Large Vision Language Models

Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal mechanisms governing how LVLMs translate abstract visual stimuli into coherent emotional narratives remain largely unexplored, primarily due to the scarcity of visual counterfactuals and the diffuse nature of emotional expression. In this paper, we bridge this gap by introducing a steering-vector-based causal attribution framework tailored for descriptive emotional reasoning. To this end, we construct a specialized dataset to demystify the emotional circuits underlying the three-stage ``Adapt-Aggregate-Execute'' mechanism. Crucially, we discover a functional decoupling: visual emotional cues are aggregated in middle layers via sentiment-specific attention heads, but are subsequently translated into narrative generation in deep layers through emotion-general pathways. Guided by these insights, we regulate the emotional information routing to strengthen attention flow and amplify the semantic activation to consolidate expression. Extensive experiments on the comprehensive MER-UniBench demonstrate that our methods significantly improve performance via inference-time intervention, effectively mitigating emotional hallucinations and corroborating the causal fidelity of the discovered circuits.

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality while failing to strengthen its reliance on visual input: on vision-critical tokens, the student's predictions remain largely unchanged whether or not fine-grained visual detail is present, even though the teacher's predictions depend heavily on it.To make this difference observable, we introduce visual advantage (VA), the token-level log-probability difference when the teacher scores a student-generated rollout with versus without access to fine-grained visual detail. VA is concentrated in a small minority of tokens, and these high-VA tokens are the ones that actually carry the visual supervision signal. This motivates a distillation objective that treats them differently from language scaffolding, so their contribution is not diluted by the abundant surrounding language tokens.We propose Visual-Advantage On-Policy Distillation (VA-OPD), which uses VA at two granularities: rollout-level reweighting by trajectory-averaged VA, and token-level KL averaged within high-VA and low-VA groups separately. We train on two math datasets (Geometry3K and ViRL39K) and evaluate on eight benchmarks covering both mathematical reasoning and visual understanding, across three teacher sizes (4B, 8B, and 32B) on the Qwen3-VL family. VA-OPD improves over standard on-policy distillation on every benchmark, with the gain growing monotonically along both the teacher-size and data-scale axes, suggesting that these factors compound consistently.

Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development indicators, where incomplete evidence use and imperfect evidence integration can introduce hidden prediction biases. Real-world SDG monitoring further spans both qualitative judgments and quantitative estimation. However, existing benchmarks typically evaluate these aspects in isolation, obscuring systematic biases that emerge when models substitute priors for evidence. To address this gap, we propose SDGBiasBench, a large-scale benchmark suite for SDG-oriented vision-language reasoning. Spanning 500k expert-involved multiple-choice questions and 50k regression tasks, the benchmark enables comprehensive assessment of both decision-level and estimation-level bias in Vision--Language Models (VLMs). Evaluations on SDGBiasBench reveal an intrinsic SDG bias in current VLMs, where predictions are frequently driven by SDG specific priors rather than reliable multi-modal cues. To mitigate such bias, we propose CADE (Contrastive Adaptive Debias Ensemble), a training-free, plug-and-play method that leverages modality-specific answer priors. CADE yields significant gains on the proposed benchmark, improving multiple-choice accuracy by up to 25% and reducing regression MAE by up to 12 points across multiple VLMs. We hope our work can foster the development of more fair and reliable AI systems for sustainable development.

Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support. We present MAVEN (Multi-stage Agentic Video Event aNnotation), a multi-stage agentic pipeline that turns raw videos into multi-task training data with Chain-of-Thought (CoT) reasoning traces, organized around a designated Event of Focus. At its core, MAVEN synthesizes a Multi-Scale Spatio-Temporal Event Description (MSTED) from three complementary caption levels; this explicit intermediate serves as the sole input to downstream Q&A generation across multiple task formats. Crucially, MAVEN supports agent-driven domain adaptation: given a new video dataset and target question examples, the agent redesigns all prompts top-down without manual re-engineering. A hierarchical refinement loop further classifies annotation errors against a taxonomy, traces root causes to the originating pipeline stage, and applies targeted edits that rewrite prompts or modify the pipeline structure itself, iteratively improving data quality. We apply MAVEN to label over 5,300 traffic videos and fine-tune Cosmos-Reason2-8B on the resulting data. On a private CCTV evaluation set, fine-tuning surpasses both Gemini 2.5 Pro and 3.1 Flash, including a $+38.8$-point gain in MCQ accuracy over zero-shot. On AccidentBench, CCTV-only training lifts Cosmos-Reason2 by $+10.7$ MCQ points and matches Gemini 2.5 Pro despite seeing no dashcam videos; adding agent-adapted dashcam annotations narrows the gap to Gemini 3.1 Flash, and RL post-training pushes overall performance past both Gemini baselines. Qualitative results on warehouse surveillance and public safety videos further show the agentic workflow readily adapts the pipeline to new domains.

Vision-language models (VLMs) often fail under low illumination because their visual grounding is learned predominantly from RGB imagery, whereas thermal infrared preserves complementary scene structure when visible cues degrade. We present Thermo-VL, a wavelength-aware VLM that augments a frozen Molmo-7B backbone with a trainable thermal encoder and a text-guided dual-attention fusion module. Given aligned RGB tokens, thermal tokens, and prompt embeddings, the fusion module conditions thermal features on both language and RGB context, then injects a gated residual into the frozen RGB stream so thermal evidence can be incorporated without disrupting Molmo's pretrained RGB-language interface. We train the model with the standard language-modeling objective together with auxiliary alignment and regularization losses that improve cross-modal grounding and reduce over-reliance on RGB. We also introduce a pixel-aligned RGB-thermal instruction-tuning dataset and Thermo-VL-Bench, a manually screened RGB-thermal VQA benchmark for low-light and cross-spectrum reasoning. Experiments show strong gains on challenging thermal-only and RGB+thermal reasoning tasks, highlighting the value of prompt-conditioned multispectral fusion. Our dataset and code are publicly available at: https://thusharakart.github.io/Thermo-VL

Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing (1) a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry, and (2) a two-stage grounding pipeline that explicitly resolves conversational ambiguity before visual localization. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types. Our contextual rewriting approach improves grounding performance by 11-22 percentage points on average, with a pure detector (GroundingDINO) reaching 56.7% on pronominals after rewriting, nearly double the best end-to-end baseline. Results demonstrate that decoupling linguistic reasoning from visual perception is more effective than end-to-end approaches for conversational grounding.

Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relationships from 2D views, which are subsequently lifted into a persistent 3D scene graph encoding both spatial and semantic relations. Given a query, we construct a query graph and perform constrained alignment with the scene graph, ensuring multi-view consistency and interpretable reasoning. Experiments on the ScanRefer benchmark demonstrate that our method achieves competitive performance among zero-shot approaches, using only RGB-D inputs. We further validate our framework through real-world deployment on a mobile robot, demonstrating robust spatial reasoning in long-horizon physical environments. We will make our code publicly available upon acceptance.

Vision-language models (VLMs) are increasingly augmented with continuous or latent non-textual tokens intended to support "visual thinking." Despite improved task accuracy, this alone does not show that models actually use these tokens for reasoning -- gains may arise from confounds such as added context length, special-token anchoring, or training-time regularization. We formalize a diagnostic principle, Ablate-to-Validate, for testing whether latent-token content is genuinely utilized, and instantiate it as the Token Replacement Test (TRT), a standardized suite of content-replacement ablations. TRT holds the prompt, image, token budget, and decoding fixed while replacing intermediate tokens with zero, random, first-repeat, or oracle alternatives, isolating whether performance depends on token content or merely on token presence. As a controlled testbed, we study relative depth reasoning with LLaVA-13B and Qwen2.5-VL-3B, training models to predict and consume continuous or discrete depth spans across multiple frozen encoders (SigLIP2, CLIP, DINOv2) and token budgets. We additionally apply TRT to three off-the-shelf visual-thinking systems (Mirage, Mull-Tokens, CoVT) on BLINK, VSP, and CV-Bench. Across all settings, accuracy gains are a misleading proxy for latent-token reasoning: VLMs retain most improvement even when token content is corrupted or replaced, revealing a persistent gap between having a latent channel and using it as an information bottleneck. We recommend TRT as a standard diagnostic alongside accuracy for any method introducing continuous thought tokens.

The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification, captioning, and retrieval. Furthermore, these benchmarks often rely on entities that can be easily identified verbally, like household objects, animals, human subjects, etc., limiting their applicability to complex, in-the-wild video scenarios. But, many applications such as furniture assembly, cooking, etc., require step-by-step fine-grained spatio-temporal understanding of the video, which is not sufficiently evaluated in current benchmarks. To address this gap, we introduce Flat-Pack Bench, a novel benchmark centered on furniture assembly tasks. Our benchmark evaluates LVLMs on nuanced tasks, including temporal ordering of assembly actions, temporal localization of assembly state, understanding part mating, and tracking, using multiple-choice questions paired with visual prompts highlighting relevant parts as references for fine-grained questions. Our experiments reveal that state-of-the-art LVLMs struggle significantly with fine-grained spatio-temporal reasoning, highlighting their limitations in effectively leveraging temporal information from videos, limited tracking ability, and understanding of spatial interactions like physical contact.

We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of supplying a reference image and a global text prompt through two separate encoders, one for vision and one for language, UniVL is trained to bind semantics to spatial locations directly from a single unified visual input, where the textual instruction is rendered onto the spatial mask. This removes the need for a standalone text encoder at inference time. The resulting model supports contextual image generation by following user-specified instructions about what should appear where, while substantially reducing computation. To address this task, we propose a framework in which the UniVL encoder, adapted from an optical-character-recognition-pretrained backbone, reads the unified condition optically and produces a UniVL embedding, fVIL, that fuses visual and semantic intent with spatial locations in a single token sequence. A two-stage pipeline first aligns UniVL with the VAE embedding space and then conditions a pretrained diffusion backbone entirely on UniVL embeddings, eliminating the standalone text encoder, such as T5. Although this reframing uses a deliberately minimal text interface, it yields strong empirical gains. On UniVL-ImgGen, a benchmark of 477K mask-annotated images that we construct for training and evaluation, UniVL improves image quality over text-prompted baselines, reducing FID from 14 to 11 and increasing PSNR from 16 to 20. It also eliminates the text encoder entirely, reducing inference TFLOPs by up to 52% and runtime by up to 44%. Additional ablation studies validate the contributions of the proposed components, paving the way for efficient, spatially grounded image generation with a unified conditioning paradigm.

Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce WikiVQABench, a human-curated knowledge-grounded VQA benchmark constructed by systematically combining Wikipedia images, their associated article captions, and structured knowledge from Wikidata. Our pipeline uses large language models (LLMs) to generate candidate multiple-choice image-question-answer sets. All generated instances are subsequently reviewed and curated by human annotators to ensure factual correctness, visual-text consistency, and that each question requires external knowledge in addition to visual evidence for correct resolution. WikiVQABench comprises a substantial collection of Wikipedia images with curated multiple-choice questions designed to benchmark knowledge-aware vision-language models (VLMs). Evaluation of fifteen VLMs (256M-90B parameters) reveals a wide performance range (24.7%-75.6% accuracy), demonstrating that the benchmark effectively discriminates model capabilities on knowledge-intensive reasoning. The dataset and benchmarking code are publicly available.

Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation over meaningful interaction with images. To explore this, we examine the generation process and categorize text tokens into three groups: image-positive, invariant, and negative, based on their visual dependence on input image tokens. Our analysis reveals that most generated tokens are minimally influenced by the image information. This suggests that during the model's training stage, more emphasis is placed on learning how to follow textual instructions, rather than extracting information from images. Based on this finding, we propose adjusting the training weights of different tokens depending on their visual dependence to control hallucination. Additionally, we remove a portion of the training data that potentially contains more hallucinations as a data filtering strategy. Both methods achieve a reduction in hallucination without compromising response length or introducing additional computational costs during inference. We validate our methods across three LVLM variants, demonstrating the effectiveness and general applicability.

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual tokens receive attention, the final token decision can be dominated by the textual pathway, causing the decoder to follow linguistic priors over visual evidence. To mitigate this, we propose a training-free, decision-aligned intervention that decomposes each attention head into a visual route and a text route, and estimates their token-level effects using an efficient one-forward/one-gradient approximation. These estimates reveal route conflict within heads and identify prior-dominant ones, enabling selective suppression of only the text route while keeping the visual route intact. Across five benchmarks spanning discriminative and generative settings, our method consistently reduces hallucination-related errors across models with limited impact on overall multimodal performance, while incurring a modest inference-time overhead.

Understanding surgical workflow in real time is fundamental for intelligent surgical embodiment, where AI systems continuously perceive and respond as surgery proceeds. In the operating room, critical decisions depend on subtle, moment-to-moment changes, such as fine instrument movements and evolving tissue states, where even slight perceptual delays can limit assistance or compromise safety. Yet existing methods remain offline or operate at coarse temporal scales, generating descriptions only after processing clips, preventing immediate reaction. We address this by proposing SurgOnAir, a streaming vision-language model that processes frames sequentially without future access and progressively generates narration tokens as visual input arrives. SurgOnAir achieves fine-grained frame-to-token generation, enabling instant responsiveness to evolving surgical dynamics. Built upon our curated hierarchical dataset SurgOnAir-11k spanning action-, step-, and phase-level supervision, the model is trained to produce multi-level textual responses that reflect the inherent hierarchy of surgical procedures. Furthermore, special transition tokens are generated to explicitly mark state changes, allowing SurgOnAir to capture and signal key workflow transitions as they occur. Experiments show that SurgOnAir enables real-time understanding through a single vision-language model that unifies streaming across multiple hierarchies of the surgical workflow, generating superior and hierarchy-aware narrations. Code and dataset will be public.

Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still prone to hallucination, generating responses that are inconsistent with visual content. In this work, we find that LVLMs tend to hallucinate when they pay insufficient attention to the correct visual evidence and gradually forget it during the generation process. We empirically find that although LVLMs overall attend insufficiently to visual evidence, they exhibit sensitivity to the correct visual evidence in specific layers, with notable inter-layer discrepancy. Motivated by this observation, we propose a novel hallucination mitigation method that enhances visual evidence based on Inter-Layer Visual Attention Discrepancy (ILVAD). Specifically, we obtain the attention weights from early generated tokens to visual tokens across layers and identify the tokens that are repeatedly activated as visual evidence, forming a saliency map. We then enhance attention to visual evidence during generation through the saliency map to reduce visual forgetting. In addition, we leverage the saliency map to obtain attention scores of generated text to visual evidence, in order to select and emphasize text tokens that are strongly grounded in visual evidence. Our method is training-free and plug-and-play. Multiple benchmark evaluations conducted on five recently released models show that our method can consistently mitigate hallucinations in different LVLMs over various architectures. Code is available at https://github.com/ytx-ML/ILVAD.

Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-language models (VLMs) offer promising semantic flexibility, they lack the geometric and relational grounding required for precise road reasoning. Conversely, traditional modular systems, e.g., HD maps and topological road graphs, provide structural precision but remain semantically rigid. To bridge this gap, we introduce the Combined Road Substrate (CRS), a graph-grounded framework that makes geometric road structure and open-vocabulary semantics jointly executable in a single representation. CRS enables the automatic generation of compositionally complex and linguistically varied question-answer pairs via recursive graph queries, augmented with a "grounding for free" mechanism that ensures logical traceability to specific map elements, and procedurally extracted chain-of-thought supervision traces. We demonstrate that state-of-the-art VLMs - including large, closed-source models - struggle significantly with structured road reasoning, yet training a small 2- or 4-billion-parameter model with as few as 20 to 80 CRS-enriched scenes yields stable gains in compositional reasoning tasks of varying depth. Analysis of model behavior via verifiable reasoning traces reveals a systematic shift in failure modes: whereas baseline models fail at relational scene understanding, CRS-trained models reduce failures to attribute recognition, suggesting that the primary bottleneck in road understanding is not model scale, but the absence of structured supervision.

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

Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-based video editing. The prevailing assumption underlying this paradigm is that a connector module can seamlessly align the VLM's rich multi-modal reasoning with the original text embedding space of DiTs. However, we hypothesize that this alignment acts as a severe semantic bottleneck, degrading fine-grained structural variables. Verifying this is challenging, as end-to-end evaluations conflate alignment failures with generation errors, and natural datasets lack disentangled annotations. To rigorously investigate this, we propose a controlled data processing pipeline based on video composition that results in TRACE-Edit, a diagnostic dataset focusing on relation-based editing. Leveraging this dataset, we propose a comprehensive diagnostic protocol to analyze two important designs of meta-query and connector in the existing video editing models. Systematic evaluation of four representative model cases reveals that fine-grained structural semantics can be severely degraded during alignment. Our findings overturn the assumption of lossless semantic transfer, identifying the VLM-to-DiT alignment as a major bottleneck and providing a new diagnostic foundation for future multi-modal alignment architectures.

Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent agents across three key vision-language tasks: image captioning, visual dialog, and interactive instruction following. First, we address limitations in visual representation for image captioning. Traditional models rely on region-based features from CNN detectors, which lack global context and suffer from high computational overhead. We propose GRIT (Grid and Region-based Image captioning Transformer), a transformer-only architecture. By integrating grid and region features using a DETR-based detector, GRIT enables end-to-end training and out-performs prior methods in both inference accuracy and speed. Second, we tackle visual dialog, which requires multi-turn conversation about an image. The challenge lies in efficiently modeling interactions between multiple inputs (image, question, history). We introduce LTMI (Light-weight Transformer for Many Inputs). Utilizing a specialized attention block, an LTMI layer matches the representational power of a standard Transformer extension while utilizing less than one-tenth of its parameters, as validated on the VisDial dataset. Finally, we study interactive instruction-following for embodied AI using the ALFRED dataset. We propose a framework featuring a two-stage instruction interpretation: it first decodes language directives independently of visual context to predict a tentative action-object sequence, which is then fused with visual features for final execution. Using multiple egocentric views and hierarchical attention, our method accurately localizes objects and achieves a state-of-the-art unseen success rate of 8.37%.

Experienced physicians develop diagnostic expertise through clinical practice, acquiring not only disease knowledge but also the ability to differentiate confusable conditions. Current medical vision-language models (VLMs) lack this capability -- their parameters encode static knowledge that does not evolve across diagnostic encounters. We propose MedExpMem, an experience memory framework enabling VLM-based diagnostic agents to accumulate differential diagnosis expertise. Unlike retrieval-augmented generation, which retrieves encyclopedic disease descriptions, MedExpMem memorizes discriminative experience derived from the agent's own diagnostic failures and organizes them as pairwise differential notes encoding key discriminators, actionable decision rules and reasoning error patterns. The framework adopts a two-phase construction process mirroring physician learning: initial practice exposes knowledge gaps, and reflective re-diagnosis refines understanding. When encountering new cases, the agent retrieves experience memory to guide differential reasoning. We evaluate MedExpMem on a radiology benchmark spanning 11 subspecialties. Results demonstrate consistent accuracy improvements, maximum 7.0%, across diverse models and scales. Analytical experiments validate experience quality and robustness, demonstrating MedExpMem as a competitive method addresses medical adaptation needs beyond the reach of parameteric learning.

Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or restricted content. Ensuring the accuracy and consistency of these disclosures remains challenging due to the multimodal nature of app content, which spans textual descriptions and visual interfaces. In this paper, we present QwenSafe, a Vision-Language Model (VLM) designed to automatically identify the presence of Apple-defined CRDs by jointly reasoning over app metadata and screenshots. To enable scalable training for this task, we introduce metadata2CRD, a data-construction pipeline that synthesizes descriptor-aligned question-answer pairs by combining app descriptions, screenshots, and formal descriptor definitions. We adapt Qwen3-VL-8B using supervised fine-tuning followed by Direct Preference Optimization (DPO) to align model predictions with descriptor-specific evidence and explanations across visual and textual modalities. We evaluate QwenSafe on 12 Apple-defined content rating descriptors and compare it against state-of-the-art vision-language models, including Qwen3-VL, LLaVA-1.6, and Gemini-2.5-Flash. QwenSafe consistently outperforms all baselines in binary CRD classification, achieving improvements in positive-class recall of 111.8%, 36.1%, and 2.1%, respectively. Our results demonstrate that descriptor-aware multimodal alignment substantially improves automated content classification and highlights the potential of vision-language models to support scalable and consistent content rating in mobile app marketplaces.

Inferring rigid-body physical states and properties from monocular videos is a fundamental step toward physics-based perception and simulation. Existing approaches assume specific underlying physical systems, object types, and camera poses, making them unable to generalize to complex real-world settings. We introduce $Δ$YNAMICS, a vision-language framework that uses language as a unified representation of rigid-body dynamics. Instead of directly predicting parameters, $Δ$YNAMICS generates scene configurations in a structured text format for physics simulation. We enhance the model's generalization by integrating natural language motion reasoning and leveraging optical flow as a semantic-agnostic input. On the CLEVRER dataset, $Δ$YNAMICS achieves a segmentation IoU of 0.30, a 7x improvement over leading VLMs (InternVL3-8B, Qwen2.5-VL-7B and Claude-4-Sonnet). Additionally, test-time sampling and evolutionary search further boost performance by 27% and 120% in segmentation IoU, respectively. Finally, we demonstrate strong transfer to a new dataset of 235 real-world rigid-body videos, highlighting the potential of language-driven physics inference for bridging perception and simulation.

Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large language model-based pipelines; however, existing frameworks remain limited to textual and tabular content, overlooking the substantial proportion of quantitative property data reported exclusively in scientific figures. Here, we extend ComProScanner, a fully end-to-end multi-agent framework for automated composition-property database construction, with a native vision-language model (VLM) based figure extraction capability. The extension introduces a FigureExtractor utility for caption-keyword-based figure filtering across all supported publishers, and a GraphExtractorTool agent that passes extracted figures to a configurable VLM to recover composition-property pairs from scientific charts and plots. Four VLMs are selected for evaluation on the basis of the LMArena Diagram leaderboard with an input cost criterion of less than $1.50 per million tokens. Benchmarking on 50 piezoelectric ceramic articles from the established $d_{33}$ test corpus demonstrates that Gemini-3-Flash-Preview achieves the highest performance with a composition accuracy of 0.97 and a normalised F1 score of 0.97, whilst remaining the most cost-effective model among the four evaluated. We additionally introduce a range-based value error threshold parameter into the evaluation framework, providing a more physically meaningful assessment of numeric property values extracted from figures than exact value matching. These contributions establish VLM-integrated ComProScanner as the first materials-specific, fully automated, multimodal literature mining platform capable of extracting structured composition-property data from text, tables, and figures within a single unified pipeline.

Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality ground truth for training. Recent work has shown that prompt tuning of vision-language models (VLMs) can reduce manual annotation by constructing a small prompt set of expert-verified image-caption exemplars that is reused as few-shot context to classify all remaining images at inference time. To further reduce effort, the VLM can draft captions for candidate exemplars, which experts then verify and lightly edit instead of writing text de novo. However, two practical questions remain unaddressed: (1) which unlabeled images should be prioritized for verification, and (2) how many verified exemplars are needed to reach a performance target. In this work, we address these questions by formulating prompt-set construction as a target-driven active learning problem that prioritizes which images to annotate. We study three complementary selection criteria under strict low-resource constraints with small unlabeled pools. Experiments show that our methods reach the target performance with substantially fewer expert-verified images than random selection, achieving 100% test accuracy with as few as 20 annotated images on average. More broadly, our human-in-the-loop framework demonstrates a human-centered use of generative AI in biomedical image analysis, where experts remain actively involved in verifying and refining model output while significantly reducing annotation cost. Code and data will be publicly available.

Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through large-scale joint pretraining or substantial retraining of the text pathway, discarding the strong image prior the text-to-image backbone already encodes. We introduce \emph{FullFlow}, a parameter-efficient recipe that upgrades a pretrained rectified-flow text-to-image model into a bidirectional vision--language generator by training only LoRA adapters and lightweight text heads. FullFlow keeps images in their native continuous flow and adds a discrete insertion process for text. Separate image and text timesteps turn inference into trajectory selection in a two-dimensional generative space, enabling text$\rightarrow$image, image$\rightarrow$text, joint sampling, and partial-text prediction with a single backbone. On Stable Diffusion 3 (SD3) under an identical trainable-parameter count and matched LoRA rank, FullFlow improves text$\rightarrow$image FID from $62.7$ to $31.6$ and image$\rightarrow$text CIDEr from $2.0$ to $99.4$ over a LoRA equivalent following the previous SOTA formulation (Dual Diffusion) at matched wall-clock training time, while reducing peak VRAM from ${\sim}84$,GB to ${\sim}38$,GB and raising throughput by ${\sim}8\times$ on two RTX A5000 GPUs in under 24 hours, training only ${\sim}5\%$ of the backbone parameters. The same recipe transfers to FLUX.1-dev and supports downstream VQA through partial-text generation. These results show that strong bidirectional vision--language capability can be unlocked from pretrained text-to-image flow models without full multimodal pretraining.

Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of visual perception as opposed to reasoning itself. In this work, we systematically study the interplay between perception and reasoning in VLM post-training by decomposing their capabilities into three separate training stages: visual perception, visual reasoning, and textual reasoning, incorporating specialized training data. We demonstrate that visual perception (a) requires targeted optimization with specialized data; (b) serves as a fundamental scaffold that should be solidified through staged training before refining visual reasoning; and (c) is more effectively learned via RL than caption-based SFT. Our experiments across multiple VLMs demonstrate that staged training consistently improves both visual perception and reasoning performance over merged training. Notably, models trained with our approach achieve 1.5% higher reasoning accuracy with 20.8% shorter reasoning traces, suggesting that superior perception reduces the need for excessive reasoning. Furthermore, we show that this capability-based staging represents a new curriculum dimension orthogonal to traditional difficulty-based curricula, and combining both yields further additive gains. Our staged-training models achieve superior performance among open-weight VLMs, establishing advanced results on several visual math and perception (e.g., +5.2% on WeMath and +3.7% on RealWorldQA) tasks compared with the base counterpart.

Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explanations actually reflect the visual evidence underlying the model's decision is largely unverified, since ground-truth annotations for internal model reasoning are typically unavailable. We address this question for chest X-ray (CXR) reasoning by developing a causal evaluation framework that retains only CXR-VQA samples for which the expert-annotated region is verified, via counterfactual editing, to be causally responsible for the model's prediction. Using this framework across 11 attribution methods, six open-source LVLMs, and two output modes (direct answer and step-by-step reasoning), we find that existing attribution methods often fail to identify the evidence used by LVLMs. To address this failure, we propose MedFocus, a concept-based attribution method that localizes clinically meaningful anatomical regions via unbalanced optimal transport and measures their causal effect on model outputs through targeted interventions. MedFocus produces spatial, concept-level, and token-level attributions and substantially outperforms prior methods, taking a step toward more trustworthy attribution for medical LVLMs. Our data and code are available at https://github.com/gzxiong/medfocus/.

Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended target sets remains challenging. Previous Large Vision Language Model (LVLM)-based methods represent referred targets with one or more special tokens sequentially, treating multiple targets as separate outputs rather than a coherent set and offering little incentive to capture set-level properties such as completeness and mutual exclusivity. We reformulate open-ended referring segmentation as explicit set-level concept prediction and propose Set-Concept Segmentation (SetCon), which uses LVLM-generated natural-language concepts, instead of segmentation-specific tokens, as semantic conditions for joint mask-set decoding. A hierarchical semantic decomposition first predicts a shared set-level concept defining the target scope and then refines it into fine-grained concept groups aligned with target subsets. To support this, a two-stage annotation pipeline augments existing reasoning segmentation datasets with hierarchical semantic supervision (236k samples, 784k concept phrases). SetCon achieves state-of-the-art results on image benchmarks (+3.3 gIoU on gRefCOCO, +12.1 gIoU on MUSE), with margins that grow as the number of referred targets increases. The concept interface also transfers to video under a detect-and-track setting, yielding new state-of-the-art results on seven referring video benchmarks, including +10.9 J&F on MeViS and +12.4 J&F on Ref-SeCVOS.

Short-form video poses new challenges to the quality assessment of user-generated content (UGC) due to its complex generation pipeline, rapid content variation, and mixed distortions. To address this challenge, we propose an end-to-end video quality assessment (VQA) framework that employs a dense visual encoder based on CLIP, and incorporates compression priors derived from the frequency domain to generate artifact- and structure-aware weight maps for feature aggregation. By explicitly decomposing artifact, structure, and original visual feature branches and adaptively fusing them over time through a learned gating module, the proposed method achieves accurate and efficient quality prediction. Experimental results show that our method achieves strong performance on short-form video datasets in terms of average rank and linear correlation (SRCC: 0.736, PLCC: 0.787), while maintaining efficient inference runtime. The code and additional results are available at: https://github.com/xinyiW915/FGSVQA.

Construction remains the deadliest industry sector in the United States, with 1,055 fatal worker injuries recorded in 2023, and the majority preventable. Existing monitoring approaches are expensive, require real-time human operators, or address only a narrow subset of violations. This paper presents a passive, end-of-shift construction safety monitoring pipeline processing video from POV body-worn and fixed wall-mounted cameras through a three-stage architecture: (1) fine-tuned YOLO11 for primary PPE and hazard detection, (2) SAM 3 for segmentation refinement and worker deduplication, and (3) Qwen3-VL-8B-Instruct with a method-prompted, persona-scaffolded three-pass adversarial chain-of-thought protocol for compliance verification and hallucination control. The principal contribution is the Stage 3 prompt design: professional persona backstories following the method-actor framing drive an observed 12% precision improvement over single-pass prompting in an informal three-author review of the 12-video Ironsite development corpus, with the largest gains on hallucination-prone violation categories. Structural message isolation enforces observational independence between a generator, discriminator, and reconciliation pass governed by asymmetric rules encoding priors about human observation versus automated detection reliability. The system maps violations to OSHA standards, performs REBA-inspired ergonomic risk scoring from pose keypoints, and produces per-worker safety reports with timestamped evidence. An evaluation harness is released for future reproduction.

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of human actions and interactions. While some recent human-centric benchmarks evaluate aspects of model behaviour such as fairness/ethics, emotion perception, and broader human-centric metrics, they do not combine long-form videos, very dense QA coverage, and frame-level spatial/temporal grounding at scale. To bridge this gap, we introduce FineBench, a human-centric video question answering (VQA) benchmark specifically designed to assess fine-grained understanding. FineBench comprises 199,420 multiple-choice QA pairs densely annotated across 64 long-form videos (15 minutes each), focusing on detailed person movement, person interaction, and object manipulation, including compositional actions. Our extensive evaluation reveals that while proprietary models like GPT-5 achieve respectable performance, current open-source VLMs significantly underperform, struggling particularly with spatial reasoning in multi-person scenes and distinguishing subtle differences in human movements and interactions. To address these identified weaknesses, we propose FineAgent, a modular framework that enhances VLMs by leveraging a Localizer and a Descriptor. Experiments show that FineAgent consistently improves the performance of various open VLMs on FineBench. FineBench provides a rigorous testbed for future research into fine-grained human-centric video understanding, while FineAgent offers a practical approach to enhance such reasoning in current VLMs. Project page and code at https://joslefaure.github.io/assets/html/finebench.html.

Facial Expression Recognition (FER) in the wild requires models to identify subtle expression cues under large variations in pose, occlusion, illumination, and identity. Recent FER methods improve robustness by introducing visual attention, facial landmarks, or vision-language models as auxiliary priors. However, these priors are typically integrated in a static manner, failing to capture instance-specific facial variations, thereby resulting in severe attention redundancy and representation instability. To address this issue, we propose LaCoVL-FER, a landmark-guided contrastive learning network with vision-language enhancement for FER, which shifts FER from static prior injection to sample-adaptive prior refinement. Specifically, a Landmark-Guided Adaptive Encoder (LGAE) calibrates regional appearance features with landmark geometry through Bi-branch Gated Cross Attention (BGCA), suppressing noisy responses and producing expression-relevant representations. In parallel, a Vision-Language Enhancement Strategy (VLES) refines the generalizable visual features from a frozen CLIP image encoder into expression-specific visual representations. Based on them, an Expression-Conditioned Prompting (ECP) mechanism adapts fixed class-level textual prompts from the frozen CLIP text encoder into instance-aware textual representations. The resulting visual-textual representations are aligned as adaptive semantic priors to enhance robustness and generalization. Quantitative and qualitative experiments show that LaCoVL-FER outperforms state-of-the-art methods on RAF-DB, FERPlus, and AffectNet. The code is available at https://github.com/ylin06804/LaCoVL-FER.

Vision-Language Models (VLMs) are becoming the cornerstone of high-level reasoning for robotic automation, enabling robots to parse natural language commands and perceive their environments. However, their susceptibility to hallucinations introduces critical failures in decision-making, posing significant safety and reliability risks in physical deployments. This challenge is exacerbated by the open-ended nature of real-world tasks, where questions vary vastly in difficulty and modality, demanding robust and adaptable reasoning strategies. To tackle this, we propose the Pseudocode-guided Structured Reasoning framework (PStar), which adaptively selects structured pseudocode reasoning paths to help VLMs perform flexible and step-by-step reasoning. We first design a set of abstract reasoning functions and formulate a structured pseudocode library to represent modular reasoning strategies. Crucially, we design a Difficulty Feature Vector (DFV) that allows the model to assess question complexity and adaptively choose appropriate reasoning strategies-enhancing robustness and interpretability. Extensive experiments demonstrate that PStar significantly reduces hallucination rates, achieving state-of-the-art scores of 87.1% on POPE and 68.0% on MMStar, outperforming even GPT-4V. By providing a validated mechanism to reduce visual-language errors, PStar offers a critical step toward deploying more trustworthy and deterministic VLMs for real-world automated systems, where such errors can lead to catastrophic outcomes.

Color constancy aims to keep object colors consistent under varying illumination. Cross-camera generalization in color constancy remains challenging because learning-based models often overfit to the color response characteristics of the training camera, resulting in degraded performance on images captured by other cameras. We propose VLM-CC, a feedback-guided framework that formulates color constancy as an iterative refinement process. Instead of directly estimating the illuminant from raw input, VLM-CC performs iterative correction driven by vision-language model (VLM)-based evaluation. At each iteration, the image is white-balanced using the current estimate and converted to pseudo-sRGB. A lightweight LoRA-tuned VLM then assesses the corrected image, identifying the dominant residual color cast and providing qualitative feedback. This feedback is mapped to a residual illumination direction (red, green, or blue) and used to update the illuminant estimate until convergence. Our key idea is to reframe color constancy as an iterative perceptual feedback problem, leveraging VLM evaluation instead of direct RGB regression. By replacing direct RGB estimation with VLM-guided perceptual feedback, VLM-CC achieves state-of-the-art robustness in cross-camera color constancy across multiple datasets. Code will be available at https://github.com/NothingIknow/VLM-CC.

Occluded person re-identification focuses on matching partially visible pedestrians across multiple camera views. However, occlusions disrupt body-region cues, thereby complicating cross-view matching. Most person ReID methods built on pretrained vision-language models only focus on enhancing prompt-based feature learning while ignoring the semantic information of occluders. Based on the success of CLIP-ReID, we propose a novel Dual Prompt Learning ReID (DPL-ReID) model for occluded person ReID. It incorporates a Dual Prompt Learning (Dual-PL) strategy, which can utilize textual cues to capture complete pedestrian semantics and keep robustness against occlusion, and a Real-World Occlusion Augmentation (RWOA) method that realistically simulates occlusion scenarios encountered in real word to enrich occluded samples. In addition, we also design a Weighted Gated Feature Fusion (WGFF) method, which in corporates LSNet to capture global information and act as a feature-gating mechanism. This mechanism can effectively guide the CLIP visual encoder toward generating more comprehensive feature representations. Extensive experiments on several benchmark occluded ReID datasets show that our proposed DPL-ReID achieves the state-of-the art performance. The occlusion instance library are available at https://github.com/stone-qiao/DPL-ReID.

Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire continually evolving domain-specific skills. Conventional approaches to enhancing VLM capabilities, such as Supervised Fine-Tuning (SFT), require extensive dataset curation and substantial computational resources. Model merging has emerged as an efficient alternative that enables the transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead. Unlike conventional merging of homogeneous LLMs, which mainly aggregates existing capabilities, cross-modal skill injection aims to induce emergent cross-modal capabilities by integrating a domain-expert LLM into a VLM. However, existing research lacks a systematic analysis of the applicability and methodology of cross-modal skill injection. In this study, we investigate cross-modal skill injection across three main aspects: scenarios, methods, and hyperparameters. For scenarios, we find that cross-modal skill injection generally performs well in instruction-following and cross-lingual settings, yet struggles with mathematical reasoning. For methods, we find that classic approaches such as TA and DARE consistently achieve superior performance over alternative merging methods. We also provide a systematic and quantitative analysis of the hyperparameter tuning that these classic methods critically depend on.

Deep learning methods have demonstrated promising results in predicting BI-RADS scores from mammography images. However, the interpretation of these images can vary, leading to discrepancies even among radiologists. Given the inherent complexity of mammograms, training classification models solely on image labels often yields limited performance. To address this challenge, we curated 2313 mammogram images and their corresponding captions from two mammography atlases. Our proposed approach employs a multi-modal model that uses a pretrained PubMedBERT as the language component. By training this model on image-text pairs with contrastive learning, we enable the vision encoder to absorb the rich information contained in the captions, thereby improving its understanding of mammography findings. We then fine-tune the vision encoder on two datasets for BI-RADS prediction, achieving superior performance compared with models trained without this pretraining, particularly when labeled samples are scarce. The improvement in the 3-class average F1 score ranges from +1% to +14%: a +1% increase with 40K training samples, and a +14% increase with 1K samples. Furthermore, our experiments reveal that 2K image-text pairs from mammography atlases can be more informative than 2K labeled samples for label prediction, with an average margin of +1.1% when more than 10K training samples are available. Overall, our work provides a vision-language model for mammography and highlights the value of textual information from mammography atlases. In addition, we publicly release preprocessed mammography images of the TEKNOFEST dataset. The training code, pre-trained model weights, data extraction scripts, and the released dataset are publicly available at: https://github.com/igulluk/MAM-CLIP

Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the intersection of neuroscience and machine learning. Most brain-encoding studies focus on aligning artificial models with brain activity during language comprehension or passive visual processing, while interactive brain-alignment studies have to date been largely limited to reinforcement-learning (RL) agents and theory-based models. To address this gap, we study brain alignment of representative models from two foundation-model families, namely vision-language models (VLMs) and large-action models (LAMs), using fMRI recordings from participants playing naturalistic Atari-style video games. Specifically, we examine how action-focused and reasoning-focused prompts shape model's internal representations and align with fMRI brain activity. First, we find that both VLMs and LAMs exhibit significantly exhibit voxel-wise encoding performance than RL baselines, with the advantage holding even under matched feature dimensionality. Second, prompt-driven gains scale with the cortical processing hierarchy: the largest improvements appear in frontal-parietal and motor-planning regions, while early visual cortex gains roughly half as much. Third, variance partitioning reveals a qualitatively different representational organization: VLM is prompt-symmetric (12.5% unique action vs. 13.6% unique reasoning), whereas LAM is prompt-asymmetric (27% unique action vs. -5% unique reasoning), with the asymmetry strongest in frontal-motor cortex. Together, these results demonstrate that action-specialized fine-tuning reorganizes multimodal representations toward action-relevant neural computations even when whole-brain prediction accuracy is statistically equivalent between VLM and LAM.

Conventional vision-language models (VLMs) struggle to interpret scenes captured under adverse conditions (e.g., low light, high dynamic range, or fast motion) because standard RGB images degrade in such environments. Event cameras provide a complementary modality: they asynchronously record per-pixel brightness changes with high temporal resolution and wide dynamic range, preserving motion cues where frames fail. We propose RE-VLM, the first dual-stream vision-language model that jointly leverages RGB images and event streams for robust scene understanding across both normal and challenging conditions. RE-VLM employs parallel RGB and event encoders together with a progressive training strategy that aligns heterogeneous visual features with language. To address the scarcity of RGB-Event-Text supervision, we further propose a graph-driven pipeline that converts synchronized RGB-Event streams into verifiable scene graphs, from which we synthesize captions and question-answer (QA) pairs. To develop and evaluate RE-VLM, we construct two datasets: PEOD-Chat, targeting illumination-challenged scenes, and RGBE-Chat, covering diverse scenarios. On captioning and VQA benchmarks, RE-VLM consistently outperforms state-of-the-art RGB-only and event-only models with comparable parameter counts, with particularly large gains under challenging conditions. These results demonstrate the effectiveness of event-augmented VLMs in achieving robust vision-language understanding across a wide range of real-world environments.

Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image foundation models already provide powerful spatial representations. This raises an important question: can competitive video models be built by reusing these spatial representations and pre-training only for temporal reasoning? We take initial steps toward exploring a lightweight training paradigm that freezes a pre-trained image foundation model and trains only a recurrent temporal module to process streaming video. By reusing an image foundation model as a spatial encoder, this approach could significantly reduce the amount of video data and compute required compared to end-to-end video pre-training. In this work, we explore the feasibility of this approach before investing in computing for video pre-training. Our empirical findings across multiple video understanding tasks suggest that strong temporal performance can emerge without large-scale video pre-training, motivating future work on recurrent video foundation models obtained by pre-training a temporal module on top of a frozen image foundation model. Code: https://github.com/tue-mps/towards-video-image-frozen .

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated web data fail to generalize to the sparse, weakly-aligned egocentric streams produced by wearable devices, embodied agents, and infant head-cams -- and no fixed evaluation pipeline exists for measuring progress on this regime. We train VLMs on datasets with varying degrees of semantic alignment between visual and linguistic inputs, including naturalistic infant and adult egocentric videos, and evaluate them with a comprehensive suite spanning multimodal language grounding and unimodal vision and language tasks. At the core of this suite is Machine-DevBench, a corpus-grounded benchmark of lexical and grammatical competence, automatically generated from the model's training vocabulary across logarithmic frequency bins to eliminate the train/eval mismatch and low statistical power of prior developmental benchmarks. Our results show that current VLM paradigms hinge on the tight semantic alignment of curated data and fail to exploit the weakly-aligned signal that dominates naturalistic egocentric input -- the very regime in which humans thrive. To motivate progress, we introduce the EgoBabyVLM Challenge to drive the development of models capable of grounded language learning from the kind of naturalistic data that human infants experience.

Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it assumes that the user already provides model-ready text, reference images, and spatial grounding for local edits, which real requests often omit. We present Aurora, an agentic video editing framework that pairs a tool-augmented vision-language model (VLM) agent with a unified video diffusion transformer. The VLM agent maps a raw user request to a structured edit plan aligned with the transformer's conditioning channels, thereby resolving textual and visual underspecification before generation. We train the VLM agent with supervised data for complete edit planning and reference-image selection, together with preference pairs for robust tool use and instruction refinement. We introduce AgentEdit-Bench to evaluate agent-enhanced video editing under textual and visual underspecification. Experiments on AgentEdit-Bench and two existing video editing benchmarks show that Aurora improves over instruction-only baselines and that the VLM agent transfers to compatible frozen video editing models. Project page: https://yeates.github.io/Aurora-Page

Most existing vision-language manipulation research targets rigid robotic arms, whose fixed morphology limits adaptability in cluttered or confined spaces. Soft robotic arms offer an appealing alternative due to their deformability, but confront challenges such as unreliable proprioception and distributed low-level actuation. To investigate these challenges, we introduce \ManiSoft, a benchmark for vision-language manipulation with soft arms. ManiSoft features a tailored simulator that couples realistic soft-body dynamics with contact-rich interactions via an elastic force constraint. On this basis, ManiSoft defines four tasks, each highlighting distinct aspects of deformable control, from basic end-effector coordination to obstacle avoidance. To support policy training and evaluation, \ManiSoft{} includes an automated pipeline that generates $6{,}300$ diverse scenes and corresponding expert trajectories. To produce high-quality trajectories at scale, we first employ a high-level planner to decompose each task into a sequence of waypoints, followed by a low-level reinforcement learning policy that generates torque commands to track waypoints. Benchmarking three representative policy models shows relatively promising results in clean scenes but substantial performance drop under randomization. Visualization analysis indicates that failures stem primarily from inaccurate visual estimation of proprioceptive state and limited exploitation of deformability for adaptive obstacle avoiding. We anticipate ManiSoft to serve as a valuable testbed, bridging the gap between rigid and soft arms in the context of vision-language manipulation. Out codes and datasets are released at https://buaa-colalab.github.io/ManiSoft.

Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically decide where to look through operations like zooming, cropping, and panning. However, current training paradigms produce models that mimic the surface form of such operations without functionally depending on their outputs, a phenomenon we term lazy perception. We trace this to a fundamental learning asymmetry: when coarse global views combined with language priors suffice for moderate accuracy, the model has no incentive to learn harder multi-step visual search. If a model can succeed without actively looking, it will never learn to look. This motivates Starve to Perceive, a training paradigm that constrains visual bandwidth -- restricting each observation to a tight token budget so that no single view suffices for task completion, making active perception the only viable strategy. Despite requiring no auxiliary losses, reward shaping, or architectural changes -- serving as a minimal, plug-in modification to standard post-training pipelines -- models trained under perceptual starvation achieve substantial gains of 5% average relative improvement across diverse benchmarks.

Emotion Recognition in Conversation (ERC) is essential for effective human-machine interaction, aiming to identify speakers' emotional states in multi-turn dialogues. Early text-based methods struggle with complex scenarios like sarcasm because they inherently neglect vital non-verbal information. While recent Vision-Language Models (VLMs) address this by analyzing video directly, they are not inherently tailored for ERC and often focus on emotionally irrelevant background regions or passive listeners rather than the active speaker. Furthermore, fine-tuning these large models incurs prohibitive computational costs. Additionally, isolated visual signals are frequently ambiguous or technically compromised without the context of linguistic content and vocal prosody. To address these challenges, we propose VISAFF, a speaker-centered VISual AFFective feature learning framework for ERC. VISAFF consists of two stages: Speaker-Centered Affective Grounding and Reliability-Guided Affective Complementation. VISAFF utilizes a tuning-free approach to unlock the reasoning capabilities of frozen VLMs, efficiently steering them to focus on the active speaker's emotional visual cues without heavy training overheads. In the second stage, we introduce a reliability-guided affective complementation mechanism that dynamically leverages textual and acoustic modalities to compensate for visual uncertainty. Experiments on two real-world datasets demonstrate that VISAFF achieves highly competitive performance compared to state-of-the-art methods in a tuning-free setting, significantly enhancing computational efficiency by eliminating the need for expensive fine-tuning of large VLMs. The source code is available at https://anonymous.4open.science/r/speaker-2365/.

Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought reasoning with continuous latent tokens as intermediate visual imagination steps. In this work, we investigate how recent models leverage such latent tokens. Surprisingly, we find that model accuracy is unaffected when latent tokens are replaced by uninformative dummy tokens. This indicates that latent tokens play a minimal causal role in the model's final prediction. To better understand this phenomenon, we analyze both the training signal provided by oracle latent representations and the quality of the latent tokens generated at inference time. Our experiments reveal two crucial issues holding back latent visual reasoning: First, in most existing datasets, oracle latent tokens provide limited additional information beyond the original image and do not substantially simplify the task, leading models to ignore them during training and effectively bypassing them at inference time. When fine-tuned on a diagnostic dataset, in which latent tokens provide sufficient support for the final prediction, we show that models can causally rely on them. Second, the latent tokens produced at inference time deviate from their corresponding oracle representations, collapsing to a narrow region and preventing benefits even when the model relies on them. Overall, our findings suggest that future progress in latent visual reasoning depends on two key pillars: high-quality datasets with informative intermediate steps and more precise latent token prediction.

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framework to eliminate spatial redundancy in standard 2D grid features, and (2) a semantic reconstruction objective that aligns the decoded outputs with the VFM's representations to preserve semantic fidelity. Grounded in these designs, we propose VFMTok, a generalist visual tokenizer capable of operating seamlessly in both discrete and continuous latent spaces. VFMTok achieves substantial improvements in synthesis quality while drastically enhancing token efficiency. For discrete autoregressive (AR) generation, it accelerates model convergence by \textbf{3 times} and achieves a state-of-the-art gFID of \textbf{1.36} on ImageNet class-conditional synthesis. Similarly, for continuous-space generation, integrating VFMTok with a denoising model yields an exceptional gFID of \textbf{1.25}. Furthermore, because the latent space inherently captures rich spatial semantics, VFMTok enables high-fidelity class-conditional synthesis without classifier-free guidance (\textbf{w/o CFG}) across both generative paradigms, significantly accelerating inference speed. Beyond these remarkable empirical results, we systematically investigate the underlying mechanisms of our approach. We discover that the specific self-supervised learning objectives utilized during VFM pre-training dictate its effectiveness as a tokenizer. Specifically, a VFM jointly optimized with global contrastive learning and latent masked image modeling provides the optimal representations for image tokenization. These insights establish a strong foundation and offer valuable guidance for the design of future image tokenizers.

Small vision-language models (2-8B) are well-suited for clinical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on-premise inference. However, their limited capacity exacerbates the generation of plausible but incorrect outputs. We extend game-theoretic decoding, previously restricted to text-only, closed-ended NLP tasks, to vision-language models for open-ended Medical VQA. We introduce a semantically aware Wasserstein stopping criterion that replaces lexical order matching, enabling convergence based on semantic consensus among near-synonymous candidate answers and avoiding unnecessary iterations caused by clinically equivalent ranking swaps. On VQA-RAD and PathVQA, we obtain consistent, statistically significant improvements over greedy and discriminative baselines. On VQA-RAD, we improve Qwen3-VL-2B by +3.5 percentage points (p < 0.01), surpassing the greedy 4B model, with similar trends at larger scales. On PathVQA, Gemma-3-4B with BDG matches MedGemma-4B under greedy decoding despite no domain-specific fine-tuning. At accuracy parity with classic BDG, the Wasserstein criterion reduces average convergence iterations by approximately 20%, improving inference efficiency while preserving the game-theoretic equilibrium behaviour. Code is available at https://github.com/luca-hagen/ Wasserstein-BDG-medical-VQA.

Vision-Language Models (VLMs) have made striking progress, yet their spatial reasoning remains fragile: models that answer an original input correctly can still fail under paired transformations with predictable answer mappings, revealing a gap between instance-level correctness and robust spatial reasoning. To address this, we propose Spatial Alignment via Geometric Evolution (SAGE), a self-evolving framework that enforces logical consistency in VLMs through geometric and linguistic duality operations. SAGE incorporates duality consistency as an auxiliary reward within GRPO training, encouraging models to produce logically coherent answers across original and transformed inputs. A dynamic operation pool continuously probes for inconsistencies, promoting challenging operations and retiring mastered ones, so that training focuses on the most informative signals. SAGE is model-agnostic, data-efficient compared to prior GRPO methods, and can be applied as a lightweight post-training stage to any existing VLM. Experiments on video and spatial reasoning benchmarks demonstrate consistent improvements over strong baselines and enhanced generalization to unseen data.

Multimodal product retrieval (MPR) underpins checkout-free retail and automated inventory systems, yet it demands fine-grained SKU discrimination that standard vision-language benchmarks fail to capture. We present the first systematic zero-shot evaluation of 190 open-source VLMs on the MPR task of the GroceryVision Challenge, isolating pre-training data, architecture, and input resolution. Our analysis yields three actionable findings. \textbf{(1) Data quality trumps scale.} Switching from raw web-scrapes to filtered datasets delivers up to 16.6% accuracy gains, exceeding the benefit of doubling model parameters. \textbf{(2) Efficient models can win.} MobileCLIP-B (150M parameters) outperforms 351M counterparts trained on noisy data. We introduce \textit{semantic power density} ($φ$), an efficiency metric that penalizes sub-threshold accuracy. \textbf{(3) A precision gap persists.} State-of-the-art models achieve 94.5% Recall@5 but suffer a 17.5% drop at Recall@1, revealing that contrastive embeddings cluster categories effectively but fail to rank visually similar SKUs. Code and evaluation scripts are available at \url{https://github.com/upeee/openmpr}.

We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual prompts, such as masks or points, SWIM leverages mask supervision only during training to guide cross-modal attention, allowing the model to automatically attend to the user-specified object at inference. Our cross-attention analysis of pretrained multimodal large languagemodels (MLLMs) reveals a systematic discrepancy: Attribute words produce sharp, localized activations in the visual modality, whereas object nouns yield diffuse and scattered patterns due to semantic reference bias and distributed high-level representations. To address this misalignment, we construct NL-Refer, an enriched dataset, in which each object mask is paired with a precise natural language referring expression. SWIM extracts multi-layer cross-attention maps from object nouns and enforces spatial consistency with ground-truth masks. Experimental results demonstrate that SWIM substantially improves text-visual alignment and achieves superior performance over visual-prompt-based methods on fine-grained object understanding benchmarks. The code and data are available at \href{https://github.com/HumanMLLM/SWIM}{https://github.com/HumanMLLM/SWIM}.

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the same form as text. However, the language model has been optimized to operate on discrete, semantically meaningful tokens, while prevailing visual projectors transform an image into a long stream of continuous and highly correlated embeddings. This causes the visual tokens to behave differently from the word-like units that LLMs are originally trained to understand. We propose a novel Disentangled Visual Tokenization (DiVT) that clusters patch embeddings into coherent semantic units, so each token corresponds to a distinct visual concept instead of a rigid grid cell. DiVT further adapts its token budget to image complexity, providing an explicit accuracy-compute trade-off modifying neither the vision encoder nor the language model. Across diverse multimodal benchmarks, DiVT matches or surpasses baselines with significantly fewer visual tokens, demonstrating robustness under limited token budgets, significantly reducing memory cost and latency while making visual inputs more compatible with LLMs. Our code is available at https://github.com/snuviplab/DiVT.

Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoning. While effective for scene-level understanding, this pipeline may prematurely compress local visual evidence, making fine-grained spatial reasoning vulnerable to language priors, especially in ultra-high-resolution remote sensing imagery. We present SkyNative, a native multimodal framework for remote sensing that adopts an encoder-free architecture, removing the pretrained visual backbone to directly represent images as raw patch tokens in the language-model token space. To reconcile low-level visual patches with textual tokens, SkyNative introduces a modality-aware decoupling mechanism that uses modality-specific parameters within a unified autoregressive backbone. We further introduce a visual reliance benchmark that diagnoses whether models ground their answers in image evidence through progressive visual degradation and misleading textual prompts. Across standard remote sensing understanding tasks and large-format spatial reasoning evaluations, SkyNative shows stronger image-grounded perception and improved robustness against prompt-induced language priors. These results suggest that native patch-level multimodal modeling is a promising direction for reliable remote sensing vision-language reasoning.

When humans view scenes without a specific task (free-viewing), they initially direct their eye movements toward the scene center and then fixate on people, text, objects being gazed at or grasped, and semantically meaningful regions. What these signature fixation patterns reflect and whether they optimize an underlying perceptual task remain unknown. We show that a computational agent with simulated foveation, trained to optimize scene comprehension, exhibits emergent human fixation signature patterns. In contrast, versions of the agent trained to search or classify scenes, or equipped with peripheral vision that was better or worse than human vision, predicted human fixation patterns less accurately. Thus, human free-viewing fixation patterns may emerge as a functional byproduct of optimizing scene comprehension under the biological constraints of foveated vision.

Frozen vision-language embeddings contain signals at multiple semantic resolutions, from object identity to attributes, relations, and full-caption meaning, but they expose these signals through a fixed-length vector interface. We study whether embedding length can be turned into a controllable semantic access interface. We propose \textbf{GraSP-VL}, which learns a shared near-orthogonal prefix transform over frozen VLM embeddings. GraSP-VL instantiates a \textbf{Semantic Matryoshka} interface: short prefixes are assigned coarse semantic roles, while longer prefixes progressively expose finer language-grounded distinctions. Because the transform is shared across image and text embeddings and preserves full-dimensional geometry, prefix behavior changes without rewriting the original VLM space. On a 20,147-example COCO/Flickr30K annotation pool, GraSP-VL reaches a staircase score of 53.01 and hard-negative selectivity of 89.76, while keeping full-space drift below $10^{-6}$. It also transfers to SugarCrepe-clean with 86.03 object accuracy and 11.96 mean external emergence, and preserves full-dimensional zero-shot CIFAR-100 accuracy. These results show that frozen VLM embeddings can be reorganized into a truncatable semantic prefix interface rather than merely compressed.

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world deployment. To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense. Building upon our prior Test-Time Adversarial Prompt Tuning (TAPT), TAME introduces an architectural reformulation by replacing TAPT's single adaptive prompt with an input-conditioned Mixture-of-Experts (MoE) framework, enabling more expressive and adaptive defense. Specifically, TAME maintains a bank of learnable expert prompts and employs an input-dependent routing mechanism to aggregate a customized prompt mixture for each unlabeled test sample at inference time. This test-time defense mechanism is driven by three unsupervised objectives: (1) multi-view prediction entropy minimization, (2) layer-wise alignment of visual token statistics to precomputed clean and adversarial reference distributions, and (3) MoE regularization for balanced expert utilization and prompt diversity. We evaluated TAME on 11 benchmark datasets, including ImageNet and 10 additional zero-shot datasets. The results show that TAME improves the zero-shot adversarial robustness of the original CLIP by at least 49.1% under AutoAttack while largely preserving generalization on clean samples. TAME also consistently outperforms existing adversarial prompt tuning methods across multiple prompt designs, yielding an average robustness gain of at least 30.2%.

Face Image Quality Assessment (FIQA) is a crucial control step in biometric pipelines. It ensures only reliable samples are processed to maintain system accuracy. State-of-the-art FIQA methods achieve high utility but typically operate as "black boxes." They produce scalar scores without human-interpretable justifications. This lack of transparency limits their effectiveness in human-in-the-loop scenarios, such as automated border control, where actionable feedback is essential. In this paper, we investigate the potential of off-the-shelf Vision-Language Models (VLMs) to bridge this gap by performing FIQA in a zero-shot setting. We present a comprehensive evaluation framework for assessing VLM performance. This involves benchmarking traditional FIQA methods through error-versus-reject curves. Additionally, using a diverse set of datasets, ranging from surveillance-oriented to synthetically generated, we analyzed their interpretability, consistency, and robustness to prompt changes. Our results show biometric utility performance depends significantly on architecture, not merely on parameter count. Most VLMs' outputs align with those of traditional methods. We also find that VLM ranking performance and the generated scores may vary across prompts. Our synthetic ablation study shows that while increasing the parameter count can improve internal consistency, it yields worse degradation-detection performance than smaller models. These findings suggest that zero-shot FIQA score estimation using VLMs is promising and could effectively complement conventional FIQA pipelines as an interpretability module. The codes are available at https://github.com/ThEnded32/VLM4FIQA.git.

Driver gaze estimation serves as a fundamental metric for evaluating driver attentiveness in modern monitoring systems. Beyond being vulnerable to sudden lighting changes and sensor noise, spatial-domain models struggle to disentangle authentic gaze cues from irrelevant visual attributes. In this paper, we propose LISA, a \textbf{L}anguage-guided \textbf{I}nterference-aware \textbf{S}patial-Frequency \textbf{A}ttention framework that combines frequency-domain priors with vision-language knowledge. Observing that the amplitude spectrum remains relatively stable even under spatial perturbations, we design a dual-domain fusion mechanism. It integrates stable low-frequency semantics into high-frequency details, employing spatial attention to precisely target ocular regions. To reduce semantic ambiguity, we also introduce a training-time disentanglement strategy. Using a frozen CLIP encoder and orthogonal regularization, we explicitly separate gaze features from appearance interference. Experiments on two benchmarks show that LISA achieves state-of-the-art performance, with significantly improved robustness against occlusions and lighting variations. The code repository is available at https://github.com/Mason-bupt/LISA.

The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction -- reducing visual tokens after feature extraction to alleviate the LLM's computational overhead. While these methods effectively reduce the number of visual tokens, we observe that the primary latency bottleneck then shifts from the LLM to the expensive per-frame processing of the vision encoder. To address this, we introduce LiteFrame, a strong, yet highly efficient video encoder backbone for Video LLMs. To train LiteFrame, we propose Compressed Token Distillation (CTD), a novel training framework that teaches a compact student vision encoder to directly predict information-dense, spatio-temporally compressed representations produced by a large teacher vision model, effectively bypassing redundant computation. When coupled with further Language Model Adaptation (LMA), this approach results in a new latency-accuracy Pareto frontier -- compared with InternVL3-8B, LiteFrame provides a 35% reduction in end-to-end latency while processing 8$\times$ more frames and improves average video understanding accuracy across multiple benchmarks. Our results demonstrate a new potential path to unlocking longer-form video understanding under fixed compute budgets.

Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories to directly predict actions, and the zero-shot modular pipeline integrating pre-trained Multimodal Large Language Model (MLLM) for training-free generalization to unseen environments. However, end-to-end methods struggle with long-horizon navigation and lack dynamic reasoning, whereas zero-shot methods are constrained by limited spatial grounding for reliable planning and also require substantial reasoning time. To bridge this gap, we introduce SEDualVLN, a spatially-enhanced dual-system VLN framework. System 1 is a VLM model enhanced with both global and local spatial awareness, used for action generation. System 2 integrates a general MLLM with a mapping module, wherein the MLLM plans waypoints by leveraging top-down views of the real-time 3D map alongside streams of rendered path images. Both systems leverage different forms of spatial enhancement to cultivate the agent's sense of direction in VLN tasks. Ultimately, they cooperate to complete the navigation task through a fast-slow coordinated approach. SEDualVLN achieves state-of-the-art performance on VLN-CE benchmarks, and further ablation studies demonstrate the effectiveness of each system and module.