datasets through extensive experimentation. We specifically showcase advancements over the previous state-of-the-art backbones on benchmark challenges like the Medical Segmentation Decathlon and Beyond the Cranial Vault. By showing that the existing inductive bias in Swin can be further improved, our work presents a promising avenue for enhancing the capabilities of sparse vision transformers for both medical and natural image segmentation tasks. Code and pre-trained weights can be accessed at https://github.com/Eiphodos/SwInception.

Multi-view multi-person 3D pose estimation in team sports scenarios remains challenging due to player occlusions, appearance similarity caused by team uniforms, and the scarcity of annotated multi-view data, all of which limit the effectiveness and generalization capability of learning-based methods. In contrast, the performance of training-free approaches is inherently constrained by the accuracy of 2D keypoint detection and the robustness of cross-view association. To address these challenges, we propose Mesh-Aware Epipolar Matching (MAEM), a training-free framework for multi-view multi-person 3D pose estimation. Our method employs a monocular 3D human mesh recovery model as the frontend and introduces a two-stage epipolar matching strategy based on the recovered mesh outputs. Specifically, the proposed framework combines disjoint-set-union-based clustering with per-joint triangulation to achieve robust cross-view association and accurate 3D pose reconstruction. Experiments on two public multi-view basketball datasets demonstrate that MAEM consistently outperforms existing training-free association baselines while achieving competitive RGB-only performance in both indoor and outdoor basketball scenarios. MAEM achieves MPJPE/PA-MPJPE scores of 59.8/40.7 mm on SportCenter EPFL and 74.0/51.8 mm on Human-M3 Basketball, highlighting the effectiveness of dense mesh geometry for cross-view association without requiring target-domain training or fine-tuning.

Autonomous driving systems are commonly trained and evaluated within limited geographic regions, which hinders their scalability when deployed in new cities. However, significant domain shifts in appearance, road topology, and traffic patterns often cause severe performance degradation under cross-city deployment. Existing approaches based on domain adaptation, data augmentation, or synthetic data generation typically rely on labeled target data, city-specific annotations, or task-specific designs, limiting their scalability and effectiveness for holistic evaluation. In this paper, we introduce CityTransfer-Bench, a geographically disjoint benchmark for evaluating cross-city generalization across perception, segmentation, and planning, and propose CityGen, a diffusion-based generative framework that performs zero-label city adaptation via HD-map-conditioned synthesis guided by city-level visual prompts. Extensive experiments demonstrate that CityGen consistently improves cross-city robustness across multiple tasks, establishing a scalable and label-efficient foundation for generalizable autonomous driving.

Forecasting the progression of neurodegenerative diseases, such as Parkinson's disease, is essential for effective long-term planning and personalized therapeutic intervention. Existing systems typically produce scalar clinical scores that ignore the rich structure of longitudinal neuroimaging, while traditional generative approaches suffer from a loss of anatomical details and blurring subtle progression patterns. To address this, we introduce a novel treatment-conditioned diffusion framework that predicts high-fidelity future brain states by conditioning the generative process on patients' screening DaTscan images and levodopa equivalent daily dose over one year. The pipeline uses a Transformer-based encoder to represent non-linear, time-dependent pharmacological dynamics and optimizes generation through a multi-weight region-of-interest mask that focuses on biologically critical areas. Experimental evaluation shows that our framework maintains sharp anatomical boundaries and significantly improves clinical fidelity relative to the baseline, achieving 14.0% lower MSE, 7.2% lower MAE, and 4.9% higher SSIM.

We propose a machine learning approach for image regression from sparse experimental measurements. We show the application of the proposed method on film cooling studies in propulsion system development, aiming to reduce the need for extensive physical testing. Our method employs a lightweight feed-forward neural network with positional encoding to generate images conditioned by input parameters. Validated on real and synthetic data, it achieves high image similarity (RMSE < 8 %, SSIM > 93 %) while maintaining accuracy with a 30 \% reduction of measurements. We further propose a knowledge-informed extension for local adaptability of the generated images. This approach significantly reduces required tests while preserving high-quality data, enabling efficient optimization of coolant injector configurations with applications beyond aerospace.

Recent progress in computer vision has produced a wide range of powerful specialized models for detection, segmentation, counting, and other visual tasks. However, these models are usually optimized for isolated task formulations, making it difficult to directly support general-purpose visual intelligence, especially when a task requires complex language understanding and dense small-object perception. In this paper, we propose VisHarness, a trainable visual agent that decouples high-level perception, reasoning, and decision-making from low-level task execution. Instead of training a model to solve a specific visual task, VisHarness learns to harness a set of carefully designed heterogeneous visual experts. This paradigm preserves the general intelligence of the agent while fully leveraging the precision advantages of specialized visual models in concrete visual tasks. With only lightweight training, VisHarness learns a generalizable visual expert-harnessing policy and can solve common fundamental vision tasks under various complex conditions through multi-turn interactions with visual expert models. To enable efficient on-policy reinforcement learning training in a live environment, we introduce dynamic visual memory archiving, which mitigates the rapidly accumulating visual-token overhead caused by multi-turn interactions with visual expert models. Experiments on four representative benchmarks covering reasoning segmentation, generalized referring segmentation, dense small-object detection, and referring counting demonstrate that VisHarness substantially outperforms existing general-purpose models and achieves competitive or superior performance compared with task-specific models.

Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks. We re-examine this design. Through controlled experiments, we show that a decoder-only architecture, which represents scenes implicitly as a KV-cache, outperforms encoder-decoder variants while using fewer parameters at identical rendering complexity. Further analysis shows that sharing weights between the color-input reconstruction network and the camera-only rendering network better aligns their features at the same viewpoint, facilitating image synthesis. Building on this finding, our model, dubbed DVSM, further incorporates foundation model priors and stage-wise patch sizing for an improved efficiency-quality tradeoff. Our results establish a new state of the art for novel-view synthesis across multiple benchmarks, in some cases even outperforming per-scene-optimized 3DGS under dense input views.

Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden states throughout generation, but they suffer from three key limitations: they lack an explicit grounding objective, intervene even when the model is already well-grounded, and use fixed correction strengths that do not adapt to the severity of grounding failure. We propose BRACS (Barrier-Regulated Adaptive Closed-form Steering), a training-free steering framework that addresses these issues through barrier-regulated adaptive closed-form steering. BRACS monitors the model's own attention to measure visual grounding and applies corrections to the hidden states only when grounding deteriorates. The corrective update is computed analytically in closed form, requiring no training of auxiliary networks or model retraining. Experiments on LLaVA-1.5-7B and Qwen-VL-Chat show that BRACS consistently outperforms prior methods on hallucination benchmarks, reducing CHAIR$_s$ by 9.4 points and improving POPE F1 by 2.7 points, while matching or improving performance on four general multimodal benchmarks. BRACS also remains efficient, operating at 80% of greedy decoding throughput and achieving 1.3 times higher speed on average than the baselines.

Centralised biometric identity systems expose users to single points of failure, opaque verification processes, and irreversible biometric compromise. Decentralised Identifiers (DIDs) and Verifiable Credentials (VCs) offer stronger privacy guarantees, yet their integration with biometric authentication and distributed verification remains insufficiently explored. This paper presents Ciphera, a decentralised biometric identity framework combining privacy-preserving facial recognition, multi-node verification, IPFS-based credential metadata storage, and blockchain-anchored revocation. Evaluated across functional, performance, security, and distributed consistency dimensions, Ciphera achieved an 81% functional success rate, with stable enrolment and authentication but measurable revocation propagation delays and occasional audit-log inconsistencies. Performance testing demonstrated sub-second p95 verification latency of approximately 820ms under concurrent multi-node conditions. Security analysis confirmed strong confidentiality and integrity guarantees, though incomplete liveness detection leaves susceptibility to deepfake and replay attacks. The results demonstrate the feasibility of decentralised biometric identity while identifying key engineering challenges for production-grade deployment.

Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Recent vision-language formulations improve semantic reasoning and support language-conditioned outputs, but their autoregressive decoders still generate tokens from left to right, preventing later semantic evidence from revising earlier timestamp predictions. We adapt masked diffusion vision-language models (MDVLMs) to TAL so that semantic tokens and boundary tokens remain editable throughout iterative denoising with bidirectional attention, allowing temporal boundaries and semantic content to be refined jointly. Direct adaptation, however, creates two TAL-specific mismatches: standard masked diffusion training corrupts all positions uniformly at random, but the time tokens are more reliable when enough semantic context is available; and token-level cross-entropy does not reflect temporal IoU. To address these mismatches, we introduce a Planned Training Objective that uses boundary-aware masking and step-weighted reconstruction to rehearse the late recovery of time tokens, together with a Step-Level IoU Reward that provides overlap-aware supervision during denoising. A standard sequence-level cross-entropy term provides the base reconstruction signal. Experiments on ActivityNet-RTL, ActivityNet-1.3, and THUMOS-14 show that MDVLM-TAL improves both temporal reasoning and boundary localization over autoregressive vision-language baselines, with especially strong gains under stricter temporal IoU criteria.

As a widespread form of informal settlements, urban villages present significant challenges for sustainable urban development and governance. Precise mapping of their infrastructure is essential, however, existing remote sensing datasets primarily focus on formal urban environments, lacking fine-grained annotated data for the high-density building patterns and narrow road networks typical of urban villages. To address this gap, we introduce the \textit{DenseUIS} dataset, the first high-resolution remote sensing dataset specifically designed for building and road extraction in extremely dense urban informal settlements, covering 126 urban villages across Shenzhen and Guangzhou in China. Furthermore, we conduct a comprehensive evaluation of state-of-the-art deep learning models on this dataset. Experimental results reveal the limitations of existing methods in handling the unique morphological patterns of dense informal settlements, underscoring the need for specialized approaches. \textit{DenseUIS} therefore provides a robust benchmark for advancing fine-grained urban mapping in complex and high-density informal environments. The dataset is publicly available at https://github.com/rui-research/DenseUIS.

Medical image analysis models can exhibit performance disparities across patient subgroups, threatening clinical safety and fairness. Existing methods typically address this issue by optimizing accuracy and fairness metrics for visible demographic attributes (e.g., sex or age) considered in isolation. This strategy not only overlooks potentially more informative latent stratifications, which may reveal deeper sources of model error and inequity, but also fails to scale when multiple demographic attributes are considered simultaneously due to the resulting sparsity of training data within each subgroup. We deal with these issues by introducing the label-free hidden-cohort fairness (LHCF) training paradigm that instead of maximizing fairness over visible demographic attributes, it optimizes fairness across latent subpopulations discovered from image appearance. By clustering images into K appearance-based cohorts and applying fairness optimization over them, LHCF uncovers underlying sources of model error and avoids the combinatorial sparsity of multi-demographic attributes, reducing disparities across both single and multiple demographic attributes. We demonstrate on our proposed fairness benchmark, HIDFairBench, that LHCF provides state-of-the-art fairness results on single and multiple demographic attributes, despite never using demographic labels for training. Our results position hidden-cohort fairness as a practical, scalable, and robust alternative to demographic-based fairness optimization for trustworthy medical image analysis.

Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video. Although recent works have made remarkable progress in this task, they implicitly are rooted in the closed-set assumption that all the given queries as video-relevant\footnote{In this paper, we treat ``video-relevant query'' as ``in-distribution (ID) query'' and ``video-irrelevant query'' as ``out-of-distribution (OOD) query''.}. Given an OOD query in open-set scenarios, they still utilize it for wrong retrieval, which might lead to irrecoverable losses in high-risk scenarios, \textit{e.g.}, criminal activity detection. To this end, we creatively explore a brand-new VMR setting termed Open-Set Video Moment Retrieval (OS-VMR), where we should not only retrieve the precise moments based on ID query, but also reject OOD queries. In this paper, we make the first attempt to step toward OS-VMR and propose a novel model \textbf{OpenVMR}, which first distinguishes ID and OOD queries based on the normalizing flow technology, and then conducts moment retrieval based on ID queries. Specifically, we first learn the ID distribution by constructing a normalizing flow, and assume the ID query distribution obeys the multi-variate Gaussian distribution. Then, we introduce an uncertainty score to search the ID-OOD separating boundary. After that, we refine the ID-OOD boundary by pulling together ID query features. Besides, video-query matching and frame-query matching are designed for coarse-grained and fine-grained cross-modal interaction, respectively. Finally, a positive-unlabeled learning module is introduced for moment retrieval. Experimental results on three VMR datasets show the effectiveness of our OpenVMR.

Large-scale text-to-image (T2I) diffusion models have enabled unprecedented creative applications, but their unauthorized use has raised serious intellectual property concerns, making model ownership verification (MOV) increasingly critical. We find that existing backdoor-based diffusion watermarking methods often (implicitly) assume a "faithful" verification process, namely, that the verifier can query a suspicious model and obtain the faithful watermark response to complete MOV. However, in practice, adversaries may intentionally or unintentionally damage potential watermark signals, significantly degrading verification reliability. To address this issue, we propose Cert-LAS, the first certified MOV method for T2I models based on layer-adaptive smoothing. In general, Cert-LAS embeds specified watermarks using diffusion classifiers and an LFS-guided layer-adaptive noise, and verifies ownership by examining whether the suspected model exhibits significantly stronger watermark responses compared to unwatermarked references through hypothesis testing. We further prove that, under certain conditions, our Cert-LAS can still achieve reliable verification even in the presence of malicious removal attacks. Extensive experiments validate the effectiveness of Cert-LAS and its resistance to adaptive attacks. Our code is available at https://github.com/Leyi-Qi/Cert-LAS.

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex and OpenClaw execution scenarios. We further build a taxonomy-guided data engine with influence-function purification to train lightweight AgentDoG 1.5 variants (0.8B, 2B, 4B, and 8B parameters) using only around 1k samples, achieving comparable performance with leading closed-source models (e.g., GPT-5.4). Based on AgentDoG 1.5, we construct a highly efficient agentic safety SFT and RL training environment, which reduces deployment overhead in Docker-level environments by two orders of magnitude. Finally, we deploy AgentDoG 1.5 as a training-free online guardrail for real-time safety moderation. Extensive experimental results indicate that AgentDoG 1.5 achieves state-of-the-art performance in diverse and complex interactive agentic scenarios. All models and datasets are openly released.

Reliable identification of fracture origins in alumina matrix composite hip and knee implants is critical for quality assurance and patient safety, yet current fractographic workflows are time-consuming, partly subjective, and reliant on high-magnification scanning electron microscopy (SEM). We present an interpretable vision-transformer (ViT) workflow for automated classification of fracture causes in an alumina matrix composite (BIOLOX delta, CeramTec GmbH) widely used in total joint replacements. A dataset of 8,493 SEM images (50x-10,000x) was curated from five years of in-production burst and proof tests and annotated into three defect categories defined along the manufacturing chain: green body, hard machining, and material defects. Under severe class imbalance, the fine-tuned ViT reached an accuracy of 0.907 and a macro-F1 of 0.888 in stratified five-fold cross-validation, with a two-stage perceptual-hash/SSIM leakage audit confirming negligible specimen overlap. Notably, performance at low magnification (50x) was comparable to that at high magnification (1k-10kx), indicating that macro-scale features - mirror geometry and hackle line fields - already encode sufficient diagnostic signal. Grad-CAM attributions consistently localised on canonical fractographic cues (mirrors, hackles, pores, machining marks), aligning with established fractographic criteria. Together, these results position interpretable ViTs as a complementary tool for ceramic-implant quality assurance, enabling low-magnification pre-screening and reducing reliance on time-intensive high-magnification inspection.

Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untrimmed video is overlong, almost all existing VMR methods first sparsely down-sample each untrimmed video into multiple fixed-length video clips and then conduct multi-modal interactions with the query feature and expensive clip features for reasoning, which is infeasible for long real-world videos that span hours. Since the video is downsampled into fixed-length clips, some query-related frames may be filtered out, which will blur the specific boundary of the target moment, take the adjacent irrelevant frames as new boundaries, easily leading to cross-modal misalignment and introducing both boundary-bias and reasoning-bias. To this end, in this paper, we propose an efficient approach, SpotVMR, to trim the query-relevant clip. Besides, our proposed SpotVMR can serve as plug-and-play module, which achieves efficiency for state-of-the-art VMR methods while maintaining good retrieval performance. Especially, we first design a novel clip search model that learns to identify promising video regions to search conditioned on the language query. Then, we introduce a set of low-cost semantic indexing features to capture the context of objects and interactions that suggest where to search the query-relevant moment. Also, the distillation loss is utilized to address the optimization issues arising from end-to-end joint training of the clip selector and VMR model. Extensive experiments on three challenging datasets demonstrate its effectiveness.

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL). In this paper, we focus on the target-domain few-shot finetuning in the CLIP-based CDFSL task. Prevailing finetuning paradigms uniformly align all image patch tokens with their corresponding textual embeddings. However, we find a counterintuitive phenomenon: actively pushing away certain low-similarity image tokens, termed "tail tokens", from their textual embeddings consistently improves target-domain performance. We delve into this phenomenon and provide a novel interpretation: under great domain shifts and scarce training data, the model can hardly extract semantic information from visual inputs; therefore, the common belief of alignment is valid only for tokens already containing sufficient semantic information; for tail tokens, forcing the alignment would lead to excessive overfitting to the scarce training, while breaking the alignment is more useful. Motivated by this, we propose Adaptive Tail-Head Alignment (ATHA), a novel fine-tuning strategy for CLIP that transforms the conventional uniform alignment paradigm to an adaptive alignment paradigm, with both alignment strengthening and weakening. Extensive experiments on four challenging CDFSL benchmarks validate our state-of-the-art performance. Our code is available at https://github.com/shuaiyi308/ATHA.

Reliable semantic segmentation for mobile robots requires both accurate dense prediction and robust uncertainty estimation under distribution shift. Strong uncertainty baselines such as Monte Carlo Dropout often require repeated stochastic forward passes and are difficult to deploy on edge platforms. We propose Energy-Aware NECO, a single-pass pixel-wise out-of-distribution (OOD) detector for semantic segmentation. The method combines a centered NECO-style geometric ratio computed from decoder features with a logit-based Energy score. Both components are standardized using statistics fitted on a pure in-distribution validation split and fused through a convex combination. We evaluate the method on the miniMUAD subset using true pixel-level OOD labels. The proposed hybrid score achieves an AUROC of 0.8539, outperforming NECO-only (0.8280), Energy-only (0.8171), and an ensemble predictive-entropy baseline (0.8124). Additional qualitative and operating-point analyses show that the hybrid detector improves overall ranking performance while preserving the efficiency advantages of a single-pass design. Code is available at https://github.com/boyuan-zhangx/Energy-Aware_NECO

Video Motion Magnification (VMM) reveals imperceptible dynamics but often suffers from structural inconsistencies under complex geometric transformations. Existing learning-based methods generally face a trade-off between the limited global context of CNNs and the high computational cost of Transformers. In addition, current training protocols, largely dominated by simple linear motion, fail to capture the geometric and imaging complexities encountered in real-world videos. To address these issues, we propose GeoMag, a geometric-aware VMM framework built upon State Space Models to achieve globally consistent motion amplification with linear complexity. We further construct Geo-200K, a large-scale synthetic dataset that introduces rich geometric transformations together with sensor-realistic degradations, improving the diversity and realism of training signals. Extensive experiments on synthetic and real-world benchmarks show that GeoMag consistently outperforms prior methods in visual fidelity and computational efficiency, while producing fewer artifacts and better structural consistency.

Compositional implicit surface representations model scenes as collections of objects, each encoded by a Signed Distance Field (SDF). A fundamental limitation of this approach is that multiple SDFs can produce geometries that interpenetrate, violating physical plausibility. Existing mitigation strategies rely on soft penalty terms that reduce but do not eliminate intersections, and require careful loss weighting. To truly prevent interpenetration, we propose a hard constraint on vector-valued SDFs and introduce S2MDF, a lightweight plug-and-play module that enforces the constraint on any object-compositional SDF representation without architectural modifications. It introduces negligible computational overhead and is compatible with linearly-interpolated standard meshing algorithms such as Marching Cubes. It can be applied during training or as a post-processing step. Experiments on multiple state-of-the-art compositional methods show that S2MDF reduces intersections to numerical precision while preserving reconstruction quality, outperforming existing mitigation strategies.

In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become increasingly popular. This has recently motivated the emerging setting of task-specific distillation, where a larger and a smaller version of the same foundation model are both adapted to the same downstream task, with the goal of transferring knowledge from the former to the latter. Recent work has demonstrated the benefits of using a larger version of the same foundation model to assist the adaptation of a smaller one. Typically, the larger model (teacher) is first adapted via fine-tuning or linear probing before its knowledge is distilled into the smaller model (student). While fine-tuning the teacher often increases its performance, recent work showed that probing it leads to better knowledge distillation to the student. Our findings show that this is mainly due to a mis-alignment in feature representation between the teacher and the student which occurs during the teacher's fine-tuning. Inspired by existing efforts to preserve previously learned knowledge, we first propose leveraging low-rank adaptation, resulting in better feature alignment and therefore better knowledge transfer. Drawing from this insight, we further enhance the feature alignment through a parameter-sharing strategy of the adapters between the two encoders during joint training. Our proposed method, SLAD, shows better feature alignment between the teacher and student, which results in increased performance for not only the student but also the teacher model, while being 2x faster to train than fine-tuning. Through extensive experiments on multiple classification and segmentation datasets, we demonstrate the improved accuracy and transfer efficiency of our method, achieving state-of-the-art performance in the task-specific distillation framework.

We propose Intrinsic Quality (IQ), a validation-free metric designed to estimate the inherent potential of face recognition (FR) datasets to produce high-performance models without the need for full-scale training. IQ integrates two components: (i) a Neighbor-Consistency Score that quantifies local identity label agreement via nearest neighbors, and (ii) Global Representation Subspace Complexity (Effective Rank, ER), which captures the underlying embedding geometry and dataset diversity. IQ allows for rapid evaluation using lightweight proxy models or data subsets, facilitating dataset diagnosis and curation prior to resource-intensive full-scale training. We describe an experimental protocol tailored to clean, noisy, and mixed-quality FR datasets, and outline evaluation methodologies to validate IQ's predictive power for downstream performance.

The study of brain morphology changes in normal individuals may capture aspects of functionally-relevant brain aging not fully indicated by gross volumetry. Despite the important role of subcortical brain structures in cognition, the associations between their morphological trajectories and cognitive changes in aging have not been documented. We use neuroimaging, demographic, and cognitive data from a large longitudinal study of cognitive aging, the Lothian Birth Cohort 1936, to explore shape changes in subcortical brain structures of community-dwelling individuals across their 8th decade of life. We investigate the association of these changes with cognitive aging using ANCOVA and mixed linear model analyses. Subcortical shape changes were heterogeneous, with varied atrophy patterns across whole period. The hippocampus and the ventral DC experienced varied morphological deformations (from its baseline point) different in left and right hemispheres, while the thalami and globus pallidi shapes, for example, experienced a more uniform volume contraction, nearly symmetrical throughout different timelines. Changes in general cognition were mainly associated with inwards and outwards vertex displacements between the time-points.

Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs) whose pretrained representations support a wide range of downstream tasks. Towards a better understanding of these models, a body of work has assessed the mechanics of their self-attention as well as the types of information captured across their representations, revealing, for example, stark differences between models trained with contrastive learning (CL) and masked image modeling (MIM). However, these advances in model understanding have not yet fully permeated the broader community, where insights specific to CL models are sometimes generalized to MIM models. To make model understanding straightforward and intuitive for a broad audience, we propose a simple and easily interpretable visualization protocol. Our protocol is based on visualizing unsupervised semantic segmentation results, yet our goal is not to maximize segmentation performance. Instead, it allows us to convey model behaviors that consistently emerge across images. Benchmarking a diverse set of SSL models across layers and representations, we obtain novel insights into distinct positional biases and scaling behaviors, including strong boundary artifacts in DINOv3-Large model tokens. These insights complement and help communicate a range of previous findings. Our protocol further enables a clear visual distinction between positional effects and the closely related but distinct locality bias, which has been studied much more extensively in the literature. The protocol is publicly available on GitHub and we believe it will catalyze further model understanding for a broad community.

Reconstruction-based inference assigns a class by comparing class-wise reconstruction residuals; Sparse Representation Classification (SRC) is a canonical instance whose reliability depends on the geometry of the learned representation. We adopt a strict training-inference separation: SRC is used only as a fixed test-time rule and is never differentiated, unrolled, or optimized during training. In a span-level idealization based on class-conditional spans and their associated projection residuals, we formalize residual-ordering stability through a residual margin and characterize geometric obstructions -- span overlap, dominance, and near-overlap via small principal angles -- that can collapse this margin in worst-case directions. This span-level theory is primary: it specifies when the idealized residual family is well-separated, and it provides a conditional solver-level interpretation for practical residual approximations (e.g., OMP) insofar as they remain close to the span-level residual ordering. Under explicit coverage and separation assumptions, we derive a quantitative lower bound on the (idealized) residual margin. Guided by these targets, we propose geometry-shaping objectives that promote masked within-class self-expressiveness, discourage cross-class reconstruction pathways and inter-class span alignment, and prevent collapse -- without invoking SRC residuals or predictions during training. Experiments on images (COIL-100), text (TREC), and EEG connectivity evaluate all representations under identical fixed SRC/OMP inference and report residual margins and geometric diagnostics; cross-entropy is included only as a reference geometry under the same evaluation protocol.

Vision-language models (VLMs) rely on long visual token sequences for visual understanding, making the prefill stage expensive in both computation and memory. Most existing pruning methods follow an absolute-ranking paradigm, assigning importance scores to visual tokens and retaining a fixed top-K subset. In this work, we argue that this paradigm is fundamentally brittle: attention sinks distort token importance rankings, while image redundancy and query-dependent visual evidence make fixed token budgets unreliable across inputs. We propose OccamToken, a training-free framework that replaces absolute token ranking with register-anchored relative evidence testing. Instead of asking which tokens are globally important, OccamToken evaluates whether a visual token provides information beyond a register-based reference. Our key insight is that register tokens naturally absorb low-information attention patterns, making them a stable reference for identifying genuinely informative visual evidence. Based on this principle, OccamToken performs both image-adaptive redundancy pruning and query-adaptive relevance pruning through dynamic thresholds derived from register attention. Across LLaVA-NeXT, LLaVA-v1.5, and Qwen3-VL, OccamToken consistently improves the accuracy-efficiency trade-off without additional training. Notably, on LLaVA-NeXT, it reduces 2,880 visual tokens to approximately 40 while preserving over 93% of the original accuracy, enabling stable visual token compression even in the extreme 1.4% retention regime.

Aerial navigation on Mars requires vision-based pipelines that are robust to the diverse illumination conditions and terrain morphology of the Martian surface. A key bottleneck for training and evaluating such methods is the scarcity of large-scale, annotated aerial datasets. We present MARTIAN, an open-source Blender-based rendering framework that leverages real HiRISE orbital map products to synthesize realistic aerial views of the Martian terrain under controllable lighting conditions and at varying altitudes. MARTIAN generates observations with accurate pose annotations, directly addressing the scarcity of training data for vision-based navigation on Mars. The framework has been validated through its deployment in concurrent work on map-based localization systems for Ingenuity and future Mars rotorcraft, where synthetically trained deep image matchers were successfully evaluated on real Mars imagery. MARTIAN is publicly available at: https://github.com/nasa-jpl/martian.

Cross-Video Reasoning (CVR) has emerged as a critical frontier in multimodal intelligence, requiring models to retrieve, align, and aggregate evidence distributed across multiple videos. Current Multimodal Large Language Models (MLLMs) often struggle with CVR, as simple single-pass strategies encode multiple videos into a shared compressed context, potentially obscuring rare but critical evidence. In this paper, we propose AgentCVR, a multi-agent framework that treats CVR as an active evidence-acquisition task. AgentCVR employs a Master Agent to iteratively coordinate specialized Visual and Audio Agents for targeted evidence extraction. To ensure efficient training, we introduce Script-Simulated RL, which optimizes the agent's policy with LLM-generated semantic scripts and a lightweight text-based simulator, bypassing costly multimodal inference during online exploration. Experimental results on a comprehensive CVR benchmark show that AgentCVR outperforms single-pass baselines and achieves comparable performance to state-of-the-art closed-source systems, particularly in complex cross-video alignment and localization. To ensure reproducibility, our code is available at https://github.com/wang-jh24/AgentCVR.

Vision-language models (VLMs) have made strong progress on high-level image-text alignment, yet their ability to perceive subtle visual differences remains limited. We study this problem in rendered web interfaces, where localized visual changes are both a diagnostic test of fine-grained perception and a practical requirement for GUI agents and design tools. We introduce \textbf{DiffSpot}, a code-driven benchmark for open-ended spot-the-difference on web interfaces. DiffSpot constructs controlled image pairs by mutating a single CSS property of a target element in self-contained HTML, re-rendering the page, and recording the changed property, element, and mutation magnitude. A grounding gate retains only pairs whose rendered pixel difference is confined to the target element. The benchmark contains 4{,}400 pairs, including 3{,}900 has-diff pairs balanced across 13 CSS-property operators and three difficulty tiers, plus 500 no-diff pairs for hallucination control. Evaluating 13 frontier VLMs zero-shot, we find that even the best model identifies only $40.7\%$ of true changes, with Hard-tier Recall below $23\%$ for every model. DiffSpot further shows that difficulty is strongly property-dependent: across CSS operators, neither pixel magnitude nor CLIP distance reliably predicts Recall.

In scene graph generation, a central challenge is modeling polysemous predicates whose meanings shift across contexts. Prior approaches address this issue by decomposing predicates into multiple static prototypes or retrieving semantically similar exemplars. However, these strategies keep predicate representations static and cannot reorganize semantics to reflect image-specific evidence, leading to systematic confusions in ambiguous contexts. We propose AlignG, which learns context-conditioned predicate semantics via prototype feedback. AlignG infers context-conditioned predicate semantics from the relation candidates within each image and feeds the adapted semantics back to recalibrate relation representations. The learning objective anchors this adaptation to global semantic centers, preventing semantic drift while still allowing selective reorganization when the scene provides consistent relational cues. Experiments on VG-150 and GQA-200 show consistent improvements over state-of-the-art baselines, with F@100 improvements of +1.4 on VG-150 and +2.7 on GQA-200 under SGDet. We further visualize per-image prototype similarity shifts and observe coherent context-dependent reorganization where prototypes selectively merge or separate predicates according to scene evidence. The code is available at https://github.com/Namgyu97/AlignG-SGG.pytorch.

Multi-modal Retrieval-Augmented Generation (MMRAG) has emerged as a powerful paradigm for enhancing Multimodal Large Language Models in knowledge-intensive question answering by integrating external visual, textual, and structural knowledge. However, existing MMRAG frameworks suffer from critical limitations, including noisy and irrelevant retrieval, cross-modal semantic misalignment, lack of adaptive reasoning, and incoherent generation across local and global contexts. We introduce \textbf{CogniVerse}, a novel MMRAG framework that addresses these challenges through a cognitive-inspired, mathematically rigorous approach. Drawing from human-like reasoning, CogniVerse integrates three synergistic components: (1) a Cognitive Reflection Module that dynamically assesses retrieval necessity and filters relevant multi-modal content, reducing noise and computational overhead; (2) a Multi-modal Retrieval Module that aligns embeddings in a Riemannian manifold using information geometry and refines knowledge graphs via spectral graph theory, ensuring precise and coherent retrieval; and (3) a Hierarchical Generation Module that employs an optimal transport-based loss to balance token-level accuracy and global semantic coherence. Extensive experiments demonstrate that CogniVerse significantly outperforms state-of-the-art systems in both accuracy and coherence, while reducing retrieval latency.

Semantic segmentation is crucial for autonomous navigation in off-road environments, enabling precise classification of surroundings to identify traversable regions. However, distinctive factors inherent to off-road conditions, such as source-target domain discrepancies and sensor corruption from rough terrain, can result in distribution shifts that alter the data differently from the trained conditions. This often leads to inaccurate semantic label predictions and subsequent failures in navigation tasks. To address this, we propose ST-Seg, a novel framework that expands the source distribution through style expansion (SE) and texture regularization (TR). Unlike prior methods that implicitly apply generalization within a fixed source distribution, ST-Seg offers an intuitive approach for distribution shift. Specifically, SE broadens domain coverage by generating diverse realistic styles, augmenting the limited style information of the source domain. TR stabilizes local texture representation affected by style-augmented learning through a deep texture manifold. Experiments across various distribution-shifted target domains demonstrate the effectiveness of ST-Seg, with substantial improvements over existing methods. These results highlight the robustness of ST-Seg, enhancing the real-world applicability of semantic segmentation for off-road navigation.

Class-Incremental Learning (CIL) with pre-trained models (PTMs) aims to sequentially adapt PTMs to new categories without forgetting old knowledge. Built upon PTMs, existing adapter-based methods mainly train models via distinct task-specific adapters, and present a uniform knowledge allocation for each adapter during inference. However, this allocation mechanism ignores the nature of task discrepancy and leads to suboptimal utilization of adapters. Also, under CIL constraint, an allocator is prone to forgetting when tasks evolve. To address these issues, we propose a Non-Forgetting Allocation with Bi-Level Competition (NoFA-BC). NoFA-BC constructs a non-forgetting allocator (NFA) by transforming the allocator training into a recursive least-squares problem and achieves an allocator equivalent to that trained with all data. Based on the NFA, a Bi-Level Competition (BLC) including an intra-task level Winner-Takes-All (WTA) mechanism and inter-task Last-Ones-Fall (LOF) elimination is proposed to provide better allocation of adapter knowledge. WTA extracts the most significant logit within a task to represent the adapter's contribution and LOF suppresses the irrelevant adapters. With BLC, participation ratio of each adapter can be tailored for each input. Moreover, a Stability Enhancement (SE) process is incorporated to further improve the performance of old tasks.

High-capacity watermarking is necessary for 3D Gaussian Splatting (3DGS) assets to embed rich information (e.g., ownership, provenance, and authentication codes), enabling reliable identification and integrity verification in large-scale 3D asset pipelines. Existing bit-to-token watermarking methods based on a pre-trained text encoder are limited to 77-bit messages due to CLIP's fixed 77-token context length, as tokens beyond this limit are unsupported by learned positional embeddings. To address this limitation, we introduce BitC-3DGS, a bit-compression framework that encodes multiple message bits per token. It employs a bit-compressed tokenization scheme that encodes multiple bits within the same chunk into a single semantic token. To enable recovery of the compressed information, it further introduces a dual-branch architecture for joint chunk decompression and bit decoding, along with a hard-message sampling strategy to improve combinatorial coverage during decoder training. Extensive experiments on the Blender and LLFF datasets demonstrate the effectiveness of BitC-3DGS for high-capacity watermarking, achieving high message recovery accuracy and rendering fidelity. For example, it supports 128-bit message capacity with recovery accuracy comparable to that of 64-bit messages in recent state-of-the-art methods.

Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Yet existing adaptive tokenizers either require post-hoc search or select among a discrete set of pre-trained rates, rather than learning a continuous per-image sequence length coupled to the model and scene, and they typically train against pixel reconstruction, emphasizing texture rather than structure. We propose STROP, a discrete visual tokenizer architecture that forms structural scene representations and simultaneously learns how long an image's visual program should be. Using a four-phase curriculum supervised by local rate--distortion probes against frozen DINOv3 features, STROP optimizes a dedicated length head that estimates the active prefix length in a single forward pass. By bypassing pixel-level reconstruction gradients, the codebook is shaped entirely by the quality of higher-level latent representations. Program length grows with scene complexity, and signs of compositional structure emerge both in downstream dense-prediction transfer and in direct inspection of the learned code vocabulary.

We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv:2510.03434), the first ever open-weight Decentralized Diffusion Model (DDM), which showed that image generation can be trained without a monolithic GPU cluster. However, temporally coherent video generation had remained an open problem under decentralized training, and Paris 2.0 closes it. In low-resolution text-to-video training, against a monolithic model trained on the same data under a matched total compute budget, Paris 2.0 cuts Frechet Video Distance (FVD) from 561.04 to 279.01, a ~2.0x improvement, and lifts CLIP text-video similarity and aesthetic score.

Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on 3D Gaussian splatting (3DGS), support relighting; however, they usually require dense input views, and their overfitting nature makes it difficult to generalize across scenes. Unlike per-scene optimization methods, generalized feed-forward models can directly reconstruct Gaussians from sparse input views. However, the resulting assets have baked-in illumination and cannot be easily used for relighting. In this paper, we present F-RNG, a feed-forward framework that directly generates relightable 3DGS assets from sparse-view inputs. Training such a model from scratch can require massive data and computing resources, and it is especially challenging to generate relightable assets in a feed-forward manner with acceptable cost. We develop F-RNG upon an existing large reconstruction model (LRM) to extract relightable representations, while also utilizing priors from an intrinsic decomposition model (IDM). Specifically, we first introduce a latent-interpolated fine-grained geometry synthesis to enhance the LRM's geometry representation. Second, we propose a prior-guided relightable appearance distillation to extract relightable neural representations by incorporating IDM priors. Finally, a universal neural renderer enables flexible and high-fidelity relighting. F-RNG requires neither re-training nor fine-tuning of the underlying LRMs, thus can automatically benefit from better LRMs and IDMs in the future. With only small networks that can be trained with affordable data and computational resources, F-RNG avoids the repetitive inference of large models under different light conditions. By comparison to the state-of-the-art LRM-based relighting method, F-RNG achieves ~25x faster relighting, as well as superior quality (~+2.0 dB).

Human egocentric video captures rich manipulation demonstrations without any robot hardware, yet transferring these skills to robots remains challenging due to the embodiment gap between human and robot in both visual appearance and kinematics. We present HumanEgo, a framework that bridges the embodiment gap by lifting each human demonstration to an entity-level representation of hand-object interaction, and training a flow matching policy with dense auxiliary objectives that amplify supervision from every trajectory. HumanEgo is robot-data-free, hardware-agnostic, data-efficient, and zero-shot human-to-robot transferable. With only 30 minutes of human videos per task, HumanEgo achieves 92.5% average success across four real-world tasks (75% with just 15 minutes), outperforms matched-time robot teleoperation by 41%, and robustly transfers zero-shot across novel robots, cameras, and environments. We release HumanEgo as an easy-to-use, open-source framework for learning robot policies directly from human data: https://github.com/TX-Leo/HumanEgo

Automatically mapping and segmenting global mining footprints using remote sensing and deep learning is critical for monitoring the socio-environmental risks and impacts of mining, yet its progress is hindered by the scarcity of fine-grained annotated data. Although large-scale datasets with coarse boundaries are widely available, leveraging them to improve fine-grained segmentation is challenging due to significant domain shift. To address this, we propose MineC2FNet, a coarse-to-fine domain incremental learning framework that exploits abundant coarse data to enhance fine-grained mining footprint segmentation. MineC2FNet adopts a teacher-student architecture with attentive distillation at both the feature and prediction levels, selectively transferring generalized knowledge from the coarse domain while enabling boundary refinement using limited fine-grained data (fine domain). We further introduce an expertly validated dataset of 219 images with precise boundary annotations across diverse geographies and commodities. Extensive experiments against state-of-the-art approaches, including domain adaptation and domain incremental learning methods, demonstrate that MineC2FNet achieves superior performance while effectively handling domain shift. The dataset and code are publicly available at https://github.com/risqiutama/MineC2FNet.

The digitization of musical scores plays a crucial role in their preservation and accessibility, yet information retrieval still depends mainly on metadata searches, such as by title or composer. Content based search in music score images remains underexplored compared to text documents, despite its potential value for musicians, musicologists, and educators. This work contributes to the field by first studying which characteristics of a score are most relevant for search and by defining a systematic method to build query datasets from any annotated corpus. We also consider diverse methods for content-based search on music score images, ranging from transcription-based approaches relying on Optical Music Recognition (OMR), to a transcription-free Transformer model trained to recognize queries directly from score images, and a text-prompted Large Language Model. Our experiments evaluate these models on four corpora exhibiting diverse characteristics in terms of dataset size, image quality, and typesetting mechanisms. Overall, each method excels under different conditions: OMR-based pipelines achieve higher in-domain retrieval, whereas transcription-free models handle domain variability more effectively.

Recent advances in garment simulation have brought high-quality results closer to real-time performance. Physics-based simulators can produce accurate motion, but remain too computationally expensive for interactive applications. In contrast, linear blend skinning is efficient, but cannot capture the complex dynamics of loose-fitting garments, often leading to unrealistic motion and visual artifacts. Neural methods offer a promising alternative, yet they still struggle to animate loose clothing plausibly under strict runtime constraints. We present a fast and physically plausible approach for dynamic garment simulation. Our method trains a reduced-space neural dynamics simulator composed of independent coarse- and fine-level components. At the coarse level, the garment is driven by a set of virtual bones integrated with a lightweight neural network. Fine-scale wrinkle details are then recovered using a trained convolutional neural map. By decoupling identity-specific computation from real-time neural integration, our architecture maintains high performance while supporting diverse body shapes and motions. We further introduce an effective physics-supervision scheme that enables accurate results without relying on an external simulator. Experiments show that our method produces physically plausible garment dynamics, generalizes across a range of motions and body shapes, and supports a fixed set of garments. Our simulator runs at 300+ FPS on a commodity GPU, making it suitable for real-time applications.

While interpretable prototype networks offer compelling case-based reasoning for clinical diagnostics, their raw continuous outputs lack the semantic structure required for medical documentation. Bridging this gap via standard Retrieval-Augmented Generation (RAG) routinely triggers ``retrieval sycophancy,'' where Large Language Models (LLMs) hallucinate post-hoc rationalizations to align with visual predictions. We introduce ProtoMedAgent, a framework that formalizes multimodal clinical reporting as an iterative, zero-gradient test-time optimization problem over a strict neuro-symbolic bottleneck. Operating on a frozen prototype backbone, we distill latent visual and tabular features into a discrete semantic memory. Online generation is strictly constrained by exact set-theoretic differentials and a reflective Scribe-Critic loop, mathematically precluding unsupported narrative claims. To safely bound data disclosure, we introduce a semantic privacy gate governed by $k$-anonymity and $\ell$-diversity. Evaluated on a 4,160-patient clinical cohort, ProtoMedAgent achieves 91.2% Comparison Set Faithfulness where it fundamentally outperforms standard RAG (46.2%). ProtoMedAgent additionally leverages a binding $\ell$-diversity phase transition to systematically reduce artifact-level membership inference risks by an absolute 9.8%.

In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it first conducts a global temporal scan to anchor anomalous time windows, then performs fine-grained spatial grounding within the localized interval, and finally derives robust judgments via structured spatiotemporal Chain-of-Thought reasoning. To equip the model with these capabilities, we construct the first large-scale generated video anomaly dataset with per-frame bounding-box annotations, temporal anomaly windows, and fine-grained attribution labels. Building on this dataset, we design a three-stage progressive training paradigm. The model initially learns spatial and temporal anchoring through single- and multi-frame supervised fine-tuning, and then is optimized by a reinforcement learning strategy based on two-turn Group Relative Policy Optimization (GRPO). Beyond conventional accuracy rewards, we introduce Temporal and Spatial IoU rewards to supervise the intermediate localization process, effectively guiding the model toward more grounded and interpretable spatiotemporal reasoning. Extensive experiments demonstrate that CaC can stably concentrate on subtle anomalies, achieving a 25.7% accuracy improvement on fine-grained anomaly benchmarks and, when used as a reward signal, CaC reduces generated-video anomalies by 11.7% while improving overall video quality.

As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-level primitive representation, which makes it difficult to capture high-level aesthetic features. To address these challenges, we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment, built on our proposed annotation strategy for 3D scene aesthetics. In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations. Notably, our model operates solely on 3D Gaussian primitives, eliminating the need for rendering multi-view images and thus reducing computational cost and hardware requirements. Through aesthetics-supervised learning on multi-view 3DGS scene representations, Aes3DGSNet effectively captures high-level aesthetic cues and accurately regresses aesthetic scores. Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment. Code and datasets will be made available in a future version.

Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first near-lossless empirical sparse framework tailored for ICL video editing. Our design is grounded in two key insights: first, context tokens exhibit significantly lower saliency than source tokens; second, we theoretically prove and empirically validate that Query sharpness correlates with approximation error. Motivated by these findings, ISA implements an efficient pre-selection strategy to prune redundant context, followed by a dynamic query grouping mechanism that routes high-error queries to full attention and low-error ones to a computationally efficient 0-th order Taylor sparse attention. Furthermore, we build \textbf{\texttt{LIVEditor-14B}} , a novel lightning video editing model via ISA and a proposed video-editing data pipeline that curated a 1.7M high-quality dataset. Extensive experiments demonstrate that LIVEditor-14B achieves a $\sim$60% reduction in attention-module latency while surpassing state-of-the-art methods across EditVerseBench, IVE-Bench, and VIE-Bench, delivering near-lossless acceleration without compromising visual fidelity.

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained Transformers provides an appealing shortcut, yet the fundamental representational gap between Softmax and linear attention prevents effective weight transfer. In this work, we address this conversion challenge from two perspectives: architectural alignment and representational alignment. We identify Test-Time Training (TTT) as a linear-complexity architecture whose two-layer dynamic formulation is structurally aligned with Softmax attention, enabling direct inheritance of pretrained attention weights. To further align representational properties, including key shift-invariance and locality, we introduce key instance normalization and a lightweight locality enhancement module. We validate our approach by linearizing Stable Diffusion 3.5 and introduce SD3.5-T$^5$ (Transformer To Test Time Training). With only 1 hour of fine-tuning on 4$\times$H20 GPUs, SD3.5-T$^5$ achieves comparable text-to-image quality to the fine-tuned Softmax model, while accelerating inference by 1.32$\times$ and 1.47$\times$ at 1K and 2K resolutions. Code is available at https://github.com/LeapLabTHU/Transformer-to-TTT.

Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the protocol grounding and layout-level safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are realistic and valid under modeled geometric, chemical-safety, and navigation constraints.

Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reasoning-driven generative multimodal embeddings can outperform discriminative embeddings on several embedding tasks. However, Chain-of-Thought (CoT) reasoning tends to generate redundant thinking steps and introduce semantic ambiguity in the summarized answers in broader retrieval scenarios. To address this limitation, we propose Rewrite-driven Multimodal Embedding (RIME), a unified framework that jointly optimizes generation and embedding through a retrieval-friendly rewrite. Meanwhile, we present the Cross-Mode Alignment (CMA) to bridge the generative and discriminative embedding spaces, enabling flexible mutual retrieval to trade off efficiency and accuracy. Based on this, we also introduce Refine Reinforcement Learning (Refine-RL) that treats discriminative embeddings as stable semantic anchors to guide the rewrite optimization. Extensive experiments on MMEB-V2, MRMR and UVRB demonstrate that RIME substantially outperforms prior generative embedding models while significantly reducing the length of thinking.

In this work, we tackle the problem of Open World Object Detection (OWOD). This challenging scenario requires the detector to incrementally learn to classify known objects without forgetting while identifying unknown objects without supervision. Previous OWOD methods have enhanced the unknown discovery process and employed memory replay to mitigate catastrophic forgetting. However, since existing methods heavily rely on the detector's known class predictions for detecting unknown objects, they struggle to effectively learn and recognize unknown object representations. Moreover, while memory replay mitigates forgetting of old classes, it often sacrifices the knowledge of newly learned classes. To resolve these limitations, we propose DEUS (Detecting Unknowns via energy-based Separation), a novel framework that addresses the challenges of Open World Object Detection. DEUS consists of Equiangular Tight Frame (ETF)-Subspace Unknown Separation (EUS) and an Energy-based Known Distinction (EKD) loss. EUS leverages ETF-based geometric properties to create orthogonal subspaces, enabling cleaner separation between known and unknown object representations. Unlike prior energy-based approaches that consider only the known space, EUS utilizes energies from both spaces to better capture distinct patterns of unknown objects. Furthermore, EKD loss enforces the separation between previous and current classifiers, thus minimizing knowledge interference between previous and newly learned classes during memory replay. We thoroughly validate DEUS on OWOD benchmarks, demonstrating outstanding performance improvements in unknown detection while maintaining competitive known class performance.

Pointing-based methods decompose complex tasks as sequential grounding and reasoning steps. Given a query, the model first grounds the relevant objects by generating their coordinates, and then predicts an answer conditioned on these points. While this approach has been shown to increase the performance of Large Vision-Language Models (LVLMs), it remains unclear why and how it improves the models' visual reasoning. In this work, we evaluate pointing-based methods in the task of zero-shot counting in visual scenes. We experiment with multiple fine-tuning and training-free approaches on state-of-the-art LVLMs, and compare them with Point-then-Count (PtC), where models first generate point coordinates for the target objects and then predict their count. Our results show that PtC achieves the highest accuracy among the evaluated approaches, with predicted points correctly grounded in the image in more than 94% of cases (based on F1-score). Mechanistic analyses show that gains arise from spatial information encoded in the predicted coordinates. Nevertheless, grounding performance varies across image regions, revealing spatial biases. Finally, the results indicate that PtC improves out-of-distribution generalization on both synthetic and real data, suggesting the potential of coordinates to help LVLMs improve their counting skills.

Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery is fundamentally challenged by the severe radiometric discrepancy between passive optical imaging and coherent active radar sensing. While existing approaches primarily rely on statistical distribution alignment or semantic matching, they often overlook a critical physical prior: ships are rigid objects whose geometric structures remain stable across sensing modalities, whereas texture appearance is highly modality-dependent. In this work, we propose SDF-Net, a Structure-Aware Disentangled Feature Learning Network that systematically incorporates geometric consistency into optical--SAR ship ReID. Built upon a ViT backbone, SDF-Net introduces a structure consistency constraint that extracts scale-invariant gradient energy statistics from intermediate layers to robustly anchor representations against radiometric variations. At the terminal stage, SDF-Net disentangles the learned representations into modality-invariant identity features and modality-specific characteristics. These decoupled cues are then integrated through a parameter-free additive residual fusion, effectively enhancing discriminative power. Extensive experiments on the HOSS-ReID dataset demonstrate that SDF-Net consistently outperforms existing state-of-the-art methods. The code and trained models are publicly available at https://github.com/cfrfree/SDF-Net.

Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO.

Although high-resolution mapping of pan-Arctic sea ice with reliable corresponding uncertainty is essential for operational sea ice concentration (SIC) charting, it is a difficult task due to key challenges, such as the subtle nature of ice signature features, inexact SIC labels, model uncertainty, and data heterogeneity. This study presents a novel Bayesian High-Resolution Transformer approach for 200 meter resolution pan-Arctic SIC mapping and uncertainty quantification using Sentinel-1, RADARSAT Constellation Mission (RCM), and Advanced Microwave Scanning Radiometer 2 (AMSR2) data. First, to improve small and subtle sea ice feature (e.g., cracks/leads, ponds, and ice floes) extraction, we design a novel high-resolution Transformer model with both global and local modules that can better discern the subtle differences in sea ice patterns. Second, to address low-resolution and inexact SIC labels, we design a geographically-weighted weakly supervised loss function to supervise the model at region level instead of pixel level, and to prioritize pure open water and ice pack signatures while mitigating the impact of ambiguity in the marginal ice zone (MIZ). Third, to improve uncertainty quantification, we design a Bayesian extension of the proposed Transformer model, treating its parameters as random variables to more effectively capture uncertainties. Fourth, to address data heterogeneity, we fuse three different data types (Sentinel-1, RCM, and AMSR2) at decision-level to improve both SIC mapping and uncertainty quantification. The proposed approach is evaluated under pan-Arctic minimum-extent conditions in 2021 and 2025. Results demonstrate that the proposed model achieves 0.70 overall feature detection accuracy using Sentinel-1 data, while also preserving pan-Arctic SIC patterns (Sentinel-1 R\textsuperscript{2} = 0.90 relative to the ARTIST Sea Ice product).

The Sun is observed in unprecedented detail, enabling studies of its activity on very small spatiotemporal scales. However, the large volume of data collected by our telescopes cannot be fully analyzed with conventional methods. Popular machine learning methods identify general trends from observations, but tend to overlook unusual events due to their low frequency of occurrence. We study the applicability of unsupervised probabilistic methods to efficiently identify rare events in multidimensional solar observations and optimize our computational resources to the study of these extreme phenomena. We introduce Inspectorch, an open-source framework that utilizes flow-based models: flexible density estimators capable of learning the multidimensional distribution of solar observations. Once optimized, it assigns a probability to each sample, allowing us to identify unusual events. We apply this approach by applying it to observations from the Hinode Spectro-Polarimeter, the Interface Region Imaging Spectrograph, the Microlensed Hyperspectral Imager at Swedish 1-m Solar Telescope, the Atmospheric Imaging Assembly on board the Solar Dynamics Observatory and the Extreme Ultraviolet Imager on board Solar Orbiter. We find that the algorithm assigns consistently lower probabilities to spectra that exhibit unusual features. For example, it identifies profiles with very strong Doppler shifts, uncommon broadening, and temporal dynamics associated with small-scale reconnection events, among others. As a result, Inspectorch demonstrates that density estimation using flow-based models offers a powerful approach to identifying rare events in large solar datasets. The resulting probabilistic anomaly scores allow computational resources to be focused on the most informative and physically relevant events. We make our Python package publicly available at https://github.com/cdiazbas/inspectorch.

Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.

Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete text communication, which imposes runtime overhead and information quantization loss. While latent state transfer offers an alternative, existing approaches either assume homogeneous sender--receiver architectures or rely on pair-specific learned translators, limiting scalability across diverse model families with disjoint manifolds. We reconceptualize the visual interface of Vision-Language Models (VLMs), trained for natural images, as a continuous communication channel between heterogeneous agents, and instantiate this idea as the \textbf{Vision Wormhole}: a Universal Visual Codec maps reasoning traces into a shared continuous reference space and injects them into the receiver's visual pathway, yielding cross-architecture latent state transfer without per-pair translators. The framework adopts a hub-and-spoke topology that reduces alignment complexity from $O(N^2)$ to $O(N)$, and is trained by label-free teacher--student distillation against the text channel, requiring no parallel hidden-state supervision. Extensive experiments across heterogeneous VLM families (Qwen-VL, Gemma, SmolVLM2, LFM2.5-VL) and nine reasoning benchmarks show that the Vision Wormhole reduces end-to-end wall-clock time across most evaluated settings and yields positive macro-average $Δ$-accuracy.

Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for collapse prevention. Existing approaches regularize representations towards isotropic Gaussian distributions, but inherently favor dense representations and fail to capture the key property of sparsity observed in efficient representations. We introduce Rectified Distribution Matching Regularization (RDMReg), a sliced two-sample distribution-matching loss that aligns representations to a Rectified Generalized Gaussian (RGG) distribution. RGG enables explicit control over expected $\ell_0$ norm through rectification, while its continuous truncated component admits a maximum-entropy characterization under expected $\ell_p$ norm and support constraints. Equipping JEPAs with RDMReg yields Rectified LpJEPA, which strictly generalizes prior Gaussian-based JEPAs. Empirically, Rectified LpJEPA learns sparse, non-negative representations with favorable sparsity--performance trade-offs and competitive downstream performance on image classification benchmarks, showing that RDMReg can enforce sparsity while preserving task-relevant information.

Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on label correction or sample selection mechanisms. In contrast, we study LNL from an optimization perspective by establishing a theoretical connection between label noise and the flatness-seeking behavior of Sharpness-Aware Minimization (SAM). Based on this analysis, we propose Noise-Compensated Sharpness-Aware Minimization (NCSAM), which uses a noise-compensated perturbation to counteract the optimization bias induced by noisy labels. By correcting distorted SAM perturbations, NCSAM mitigates the memorization of noisy labels during training while preserving the simplicity of optimization-based learning. Experiments on synthetic and real-world noisy-label benchmarks show that NCSAM consistently improves over SAM-based optimization baselines and remains competitive with representative noisy-label learning methods.

Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera datasets with limited scene coverage, making them inadequate for crowd analysis in large-scale scenes. To bridge this gap, we introduce MovingDroneCrowd++, the largest video-level dataset dedicated to dense crowd counting and tracking with fast-moving drones, captured under diverse flight altitudes, camera angles, and illumination conditions. Existing methods, however, still fail to achieve satisfactory video individual counting or tracking performance under these challenging aerial conditions. To this end, we propose GD3A (Global Density map Decomposition via group-wise Descriptor Association), a video individual counting method that first establishes pixel-level correspondences between pedestrian descriptors across frames via optimal transport with an adaptive dustbin score. Then, group-wise association is adopted to guide the decomposition of the global density map into shared, inflow, and outflow density maps. We further introduce a pedestrian tracking method, DVTrack (Descriptor Voting Track), which converts descriptor-level matching into instance-level association through descriptor voting. Our methods rely on the association results of group-wise multiple descriptors for each pedestrian rather than a single vector. Since intra-group matching errors do not affect the final counting and tracking results, our methods are more robust in dense crowds and challenging aerial conditions. Experiments show that our methods achieve substantial gains in both crowd counting and tracking on moving-drone videos with dense crowds and complex motions, reducing counting error by 47.4% and improving tracking accuracy by 64.6%. Code, dataset, and pretrained models are available at https://github.com/fyw1999/MovingDroneCrowd.

Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a promising avenue for acceleration, but existing approaches are limited by token-level ambiguity and lack of spatial awareness. In this work, we introduce Multi-Scale Local Speculative Decoding (MuLo-SD), a novel framework that combines multi-resolution drafting with spatially informed verification to accelerate AR image generation. Our method leverages a low-resolution drafter paired with an up-sampling step to propose candidate image tokens, which are then verified in parallel by a high-resolution target model. Crucially, we incorporate a local rejection and resampling mechanism, enabling efficient correction of draft errors by focusing on spatial neighborhoods rather than raster-scan resampling after the first rejection. When integrated with parallel decoding resampling, MuLo-SD achieves substantial speedups -- up to $\mathbf{5\times}$ -- outperforming both speculative decoding and parallel decoding baselines in terms of acceleration, while maintaining comparable semantic alignment and perceptual quality. These results are validated using GenEval, DPG-Bench, and FID/HPSv2 on the MS-COCO 5k validation split. Extensive ablations highlight the impact of up-sampling design, probability pooling, and local rejection and resampling with neighborhood expansion. Our approach sets a new state-of-the-art in speculative decoding for image synthesis, bridging the gap between efficiency and fidelity. Project page is available at https://qualcomm-ai-research.github.io/mulo-sd-webpage/ .

Fine-grained recognition of marine organisms is important for ecological research, biodiversity monitoring, habitat conservation, and evidence-based policy-making. However, many existing approaches primarily rely on object- or ROI-centered representations. These limitations can reduce discriminative performance in challenging underwater scenes, where visually similar organisms often appear under diverse environmental conditions. To address these challenges, we propose MATANet (Multi-context Attention and Taxonomy-Aware Network), a framework for fine-grained taxonomic recognition of marine organisms. MATANet is motivated by expert taxonomic identification practices, in which both organism-level morphology and contextual cues are considered during recognition. The framework consists of two main components. First, the Multi-Context Environmental Attention Module (MCEAM) models cross-attention between the primary region of interest (ROI) and multi-scale surrounding environmental regions, thereby combining local morphological cues with habitat-level contextual information. Second, the Hierarchy-Aware Representation Learning Module (HRLM) uses taxonomic hierarchy as auxiliary supervision to regularize representation learning and encourage semantically structured embeddings across taxonomic levels. By jointly modeling organism appearance, environmental context, and taxonomic structure, MATANet learns more discriminative representations for fine-grained taxonomic recognition. Experiments on FathomNet2025 and LifeCLEF2015-Fish demonstrate that MATANet consistently improves recognition performance over existing methods. Additional experiments on FAIR1M further examine the applicability of the proposed framework beyond underwater imagery. Notably, MATANet ranked first in the FathomNet 2025 Challenge at the CVPR 2025 FGVC12 workshop.

End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valenc-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These evaluation results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and feedback.

Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure traceability by embedding imperceptible watermarks into training images, which remain detectable in outputs even after fine-tuning. However, current methods lack a unified evaluation framework. To address this, this paper establishes a general threat model and introduces a comprehensive evaluation framework encompassing Universality, Transmissibility, and Robustness. Experiments show that existing methods perform well in universality and transmissibility, and exhibit some robustness against common image processing operations, yet still fall short under real-world threat scenarios. To reveal these vulnerabilities, the paper further proposes a practical watermark removal method that fully eliminates dataset watermarks without affecting fine-tuning, highlighting a key challenge for future research.

A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, entangled forgery representation, conflating content-dependent flaws with content-agnostic artifacts, and are further constrained by outdated benchmarks. We propose OmniAID, a novel framework centered on a decoupled Mixture-of-Experts (MoE) architecture that separates: (1) semantic flaws across distinct content domains via Routable Specialized Semantic Experts, and (2) content-agnostic universal artifacts from content-dependent flaws via a Fixed Universal Artifact Expert. A two-stage training strategy first specializes experts independently with domain-specific hard-sampling, then trains a lightweight gating network for effective input routing. By explicitly decoupling "what is generated" (content-specific flaws) from "how it is generated" (universal artifacts), OmniAID achieves robust generalization. We also introduce Mirage, a large-scale, contemporary dataset comprising a modern training set and a challenging test set. Extensive experiments demonstrate that OmniAID surpasses existing detectors, establishing a new standard for AIGI detection against modern, in-the-wild threats. Code is available at https://github.com/yunncheng/OmniAID.

Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature, leading to asymmetric and suboptimal alignment. To address this, we propose Alignment across Trees, a method that constructs and aligns tree-like hierarchical features for both image and text modalities. Specifically, we introduce a semantic-aware visual feature extraction framework that applies a cross-attention mechanism to visual class tokens from intermediate Transformer layers, guided by textual cues to extract visual features with coarse-to-fine semantics. We then embed the feature trees of the two modalities into hyperbolic manifolds with distinct curvatures to effectively model their hierarchical structures. To align across the heterogeneous hyperbolic manifolds with different curvatures, we formulate a KL distance measure between distributions on heterogeneous manifolds, and learn an intermediate manifold for manifold alignment by minimizing the distance. We prove the existence and uniqueness of the optimal intermediate manifold. Experiments on taxonomic open-set classification tasks across multiple image datasets demonstrate that our method consistently outperforms strong baselines under few-shot and cross-domain settings.

Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose \textbf{stReaming drag-oriEnted interactiVe vidEo manipuLation (REVEL)}, a new task that enables users to modify generated videos \emph{anytime} on \emph{anything} via fine-grained, interactive drag. Beyond DragVideo and SG-I2V, REVEL unifies drag-style video manipulation as editing and animating video frames with both supporting user-specified translation, deformation, and rotation effects, making drag operations versatile. In resolving REVEL, we observe: \emph{i}) drag-induced perturbations accumulate in latent space, causing severe latent distribution drift that halts the drag process; \emph{ii}) streaming drag is easily disturbed by context frames, thereby yielding visually unnatural outcomes. We thus propose a training-free approach, \textbf{DragStream}, comprising: \emph{i}) an adaptive distribution self-rectification strategy that leverages neighboring frames' statistics to effectively constrain the drift of latent embeddings; \emph{ii}) a spatial-frequency selective optimization mechanism, allowing the model to fully exploit contextual information while mitigating its interference via selectively propagating visual cues along generation. Our method can be seamlessly integrated into existing autoregressive video diffusion models, and extensive experiments firmly demonstrate the effectiveness of our DragStream.

Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to substantial resolution gaps between low-resolution (LR) queries and high-resolution (HR) gallery images. Prior approaches commonly rely on super-resolution (SR) or resolution-invariant representation learning, which often increases system complexity and may not directly address the feature mismatch induced by resolution degradation. In this work, we report a new empirical finding from a dedicated analysis in which identity-specific variation is averaged out: the HR--LR feature discrepancy produced by standard ReID backbones exhibits a consistent, resolution-related semantic direction in the embedding space. We further support this observation with statistical analyses based on Canonical Correlation Analysis (CCA) and Pearson correlation analysis. Motivated by this finding, we propose Vector Panning Feature Alignment (VPFA), a lightweight post-hoc module that learns to pan LR features along the learned resolution direction to obtain pseudo-HR representations. VPFA operates after feature extraction and can be integrated into existing ReID systems with negligible overhead. Extensive experiments on multiple CR-ReID benchmarks show that VPFA achieves state-of-the-art performance while improving efficiency compared to SR-based or jointly trained alternatives.

Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a systematic benchmark remains lacking. This paper addresses this gap by introducing a Medical benchmark that applies multiple templates to VLMs in a hierarchical medical visual question answering task. We find that current VLMs are highly susceptible to visual cues, with failure rates showing a correlation to model size or overall accuracy. we discover that perceived authority and user mimicry are powerful triggers, suggesting a bias mechanism independent of visual data. To overcome this, we propose a Visual Information Purification for Evidence based Responses (VIPER) strategy that proactively filters out non-evidence-based social cues, thereby reinforcing evidence based reasoning. VIPER reduces sycophancy while maintaining interpretability and consistently outperforms baseline methods, laying the necessary foundation for the robust and secure integration of VLMs.

Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing threats through visual inspection or feature analysis, we introduce BadBlocks-a novel, lightweight, and highly covert attack that challenges these safeguards. By selectively poisoning specific blocks within the UNet architecture while keeping other components intact, BadBlocks requires only 30% of the computational resources and 20% of the GPU time of conventional attacks, effectively democratizing backdoor injection on consumer-grade GPUs. Empirical evaluations demonstrate that BadBlocks achieves a high attack success rate with negligible perceptual quality loss, while successfully bypassing state-of-the-art defenses, particularly attention-based detection frameworks. Layer-level ablation studies further confirm that backdoor mapping does not require full-network fine-tuning, revealing the disparate vulnerability of different neural layers. Overall, BadBlocks significantly lowers the barrier for executing backdoor attacks, presenting a critical security risk. Our code is available at: https://github.com/paoche11/BadBlocks.

Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potential to inadvertently memorize and replicate training data. Recent mitigation efforts have focused on identifying and pruning weights responsible for triggering verbatim training data replication, based on the assumption that memorization can be localized. We challenge this assumption and demonstrate that, even after such pruning, small perturbations to the text embeddings of previously mitigated prompts can re-trigger data replication, revealing the fragility of such methods. Our further analysis then provides multiple indications that memorization is indeed \textit{not} inherently local: (1) replication triggers for memorized images are distributed throughout text embedding space; (2) embeddings yielding the same replicated image produce divergent model activations; and (3) different pruning methods identify inconsistent sets of memorization-related weights for the same image. Finally, we show that bypassing the locality assumption enables more robust mitigation through adversarial fine-tuning. These findings provide new insights into the fundamental nature of memorization in text-to-image DMs and inform the future development of more reliable mitigation methods against DM memorization.

Gloss-free Sign Language Translation (SLT) has advanced rapidly, achieving strong performances without relying on gloss annotations. However, these gains have often come with increased model complexity and high computational demands, raising concerns about scalability, especially as large-scale sign language datasets become more common. We propose a segment-aware visual tokenization framework that leverages sign segmentation to convert continuous video into discrete, sign-informed visual tokens. This reduces input sequence length by up to 50% compared to prior methods, resulting in up to 2.67x lower memory usage and better scalability on larger datasets. To bridge the visual and linguistic modalities, we introduce a token-to-token contrastive alignment objective, along with a dual-level supervision that aligns both language embeddings and intermediate hidden states. This improves fine-grained cross-modal alignment without relying on gloss-level supervision. Our approach notably exceeds the performance of state-of-the-art methods on the PHOENIX14T benchmark, while significantly reducing sequence length. Further experiments also demonstrate our improved performance over prior work under comparable sequence-lengths, validating the potential of our tokenization and alignment strategies.

Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditions to guide generation. However, these models primarily animate static images without extending beyond their provided context. Introducing additional constraints, such as camera trajectories, can enhance diversity but often degrade visual quality, limiting their applicability for tasks requiring faithful scene representation. We propose CamC2V, a context-to-video (C2V) model that integrates multiple image conditions as context with 3D constraints alongside camera control to enrich both global semantics and fine-grained visual details. This enables more coherent and context-aware video generation. Moreover, we motivate the necessity of temporal awareness for an effective context representation. Our comprehensive study on the RealEstate10K dataset demonstrates a $24.09\%$ (FVD) improvement in visual quality and camera controllability. Our code is publicly available at: https://github.com/LDenninger/CamC2V.

Dynamic Facial Expression Recognition (DFER) facilitates the understanding of psychological intentions through non-verbal communication. Existing methods struggle to manage irrelevant information, such as background noise and redundant semantics, which impacts both efficiency and effectiveness. In this work, we propose a novel supervised temporal soft masked autoencoder network for DFER, namely AdaTosk, which integrates a parallel supervised classification branch with the self-supervised reconstruction branch. The self-supervised reconstruction branch applies random binary hard mask to generate diverse training samples, encouraging meaningful feature representations in visible tokens. Meanwhile the classification branch employs an adaptive temporal soft mask to flexibly mask visible tokens based on their temporal significance. Its two key components, respectively of, class-agnostic and class-semantic soft masks, serve to enhance critical expression moments and reduce semantic redundancy over time. Extensive experiments conducted on widely-used benchmarks demonstrate that our AdaTosk remarkably reduces computational costs compared with current state-of-the-art methods while still maintaining competitive performance.

Conventional federated learning (FL) heavily depends on high-quality labels, which are often impractical in the real world, leading to the federated label-noise (F-LN) problem. Worse still, the F-LN problem is exacerbated by the heterogeneity of FL, whereas clients experience different label-noise types, ratios, and data distribution. In this study, we first observe an intriguing phenomenon that the global model of FL exhibits a slow memorization of noisy labels, suggesting its ability to maintain reliable predictions and robust representations in FL. Motivated by this, we propose a novel method termed Federated Global Reviser (\method), a straightforward yet effective method comprising three modules that collaboratively rectify noisy labels and regularize local training. By exploiting this inherent property, \method\ improves the label-noise robustness of FL in a self-contained manner. Extensive experiments on three widely used F-LN benchmarks demonstrate the superior performance of FedGR, consistently outperforming eight state-of-the-art baselines even in severe label-noise and data heterogeneity. Code: https://github.com/cs-yuxintian/FedGR-ICML26

While multimodal large language models (MLLMs) have achieved rapid progress in vision-language understanding, they remain prone to multimodal hallucinations, producing responses that are inconsistent with the visual input. Existing benchmarks predominantly focus on detecting hallucination outcomes rather than evaluating the underlying causes of these failures. Moreover, many benchmarks rely on simplistic scenarios and limited evaluation formats that no longer challenge state-of-the-art models. To address these limitations, we introduce ReactBench, a cause-driven hallucination benchmark featuring multiple tasks and an exam-style evaluation format. By generating adversarial images and hallucination-inducing queries, ReactBench introduces four targeted tasks: Relational Erasure, Counterfactual Attribute, Alteration Tracing, and Dense Counting. These tasks systematically expose co-occurrence bias, language priors, cross-image comparative perception deficiencies, and fine-grained perceptual bottlenecks. Beyond standard accuracy-based evaluation, we leverage Chain-of-Thought reasoning to identify fine-grained sub-causes of hallucination within each task. Extensive evaluations reveal that current MLLMs remain notably vulnerable to cause-specific hallucination triggers, demonstrating the value of ReactBench as a systematic and interpretable testbed for diagnosing and improving multimodal model robustness. The project page is available at https://reactbench.github.io/.

Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adapting pretrained vision-language models (VLMs) to action prediction. However, VLM-derived representations are often insensitive to subtle visual distinctions required for low-level control, causing state aliasing between visually similar states that require substantially different actions. Prior VLA studies improve visual understanding by generating visual or reasoning outputs, such as future frames, 2D grounding points or traces, or intermediate spatial reasoning steps, but these objectives typically shape the vision encoder only indirectly through end-to-end prediction and do not explicitly analyze state aliasing in the learned visual feature space. To mitigate state aliasing, we introduce inverse dynamics learning as an auxiliary objective that directly supervises the VLA vision encoder. By predicting the action between current and future observations, our objective encourages the encoder to capture fine-grained visual distinctions that determine low-level actions. We further use pseudo-reversed supervision to expose the encoder to a broader range of action directions and improve generalization under limited robot demonstrations. Our method applies to diverse VLA baselines, uses only standard observation-action pairs without additional annotations, and preserves the original inference pipeline at test time. Experiments on CALVIN ABC-D and SimplerEnv show consistent gains across diverse VLA baselines. Frozen-encoder probing and state-feature alignment analyses further show that our method learns state-discriminative visual representations that reduce state aliasing and better align with robot state changes.

Rapid identification of damaged buildings after natural disasters or on war areas is crucial to support emergency response and prioritize interventions. Earth Observation constellations provide timely, large-scale coverage, but actionable information is often delayed by data downlink constraints, on-ground processing, and human interpretation. Reducing this latency is essential to improve decision-making responsiveness. In this work, we propose an original AI-based system that enables object-level building damage assessment (localization and damage classification) directly onboard satellites from pre-disaster and post-disaster highresolution optical imagery. Available pre-disaster images are encoded on ground into compact latent representations, transmitted to the satellite, and compared on-board with newly acquired post-event observations. Leveraging AI interpretation capabilities and increasing processing capabilities on-board satellites, the proposed design enables processing directly at the data source, reducing the amount of information to be downlinked while preserving task-relevant content and improving overall system responsivity. We explore the design space through a systematic benchmark of onboard-compatible variants, analyzing the impact of siamese processing, cross-attention, latent-space compression, and robustness-oriented data augmentation. Experiments on xBD dataset demonstrate reliable and robust damage assessment under misalignment, with minimal performance degradation under strong compression.

Purpose: Laparoscopic ultrasound (LUS) enhances the safety of liver surgery by visualizing intrahepatic vessels in real-time. Still, vessel identification remains difficult due to probe constraints, complex vascular structure, and tissue deformation. This work aims to enable real-time, patient-specific vessel identification that remains robust under deformation through deformable ultrasound augmentation. Methods: Preoperative CT vessel annotations are used to generate synthetic ultrasound data via optimized physics-based rendering, coupled with domain adaptation to intraoperative ultrasound. The rendering is trained end-to-end for vessel identification and patient-specificity, eliminating the need for preoperative ultrasound. A deformation-aware augmentation simulates realistic intraoperative motion and tissue deformation within the rendering pipeline. Results: In abdominal phantom and limited clinical feasibility experiments (single-case clinical evaluation), the framework achieved real-time intrahepatic vessel-branch identification, maintaining performance under new patient poses. Conclusion: The framework enables real-time vessel identification without preoperative ultrasound and supports technical feasibility, but multi-patient validation is still needed for generalizability and clinical feasibility.

Vision-based approaches have become the dominant paradigm for traversability estimation in unstructured outdoor environments, typically adapting vision foundation models (VFMs) via semantic segmentation supervision. However, this paradigm faces three fundamental challenges that undermine its reliability: the task-agnostic design of VFMs, the ambiguity of traversability annotations, and the discrepancy between semantic labels and physical safety. We propose Vision-to-Traversability Adaptation (ViTA), a framework that adapts VFMs for reliable traversability estimation, instantiated on SAM2. ViTA injects task-specific knowledge through learnable traversability prompts while preserving the VFM's cross-domain generalization. To handle annotation ambiguity, we introduce Perspective-Diversified Training, which estimates semantic uncertainty to suppress confident predictions at ambiguous boundaries. To bridge the semantic-traversability discrepancy, we distill geometric knowledge during training, enabling slope and elevation reasoning from RGB images alone at inference. The semantic and geometric outputs are fused into a continuous traversability score that reflects both semantic uncertainty and geometric risk. Evaluations across diverse domains, including challenging real-world off-road datasets, demonstrate that ViTA achieves state-of-the-art IoU and Precision with substantial false-positive reduction and strong cross-domain generalization.

Vision-Language-Action~(VLA) models have shown strong potential for general-purpose robotic manipulation, yet they still struggle to generalize to unseen tasks that necessitate transferring relevant experience across objects, scenes, and action patterns. This paper proposes VLA-Pro, a plug-and-play framework designed to enhance cross-task generalization by storing task-relevant procedural memories at training time and transferring these memories during inference. Specifically, VLA-Pro stores task-specific LoRA adapters as parameterized procedural memories during training. At inference time, VLA-Pro retrieves relevant procedural memories based on the current multi-modal context and dynamically fuses these memories for generating the current action chunk. Experiments on RoboTwin, RLBench, and real-world manipulation tasks show that VLA-Pro consistently improves cross-task generalization across multiple backbones, achieving up to a 207% relative improvement in simulation and increasing real-world success rate from 5.8% to 65.0%. These results suggest that procedural memory retrieval and adaptation provide an effective mechanism for transferring manipulation experience to novel tasks while preserving modularity and execution stability.

Severe image degradation under low-light nighttime conditions constitutes a core bottleneck preventing all-day applications for UAV-based single object tracking. Existing image enhancement methods often struggle to distinguish between target and background regions, which can easily lead to amplified background noise or compromise target features. To overcome this limitation, we propose TAE, a target-aware low-light enhancement framework tailored for nighttime object tracking. Guided explicitly by weak supervisory signals from tracking bounding boxes, the framework performs region-aware enhancement to ensure operations focus on the target area. It further adopts an adaptive RGB multi-curve fusion mechanism to achieve refined modeling and adaptive adjustment across different regions. To facilitate research in this domain, we also contribute DarkSOT, a new benchmark for nighttime UAV tracking, comprising 268 sequences across 9 target categories. Experimental results on the DarkSOT and UAVDark135 demonstrate that TAE significantly improves tracking performance in low-light nighttime scenarios, exhibiting strong robustness and generalization. The DarkSOT dataset is available at https://github.com/Fu0511/DarkSOT-Dataset.

3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of various geometric deep learning architectures for the classification of 3D scenes represented using Gaussian Splatting. We benchmark point-based and graph-based models across both traditional point cloud datasets and dedicated Gaussian Splatting datasets. Scenes are embedded into latent representations, which are evaluated through end-to-end classification, linear probing, and clustering analysis. Our study provides insight into the suitability of different geometry-aware architectures and input feature configurations for learning effective 3D Gaussian Splat representations. The results highlight consistent differences between architectural families and reveal the impact of Gaussian-specific attributes on the quality of representation.

With the emergence of wireless applications in three-dimensional environments, such as the low-altitude airspace and 3D heterogeneous networks, radio map estimation is increasingly required to characterize signal propagation across both horizontal and vertical dimensions. However, extending radio map estimation from 2D to 3D remains challenging due to increased spatial sparsity and limited supervision across continuous altitudes. In this paper, we propose \textbf{\textit{RadioFormer3D}}, a specialized model for volumetric spectrum reconstruction under weak supervision. Building on the dual-stream, multi-granularity fusion architecture of \textit{RadioFormer}, \textit{RadioFormer3D} introduces a Fourier-based sampling encoder and a volumetric decoder to efficiently process sparse measurements in 3D space. To alleviate the lack of vertical supervision, we propose the \textbf{\textit{Joint Spectrum Integrity Loss}}, which integrates volume-level pseudo-label supervision, map-level geometry-aware radio rendering, and pixel-level localized constraints within a unified optimization scheme. This design enables the model to capture complex vertical structural relationships more effectively under sparse supervision. Extensive experiments across several radio map datasets show that \textit{RadioFormer3D} achieves superior overall performance compared to representative existing methods. In particular, it demonstrates improved reconstruction quality at unlabeled altitudes while maintaining a favorable trade-off between accuracy and inference efficiency, positioning it as a highly promising solution for future 3D environment-aware wireless networks.

Audio deepfake detection is well-studied as a binary problem, but partially manipulated speech, where a short synthesised segment is spliced into an otherwise genuine utterance, poses a harder and more realistic threat. Detecting such half-truth audio requires not only distinguishing it from real and fully fake speech, but also localising where the manipulation occurs. We present CAFNet, a 576k-parameter architecture that addresses both tasks jointly: it performs ternary classification (real, fully-fake, or half-truth) and regresses the temporal boundaries of the synthesised region in a single forward pass. CAFNet fuses Mel-Frequency Cepstral Coefficient (MFCC), Linear-Frequency Cepstral Coefficient (LFCC), and Chroma Short-Time Fourier Transform (Chroma-STFT) features through parallel depthwise-separable convolution branches with cross-attention, followed by a Bidirectional Long Short-Term Memory (BiLSTM) regression head for boundary prediction. On the combined Multi-Lingual Audio Deepfake Detection Corpus (MLADDC) T2+T3 test set, CAFNet achieves 92.71% accuracy and macro Area Under the Curve (AUC) of 0.9910, with boundary localisation Mean Absolute Error (MAE) of 0.075s and a median error of 0.052s. On binary detection, it achieves 96.76% accuracy and 3.20% Equal Error Rate (EER), outperforming fine-tuned XLS-R 300M (78.31%) and AST 87M (93.03%) at over 500 times fewer parameters. A cross-dataset study further shows that standard fine-tuning collapses cross-domain representations even under reduced backbone learning rates.

Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited and privacy is crucial. Recent state-of-the-art methods like EmbodiedSAM (ESAM) demonstrate the promise of online 3D perception by leveraging the Segment Anything Model (SAM) for real-time, fine-grained, and generalized 3D instance segmentation. However, ESAM still relies on a computationally expensive 3D sparse UNet for point cloud feature extraction, which accounts for the majority of the 3D inference time, hindering its practicality on resource-constrained devices. In this paper, we propose ESAM++, a lightweight and scalable alternative for online 3D scene perception tailored to edge devices without GPU acceleration. Our method introduces a 3D Sparse Feature Pyramid Network (SFPN) that efficiently captures multi-scale geometric features from streaming 3D point clouds while significantly reducing computational overhead and model size. We evaluate our approach on four challenging segmentation benchmarks, namely ScanNet, ScanNet200, SceneNN, and 3RScan, demonstrating that our model achieves competitive accuracy with up to 3 times faster inference with a 2 times smaller model size compared to ESAM, enabling practical deployment on edge devices.

Low-Rank Adaptation (LoRA) has become one of the most widely used fine-tuning mechanisms for adapting large language models to new domains, tasks, and users. Yet adaptation performance alone can obscure an important failure mode: LoRA updates may improve performance on the target distribution while degrading prior capabilities learned during pretraining and alignment. We show that this forgetting becomes especially severe when the adaptation distribution differs substantially from the models original training or alignment distributions. The challenge is amplified in practical settings, where the original training and alignment data are typically unavailable. Motivated by this constraint, we study how LoRA based adaptation balances new learning against forgetting in a replay-free setting, and introduce a simple output space regularizer that can be added directly to existing training pipelines. Our method removes the ground-truth token from both the base and adapted model distributions, renormalizes the remaining probabilities, and applies KL regularization only over the non-target vocabulary. This preserves the base models relative preferences among alternative tokens without directly opposing the cross-entropy signal required for adaptation. As the regularizer acts only at the loss level, it requires no replay data, architectural changes, adapter redesign, or inference-time overhead, and can be applied directly to existing LoRA variants. Across all LoRA variants tested and across various backbones, our method improves the frontier between new learning and forgetting when the adaptation distribution differs substantially from the base models original training or alignment distributions, suggesting a broadly applicable route toward more reliable LLM updating.

Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a controlled diagnostic framework with two synthetic tasks that disentangle perception from reasoning. Our analysis reveals a consistent perception-reasoning asymmetry: posttraining improves reasoning more substantially than perception, though the underlying mechanism differs by training paradigm. For supervised fine-tuning (SFT), this asymmetry stems from token imbalance in chain-of-thought supervision, where perception occupies fewer tokens and thus receives a weaker training signal. Dynamically reweighting the loss mitigates this imbalance and boosts end-to-end performance by up to 18.2. For reinforcement learning (RL), the asymmetry instead arises from reward coupling: outcome rewards correlate more strongly with reasoning than with perception, weakening the signal for perception learning. Adding a perception-aware reward alleviates the imbalance and improves end-to-end accuracy by up to 6.0; even without groundtruth perception rewards, a reliable surrogate reward provide useful signal, yielding gains of 3.2 points. Together, our results comprehensively diagnose asymmetric optimization and suggest concrete interventions to balance perception and reasoning.

Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited generalization across diverse driving conditions. While image generation technology offers a feasible solution for data augmentation, existing methods tailored for single-vehicle multi-view scenarios face two fundamental challenges in multi-agent driving settings: (1) the expansion of the learning objective degrades generation quality, and (2) the highly dynamic variations across agents hinder the modeling of consistency for physical attributes (e.g., color, category) in jointly observed objects. To bridge this gap, we propose V2XCrafter, the first framework for generating controllable and realistic collaborative driving scene across agents' camera views. For effective learning, we develop a progressive multi-agent diffusion model based on a single-agent backbone, using neighboring agents' latent states as reference signals to progressively guide the single-to-multi diffusion. To address cross-vehicle inconsistency, we propose a cross-agent attention module that leverages a collaboration view graph and learnable jointly observed object representation to model the dynamic cross-agent camera view relationships. Experiments have shown that V2XCrafter can generate high-fidelity and controllable street views with consistency across agents, thereby effectively enhancing the downstream collaborative 3D object detection tasks.

The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified inference across both visual and textual modalities and supporting a broader range of real-world applications. To comprehensively evaluate the perception, understanding, reasoning, and cognition capabilities of LVLMs throughout the entire financial business workflow in Chinese contexts, we introduce CFMME, a novel Chinese financial multimodal evaluation benchmark. CFMME comprises 6,052 instances spanning from fundamental academic knowledge to complex real-world applications, covering eight primary financial image modalities and four core multimodal tasks. On CFMME, we conduct a thorough evaluation of representative LVLMs. The results show that the state-of-the-art model attains an overall accuracy of 66.11\% on the question answering task and an average score of 77.18 on the detection, recognition, and information extraction tasks, indicating substantial room for improvement in current LVLMs. In addition, we conduct detailed analyses of error causes, cross-modal capabilities, and multi-orientation settings, yielding valuable insights for future research. We hope that CFMME will spur further progress in LVLMs, especially by improving their performance on multiple multimodal tasks in the financial domain.

LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although high-quality mask candidates are often generated, the final prediction may fail to match the given linguistic condition. This failure arises because language semantics are typically used as static prompts or post-hoc matching signals, rather than participating in the iterative mask generation process. Through systematic analysis, we show that many errors stem from semantic misalignment rather than poor mask quality. To address this issue, we propose FlowSeg, which introduces dynamic semantic guidance via a bidirectional semantic flow between intermediate decoding states and LLM-derived condition embeddings throughout the generation process. Language conditions actively guide mask refinement at each stage, while condition embeddings are progressively updated by emerging visual evidence. This design yields semantically grounded mask representations and visually aligned language conditions, enabling more reliable matching. We further incorporate a lightweight boundary-aware refinement to selectively enhance uncertain regions without perturbing confident interiors. Extensive experiments on referring expression segmentation and reasoning segmentation tasks demonstrate that FlowSeg consistently improves language-mask alignment and achieves state-of-the-art performance. Project page: https://zkzhang98.github.io/FlowSeg_page

Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data locality. However, the direct combination of FedAvg and LoRA suffers from three key issues: limited update space, which restricts the model's effective learning capacity; inter-round state mismatch, which disrupts cross-round local optimization continuity; and a client-agnostic starting state, which slows local convergence on clients. Although recent methods mitigate the limited update space issue by merging LoRA updates into the backbone across communication rounds, inter-round state mismatch and the client-agnostic starting state remain insufficiently addressed. To address these issues, we propose FedSmoothLoRA, a federated LoRA tuning framework that preserves the enlarged update space, improves cross-round local optimization continuity, and provides a client-aware starting state for local training. At each communication round, FedSmoothLoRA constructs the local LoRA initialization using two matrices: a Round-Matching matrix that preserves cross-round local state continuity, and a Gradient-Aligned matrix that provides client-specific optimization guidance from gradient signals estimated on local data. Together, these designs enable smoother and faster convergence. Extensive experiments on image classification and natural language generation tasks demonstrate that FedSmoothLoRA consistently outperforms existing federated LoRA tuning methods. Code: https://github.com/wangzehao0704/FedSmoothLoRA

Multi-modal industrial anomaly detection typically relies on separate models for each product category, fundamentally limiting practical scalability. When shifting to a unified paradigm that handles diverse classes simultaneously, detection accuracy often degrades due to inter-class interference and feature manifold confusion. To overcome these challenges, we propose a Unified Reference guided Cross-modal Mapping framework, named Uni-RCM. At its core, we propose a reference guide block to dynamically filter out category-specific noise by introducing a learnable reference feature, which captures the commonalities across different modalities. Besides, an offline residual quantizer is proposed to characterize the normal distribution by multiple cascaded codebooks. Extensive evaluations on the MVTec-3D AD dataset demonstrate the state-of-the-art performance in the challenging multi-class setting and in terms of image-level detection and pixel-level localization.

Image-based 3D reconstruction offers a low-cost alternative to traditional sensor-based techniques for road surface assessment. This study compares four reconstruction pipelines--COLMAP, Meshroom, Metashape, and 3D Gaussian Splatting (3DGS)--to evaluate their ability to estimate road surface roughness from smartphone imagery. All point clouds were processed in CloudCompare using a consistent workflow involving orientation alignment, segmentation, normal estimation, and roughness computation at neighborhood radiuses of 0.2, 0.4, and 0.6 model units. The results show that COLMAP provides the highest sensitivity to micro-texture, while Meshroom yields balanced reconstructions with moderate roughness variation. Metashape produces the smoothest geometry due to its internal filtering, and 3DGS captures visible irregularities but exhibits higher noise and lower density. The comparison demonstrates that open-source pipelines are viable for relative roughness evaluation, offering a practical approach for low-cost pavement monitoring.

Neural scaling laws appraise data through dataset size, while the Vendi Score uses quantum entropy to measure dataset value. We show both that common neural-scaling-law objectives and the Vendi Score are submodular. We further show that the Vendi Score is a special case of a broader class of submodular objectives that we call matrix spectral functions. This also includes determinantal (DPP) objectives, as well as many others. We also introduce weakly matrix monotone functions and show how they lead to weakly submodular matrix spectral functions, yielding a broad family of practical objectives for data appraisal. We develop secular-equation-based updates that avoid repeated eigendecompositions during greedy optimization, reducing marginal-gain evaluation for $m$-dimensional embeddings by an $O(m)$ factor relative to oracle queries. This yields an average empirical speedup of about 35,000x, making direct optimization of the Vendi Score feasible on ImageNet-1K-scale datasets. Thus enabled, we compare how well several objectives predict the value of training subsets for held-out test performance under fixed-size, class-balanced, and fixed training-budget regimes, including the Vendi Score, DPPs, facility location, and three new matrix spectral variants. Across multiple datasets, facility location performs the best. Direct optimization also reveals that, while the Vendi Score is predictive over moderate score ranges, pushing the objective to higher values can make it a poor downstream performance proxy. We also find that uniformly at random fixed-size subsets, both unconstrained and class-balanced, are remarkably concentrated in both appraisal scores and held-out performance. Finally, we show that size, class balance, and training budget do not alone determine data value: even when controlling for these factors, performance ranges smoothly from good to bad.

While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation and data levels, we introduce GUI-RobustEval and propose Robustness-driven Trajectory Synthesis. GUI-RobustEval contains $1,216$ executable test cases that systematically measure error recovery capabilities across a broad and realistic spectrum of error modes. At the data level, RoTS is a scalable synthesis framework that creates $800k$ high-quality data via a tree-based pipeline that proactively discovers diverse error modes and synthesizes corresponding recovery steps. Our two models, RoTS-7B and RoTS-32B, fine-tuned on our dataset, both demonstrate significant gains on GUI-RobustEval and traditional GUI benchmarks. Notably, RoTS-32B achieves state-of-the-art performance on OSWorld, with a $47.4\%$ success rate and a $33.8\%$ All-Pass@4 score, suggesting that improved long-horizon error recovery ability contributes to both robustness and overall performance. Our code is available at https://github.com/AlibabaResearch/RoTS.

Cell instance segmentation models trained on cell-specific datasets suffer severe performance drops on out-of-distribution cell types, while interactive foundation models overcome this through per-instance prompting at a cost that is prohibitively expensive for histopathology images containing hundreds to thousands of densely packed instances. We introduce Group Prompting, a new paradigm that shifts interactive segmentation from per-instance $O(N)$ to per-type $O(T)$, where a single click per cell type suffices to segment all instances of that type. Our key observation is that the frozen image encoder of the Segment Anything Model (SAM) already clusters same-type cells in its feature space before any prompt is given. Exploiting this property, we propose Chain-of-Prompts (CoP), a training-free framework that recursively expands a single user click by (1) identifying reliable same-type locations through non-parametric gating of multi-scale encoder features, and (2) selecting the most spatially distant reliable point as the next prompt to maximize coverage. On three cell-type-annotated benchmarks, CoP with one click per type retains over 90% of per-instance performance and surpasses fully-supervised methods without any additional training. On four morphologically homogeneous benchmarks, a single click retains over 99%. Project Page: https://shjo-april.github.io/Chain-of-Prompts/

Vision-Language-Action models have achieved remarkable progress in robotic manipulation, yet they suffer from a critical limitation: a lack of 3D scene understanding. This deficiency manifests as three intertwined challenges: weak extraction of 3D spatial positions without enforcing multi-view consistency, inadequate 3D instance understanding, and fragile reasoning under occlusion. Although mature 3D perception methods exist, their direct integration into VLA pipelines is hindered by architectural incompatibility and by heavy reliance on costly instance-level annotations. To address the above challenges, we propose 3DVLA, a plug-and-play framework that injects robust 3D reasoning into pretrained VLAs without requiring extra manual labels or discarding VLM priors. Specifically, 3DVLA tackles the three challenges through: (1) pervasive 3D feature encoding with explicit multi-view consistency constraints across all modalities and a Spatially-Conditioned Geometry Aggregation method, (2) an instance estimation module with high-level instance tokens for 3D instance awareness, and (3) a masked self-supervised 3D encoding branch that retains its predictor for visual token completion to handle occlusions. We integrate 3DVLA with multiple VLA baselines and evaluate on LIBERO-Plus and RoboTwin 2.0. Results show consistent and significant gains in manipulation performance, validating both the effectiveness and plug-and-play compatibility of our approach.

Task-based assessment of image quality (IQ) is critically important for the design and optimization of medical imaging systems. Ideal observers, including the Bayesian Ideal Observer (IO) and the ideal linear observer, i.e., the Hotelling observer (HO), provide objective figures of merit (FOMs) that quantify system performance on signal detection tasks. However, the application of ideal observers to high-dimensional image data is often computationally intractable. Channel mechanisms provide an effective framework for dimensionality reduction that can facilitate the computation of ideal observers. This work presents a conjugate gradient (CG)-based method to construct efficient channels for approximating the IO and HO performance.

Understanding long-form egocentric videos remains challenging for multimodal large language models (MLLMs) due to limited context length and insufficient grounding of fine-grained visual details. The recently proposed HD-EPIC benchmark highlights these limitations: even strong long-context models achieve relatively low performance across diverse video question answering tasks. In this paper, we propose a unified framework that decouples long-video reasoning into two complementary forms of evidence: semantic evidence and visual evidence. Semantic evidence captures global procedural structure through a coarse-to-fine extraction pipeline, while object-centric visual evidence preserves fine-grained grounding through bounding boxes and visual embeddings. During inference, we formulate reasoning as a query-conditioned evidence retrieval and integration process, dynamically selecting relevant information from both sources. Our approach achieves competitive performance in the HD-EPIC-VQA Challenge across multiple task categories. More broadly, our results demonstrate that explicitly structuring, retrieving, and integrating semantic and visual evidence is critical for effective long-video understanding with MLLMs.

Text-to-image (T2I) models have become increasingly capable of generating high-quality images. Yet, enforcing the explicit absence of a specified object or attribute remains a fundamentally challenging problem. Existing approaches, including prompt negation, post-hoc editing, and negative guidance, remain insufficient for explicit concept suppression, often failing to remove the target concept or degrading overall image quality. To this end, we propose Orthogonal Negative Guidance in attention feature space, a training-free method that operates in the attention output space of MM-DiT-based T2I transformers. Our method orthogonalizes negative-prompt attention features with respect to positive-prompt features and subtracts only the orthogonal component, suppressing unwanted concepts while preserving desired semantics. Experiments on FLUX-dev and FLUX-schnell show that our method achieves favorable trade-offs between concept suppression, prompt alignment, and image quality. In human evaluation, our method outperforms the second-best baseline by 18.78%. We further show that our method supports multi-concept suppression and adjustable concept suppression.

Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastrophic forgetting. In this paper, we develop a theoretical framework for multimodal contrastive finetuning, yielding closed-form solutions and a geometric decomposition for each strategy. This framework shows that self-distillation is more effective than other regularization approaches to retain the knowledge of the pretrained model. Our analysis reveals a largely overlooked limitation: standard Exponential Moving Average (EMA) teachers, widely used in robust finetuning, suffer from collapse. To solve this, we prove that a Weighted Moving Average (WMA) teacher maintains a persistent regularizing force over finite horizons and yields bias-free convergence in the task subspace while preserving orthogonal knowledge. These insights motivate **TRACER** (**T**rajectory-**R**obust **A**nchoring for **C**ontrastive **E**ncoder **R**egularization), which combines contrastive learning with WMA-guided multi-perspective distillation. Extensive experiments on CLIP finetuning demonstrate consistent OOD accuracy and calibration gains across three backbone architectures, and comprehensive ablations confirm that TRACER is both principled and robust to hyperparameter choices. Code is available at [https://github.com/HesamAsad/TRACER](https://github.com/HesamAsad/TRACER).

The proliferation of AI-generated synthetic media poses a critical threat to the integrity of digital evidence in legal and forensic contexts. Existing deepfake detection systems typically address a single modality and provide no mechanism for tamper-proof evidence preservation. We present DeepFake Forensics AI, a unified platform that detects synthetic media across image, video, and audio modalities, identifies generative architecture fingerprints, and anchors forensic evidence immutably on the Ethereum blockchain. Our system trains four independent neural networks from scratch: an EfficientNet-B4 image detector (AUC = 0.9868), a Bidirectional LSTM video detector (AUC= 0.9628), an ECAPA-TDNN audio detector (EER = 18.63%), and a novel GAN fingerprinting module (accuracy = 99.88%) that identifies the generative architecture behind a fake image. Evidence files are hashed with SHA-256, stored on IPFS via Pinata, and registered on-chain via a Solidity smart contract with role-based access control. The platform provides a React frontend and FastAPI backend suitable for deployment in forensic and legal workflows. To our knowledge, this is the first system to unify multi-modal deepfake detection with blockchain-based chain-of custody management.

With the rapid advancement of multimodal large language models (MLLMs), models have demonstrated increasingly powerful multimodal capabilities. However, whether MLLMs trained through statistical learning can truly understand the causal relationships underlying the real world remains a key research question. In recent years, numerous multimodal causal reasoning datasets have been proposed. Nevertheless, these datasets are either limited in scale or constructed from synthetic images and videos, cartoon-based content, or other non-realistic multimodal sources. To address these limitations, we collect real-world videos and construct DMC-CF-Static, a large-scale benchmark for multimodal causal counterfactual reasoning. Furthermore, to mitigate issues such as data contamination in traditional static evaluation, we represent causal events using causal graphs and propose the Dynamic Graph Intervention (DGI) framework to build the dynamic evaluation benchmark DMC-CF-Dynamic from DMC-CF-Static. Experimental results on the overall DMC-CF, which includes both static and dynamic evaluation benchmarks, demonstrate that the multimodal causal reasoning capabilities of current multimodal large language models in real-world scenarios still require substantial improvement.

Fréchet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We show that this mismatch depends in part on the geometry of the reference dataset. In a controlled study across six datasets, distributional density and effective rank significantly explain how FID changes as sample quality improves. Concentrated datasets tend to yield more favorable FID trends, whereas more dispersed datasets can make FID worsen despite better samples. Attribution to precision and recall and ablations with alternative feature spaces and distances support the same conclusion. These results suggest that distributional metrics should be interpreted together with the geometry of the reference dataset for more reliable benchmarking.

Current Earth observation benchmarks focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. But when models are deployed, they must generalize to myriad out-of-distribution scenarios, such as new time periods, geographies, scales, and sensors. We introduce EarthShift: the first public testbed for benchmarking robustness across multiple realistic distribution shifts encountered in remote sensing. EarthShift enables users to measure distributional robustness by comparing performance in- and out-of-distribution using datasets from paired datasets from different sources, temporal windows, geographic locations, and sensors. Our experiments on 8 geospatial foundation models (GFMs) and 11 tasks covering 5 shift types show that GFMs consistently perform 15-20% worse out-of-distribution on average regardless of model architecture, size, pre-training or fine-tuning strategy. We show that GFM robustness is similar to that of generic vision foundation models, and even fully-supervised models. This highlights a need for future research to strive for improvements in distributional robustness, not just performance, which can be benchmarked using EarthShift. We release our code and datasets to provide a testbed to guide future work to create foundation models that are robust and reliable in real-world applications. Code and data for EarthShift are available at: https://earthshift.github.io

We present the 1st-place solution to the ACCIDENT challenge at the CVPR 2026 AUTOPILOT Workshop, which asks for zero-shot prediction of accident timing, impact centroid, and collision type from CCTV footage. On a frozen Qwen3-VL-32B-Instruct checkpoint we build a three-stage pipeline (full-video joint prediction, time refinement, and single-frame grounding of the impact centroid), run the same pipeline a second time on a 235B Mixture-of-Experts sibling, blend the two outputs 9:1, and finally snap each predicted point onto the nearest vehicle detection. The final system reaches Public LB 0.55469 / Private LB 0.57080, roughly +0.21 over the strongest host baseline (Molmo-7B, 0.358) and wins the challenge. We ablate each component, report the negative results that shaped the final design, and release the code at https://github.com/fuumin621/cvpr2026-accident-1st-place-solution.

Mobile GUI agents excel at immediate reactive control but frequently fail in realistic, long-horizon tasks that require memory. This failure stems from a fundamental conflict between limited context windows and token-heavy screenshots. To save the limited context, agents must progressively discard older visual history, permanently losing crucial transient information. Furthermore, existing action-centric datasets fail to teach agents what or when to explicitly memorize, and augmenting static real-world data is prohibitively expensive and lacks interactive verification. To resolve this, we present STAMP, a framework that trains explicit memory in mobile agents through controllable virtual environments, where deterministic memory variables are programmatically injected into synthesized tasks to control what must be memorized, when it should be encoded, and when it must later be retrieved, thereby producing verifiable supervised data at scale and enabling online reinforcement learning through environment-driven reward feedback. Evaluated on our newly introduced Memory-World benchmark, the resulting Stamp-GUI agent achieves state-of-the-art performance among GUI-specialized models and sets a new high watermark on our Memory-World benchmark, demonstrating exceptional memory accuracy and task resilience while maintaining strong general mobile navigation capabilities.

We present a novel formulation for mesh-free, reduced-order simulation of deformable hyperelastic objects. Existing work in reduced-order elastodynamic simulation represents the input geometry by either meshes, which can be difficult to obtain due to challenges in scanning and triangulating complex shapes, or by neural fields that require per-shape optimization. We propose to adopt a Reproducing Kernel Particle Method (RKPM) representation, which enables the construction of reduced-order skinning weights by solving a generalized eigensystem on the Hessian matrix of the elastic energy. We demonstrate that this formulation not only leads to a 40x training speedup compared with the per-shape optimization of neural fields, but also achieves lower simulation error when evaluated against the converged results of finite element method. We show our simulation results on a wide variety of objects in different representations including meshes and Gaussian splats, as well as the application of our method in the downstream task of robot simulation.

Audio-driven 3D facial animation aims to generate synchronized lip movements and vivid facial expressions from arbitrary audio clips. While existing methods can produce synchronized lip motions, they often rely on predefined identity or style latent features, which limits users' ability to freely control speaking styles. Moreover, applying a fixed style or identity to an entire audio segment typically results in facial animation styles that do not adapt to the emotional content of the audio. To address these challenges, we revisit the entanglement between style and emotion, construct a large-scale dataset with textual descriptions of both style and emotion, and propose a novel talking head generation framework that enables separate control over style and emotion. Our model takes as input both textual descriptions of speaking style and character emotion, as well as the driving audio stream, enabling real-time generation of highly synchronized lip movements and facial expressions that match the provided descriptions. Furthermore, our model supports dynamic emotion control during inference, allowing it to handle scenarios where the target emotion changes throughout the speech.

The digital media landscape has seen a pervasive shift toward short-form video advertising on TV, social media and e-commerce platforms. The present study focuses on deep saliency prediction for short-form video advertising. Deep saliency models have been used to generate predictions of human eye fixation patterns with the purpose of enhancing user interaction with digital technology and optimizing its design. For video ads, dynamic saliency maps capture where and when viewers are looking, revealing why video ads are effective, and how their content should be optimized. We develop and test a new deep dynamic saliency prediction model called ViASNet (Video Ad Saliency Network), which has an architecture founded on the 3D U-Net, and accommodates the influence of audio and the semantic meaning of scenes. We assess the model's performance on 151 video ads, each seen by about 20 viewers wile their eye movements were tracked, and explore the critical factors influencing model performance through ablation experiments. We calculate the entropy of the predicted saliency maps frame-by-frame as a diagnostic tool to identify ads and scenes that fail to engage viewers, and illustrate its use on test data of 15 unseen ads. Our study reveals that ad design and testing can be sped up considerably through automated systems built on deep saliency models such as ViASNet.

Age estimation from facial images typically relies on training data that includes images of minors, a practice that raises serious ethical, legal, and privacy concerns. In this work, we propose a generalized zero-shot benchmark for facial age estimation that explicitly excludes children's data during training while still assessing model performance on younger populations. We revisit six widely used datasets and introduce standardized splits with strict age-group separation: samples aged 18-59 for training, validation, and testing; samples under 18 reserved exclusively for zero-shot evaluation; and samples 60+ as an unseen validation set for model selection under distribution shift. For datasets with identity annotations, subject-exclusive splits prevent identity leakage and better reflect real-world deployment conditions. Evaluating nine state-of-the-art age estimation methods under this protocol reveals that all evaluated methods consistently fail to generalize to unseen age groups, suffering substantial performance degradation -- on average 46.4%, and up to 52.8% -- relative to the supervised baseline. Moreover, models do not simply degrade: they systematically anchor predictions for unseen ages to nearby seen classes, a manifestation of the well-known seen-class bias in generalized zero-shot learning. By formalizing age estimation without children's data as a generalized zero-shot benchmark on existing datasets, this work highlights a critical gap between current modeling practices and real-world ethical constraints. Our benchmark provides a principled basis for evaluating models under restricted data regimes and encourages the development of methods that are robust to distribution shift and aligned with responsible data use.

Thyroid cancer is said to be the second most common type of cancer in female individuals and the third in males by 2030, according to projections. In general, detecting cancer in its early stages improves the chance of survival of the individual. Thermography is a diagnostic tool that has been increasingly used to detect cancer and abnormalities, including that of thyroid. Various methods to segment and detect hot regions in thermograms and, consequently, to detect suspicious tissues present in these images have been proposed. It is well known that medical diagnosis yields a great deal of information. Thus, physicians have to comprehensively analyse and evaluate this information in a short period of time, which is infeasible in most cases. In this work, we perform a general review of thermography , focusing on the thyroid analysis. We propose protocols for image acquisiton and an autonomous registration for thyroid images. We also perform analyses of the image data, which include feature extraction, image processing, and a possible approach for classification of healthy or unhealthy patients. In summary, this work presents a pilot project for detection of tumors in our university hospital, which is part of an effort to support preventive medical actions in our endocrinology department. Under some future adjustments, this project will be submitted for approval by the ethics and research committee of Hospital Universitário Antonio Pedro at Universidade Federal Fluminense (HUAP-UFF) and to the Brazilian Ministry of Health Ethical committee under the name: Evaluation of the importance of thermography to aid diagnosis of thyroid nodules of patients in HUAP-UFF (in Portuguese: Avaliação da importância da termografia no auxílio à investigação diagnóstica de nódulos tireoidianos em pacientes acompanhados no HUAP-UFF).