Vision-Language Models

Also known as VLM

Follow this topic Ask about this topic

Momentum

55 papers in the last four weeks, up 120% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 491

Aug 3, 2026cs.CV

DiffPrune: differentiable information throttling for token pruning in vision-language models

Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. The key is to learn a score that measures whether a token is useful. Existing methods typically rely on Gumbel-Softmax to approximate discrete selection during training. Such selectors make the score depend on the behavior of a relaxed pruning operator, not directly on the consequence of information loss. In this paper, we propose DiffPrune, which gives token scores a direct meaning. During training, DiffPrune keeps all tokens and weakens each token's information according to its score. If weakening a token hurts the task, the scorer is pushed to protect it; if not, the token can receive a lower score. Because the loss is differentiated through this actual information-throttling path, the scorer avoids the unstable surrogate path of relaxed token selection. DiffPrune implements this idea with an Information Throttler, which injects variance-preserving noise into visual tokens, where high-score tokens remain close to their original representations, while low-score tokens carry less original information. At inference, the throttler is removed, and hard top-K pruning is applied using the learned scores. Across ten VLM benchmarks, DiffPrune retains 96.5% of full-model accuracy while accelerating LLM prefill by 2.85x, with only 0.69 ms inference overhead. Code will be publicly available.

Landi He, Mingde Yao, Shawn Young +1

Shenzhen University of Advanced Technology · CUHK MMLab, CPII under InnoHK

Vision-Language Models Efficient VLM Inference Token Pruning Visual Token Pruning

Aug 3, 2026cs.CV

Recompute or Reuse? Diagnosing and Mitigating Textual Shortcuts in VLM Self-Reflection

Vision-language models (VLMs) are expected to revise their reasoning when visual evidence changes. Failures to do so are often attributed to insufficient visual attention or contextual inertia, leaving unclear what models reuse instead of recomputing from the current image. We show that evidence-bearing reasoning in a prior chain of thought (CoT) can form a textual shortcut that competes behaviorally with visual recomputation. Across 16 VLMs, a matched counterfactual analysis identifies evidence-bearing content as the most robust carrier of prior-CoT influence. Removing this evidence-bearing content shifts answer preference more than removing length-matched non-evidence context or the final-answer span, with prior control weakening progressively as more stale evidence is removed. Reordering this evidence also weakens prior control, showing that its organization modulates shortcut strength. Beyond the immediate answer, the shortcut can retain residual influence after answer correction: weakening current-image support shifts preference back toward the prior answer, while repeated prior answers and reused premises arise mainly when the shortcut remains active. To limit this influence, we introduce Fresh-State Attention Firewall (FSAF), a training-free intervention that isolates fresh computation from the prior CoT. Across five VLMs, FSAF raises visual update rate from 35.28% to 53.61% and reduces prior-answer rate from 39.22% to 3.67%. Reliable VLM self-reflection therefore requires more than looking again: fresh visual recomputation must be protected from stale textual reuse.

Wenxiao Fan, Jingling Fu, Fang Li +9

School of Computer Science, Beijing Institute of Technology · Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University

Vision-Language Models VLM Reasoning

Aug 3, 2026cs.CV

SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models

Vision-Language Models (VLMs) perform well on commonsense reasoning tasks but struggle with visual spatial reasoning. Most existing solutions introduce extra 3D prior inputs or external spatial encoders, which increase complexity and degrade the underlying VLMs' general-purpose capabilities after spatial fine-tuning. To this end, we propose a parameter-efficient \textit{\textbf{Spatio}-vision \textbf{L}anguage \textbf{M}odels (SpatioLM)}, that enhances spatial intelligence without extra 3D prior inputs or third-party spatial encoders. Concretely, we design a plug-and-play and non-invasive spatio-vision module that elicits the spatial knowledge inherent in VLMs. Furthermore, we innovatively leverage pseudo depth and camera information as supervision to guide the model in learning physically coherent representations. Extensive experiments show that SpatioLM achieves significant improvements in diverse tasks, including spatial perception and understanding while effectively limiting the degradation of general capabilities. Notably, the model achieves an impressive score of 71.6 on the VSI-Bench (the first model to surpass 70). In addition, it attains competitive performance when transferred to embodied manipulation tasks. Code is available at \faGithub~spatio-lm.

Jing Wu, Jianhua Wu, Jiayi Guan +5

Xiaomi EV, Beijing, China · College of Automotive and Energy Engineering, Tongji University, Shanghai, China · Independent Researcher

Vision-Language Models Visual Spatial Reasoning VLM Reasoning

Aug 3, 2026cs.CV

DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models

Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial recurring inference cost. Unlike autoregressive decoding, diffusion generation repeatedly revisits the entire response as uncertainty evolves. Our analysis reveals that visual evidence demand is strongly step-dependent, motivating adaptive allocation across denoising steps. Existing inference acceleration methods operate through decoding-side strategies or visual token compression via pruning and merging, but do not explicitly treat visual evidence as a resource whose demand evolves across the diffusion process. Therefore, we present Denoising-Aware Visual Evidence Trajectory Allocation (DAVET), a training-free framework that allocates visual evidence according to the evolving generation state. Starting from a phase-conditioned evidence trajectory, the proposed allocation policy uses operation demand to set an evidence reserve whose allocation at each denoising step is modulated by trajectory risk. DAVET realizes the resulting budgets through a hierarchy of evidence views constructed from a single visual encoding, separating when and how much evidence is needed from how the evidence views are constructed. Evaluated on two representative dVLMs, LLaDA-V and LaViDa, across multiple visual-understanding benchmarks, DAVET achieves an average speedup of 1.55

\times

with an average relative performance drop of 1.86%, showing that denoising-aware visual evidence allocation can reduce visual conditioning cost while largely preserving generation quality.

Yongkang Zhou, Xiang Xia, Cheng Yan +2

University of Science and Technology of China Hefei, China

Vision-Language Models Efficient VLM Inference Diffusion Model Inference Acceleration

Aug 3, 2026cs.CV

Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit

Addressing urban blight has seen increased focus in the past 15 years. Assessing urban blight is essential for guiding urban planning, targeting rehabilitation, and safeguarding public health, yet traditional residential blight surveys are difficult to maintain at scale due to the labor-intensive cost and long-term cycle. This study introduced a scalable framework for estimating residential blight using open-source large vision-language models on multiple views. Structured prompts guided models to evaluate housing attributes, including roof integrity, wall damage, and broken or boarded openings, producing both binary assessments and probabilistic estimates of disrepair. To evaluate the performance of these visual assessments, we compared professional human annotations of these features across several models, including an ensemble stacking approach based on XGBoost and a weighted scoring system. Results showed that (i) multiple street views can contribute to the improvement of accuracy, (ii) large vision-language models have different strengths of inference, (iii) the ensemble learner outperforms individual base models, enhancing robustness across all residential conditions and blight assessment. The practical application of the method allows low-cost tracking and management of housing stock conditions, providing a regularly updatable complement to traditional blight surveys.

Xiaohao Yang, Aohua Tian, Derek Van Berkel +2

School for Environment and Sustainability; School of Information University of Michigan, Ann Arbor, USA

VLM Evaluation Vision-Language Models Large Vision-Language Models

Aug 3, 2026cs.CV

Linear Multi-Timescale Retention as a Memory-Efficient Vision-Language Bridge

Vision-Language Models (VLMs) face a critical computational bottleneck when processing high-resolution imagery due to the

O(N^2)

memory complexity of Softmax Multi-Head Attention (MHA). While substituting MHA with independent Multi-Layer Perceptrons (MLPs) achieves

O(N)

scaling, it strips the architecture of spatial sequence routing, severely degrading global scene understanding and object permanence. In this paper, we propose the Linear Multi-Timescale Retention (LIA-MTR) module, a memory-efficient cross-modal bridge. By integrating an ELU-based positive feature mapping with adaptive write-gating and log-linearly distributed recurrent decays, LIA-MTR mathematically compresses continuous visual sequences into bounded memory states. Theoretical analysis proves the architecture operates with strict

O(N)

sequence-interaction complexity. Empirically, synthetic retrieval evaluations demonstrate that LIA-MTR flawlessly routes context across 16,000 tokens, eliminating the "Lost in the Middle" degradation typical of naive linear attention. Hardware benchmarking reveals infinite-context scaling capabilities, natively processing 262,144 visual patches within an 11.2 GB VRAM footprint, whereas standard MHA suffers out-of-memory failure at 16,384 patches. Furthermore, following instruction tuning on 665K conversational samples, LIA-MTR significantly outperforms an industry-standard MLP baseline on the MME benchmark (71.00% vs. 68.11%), driven by a 10% absolute improvement in object permanence and superior global semantic extraction. This work establishes a mathematically rigorous, computationally flat foundation for infinite-context Vision-Language integration.

Ashfak Yeafi, Mehedi Hasan, Md Khairul Islam

Department of Electrical and Electronic Engineering Khulna University of Engineering & Technology Khulna-9203, Bangladesh · Department of Computer Science and Engineering Brac University, Dhaka, Bangladesh · Department of Mathematics and Computer Science Hobart and William Smith Colleges Geneva, NY, USA

Memory-Augmented VLMs Vision-Language Models Efficient VLM Inference Linear Attention Long-Context VLMs

Aug 2, 2026cs.CV

Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning

Multimodal large language models (MLLMs) increasingly rely on long chain-of-thought reasoning for complex tasks. However, as reasoning sequences lengthen, models may gradually rely less on visual evidence and more on accumulated textual context, leading to visual forgetting. Existing approaches do not directly constrain how visual evidence is used and maintained along the original reasoning trajectory, leaving long-context visual forgetting insufficiently addressed. To address this issue, we propose Remember-R1, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory. Specifically, Remember-R1 introduces rewards that encourage broader coverage of matched visual keywords, stronger persistence of visual dependence in later reasoning steps, and greater focus on question-relevant image regions. Experiments across multiple model scales and diverse multimodal benchmarks demonstrate that Remember-R1 consistently improves reasoning performance. Additional analyses further show that it slows the decline of visual attention during generation, supporting its effectiveness in mitigating long-context visual forgetting.

Jianmin Chen, Jiaqi Tang, Wei Wei +9

Hong Kong University of Science and Technology Hong Kong, China · Northwestern Polytechnical University Xi’an, China · Zhejiang University Hangzhou, China

Vision-Language Models Long-Context Modeling VLM Reasoning RL for VLMs

Aug 2, 2026cs.CL

Evaluating VLMs on Multimodal Aristotelian Persuasion Tasks

Vision Language Models (VLMs) have demonstrated exceptional performance across various tasks. However, they have not yet been thoroughly evaluated on more complex tasks. The Persuasion Model, conceived by Aristotle, resembles a triangle shape, which highlights its inherent challenges related to personal biases. To assess the progress of VLMs on these complex tasks, we use the ImageArg datasets, focusing on the Logos, Ethos, and Pathos detection tasks. Our findings indicate that models from the Qwen family achieve improved F1 scores, with Qwen3 performing exceptionally well on the Logos and Pathos tasks, while Qwen2 exhibits competitive performance on the more complex Ethos detection task. We release the code to foster research in this direction.

Khondoker Ittehadul Islam

Saarland University · Department of Language Science & Technology

VLM Evaluation Vision-Language Models Persuasion in Language Models

Aug 2, 2026cs.CR

Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks

We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR). The operative change is in the defense pipeline, not in the image. Across five frontier VLMs, two encoded-attack families, and three black-box defenses, a caption-mediated defense (ECSO) that leaves ASR essentially unchanged on text-only encoded input drops it by up to

73

pp once a content-free decoy is attached; every non-saturated contrast is significant under exact McNemar tests. We advance two hypotheses for this pattern, supported by indirect evidence rather than pipeline introspection, since a black-box threat model precludes inspecting vendor internals: caption-mediated defenses branch on image presence, and intrinsic image-side safety engages on image-resident content. Three controls constrain the explanation. Blank-canvas and natural-photograph decoys reproduce the effect on every model, implicating image presence rather than content; the effect replicates on three open-weight VLMs served with no moderation layer, so it is not a vendor-filtering artifact; and a non-symbolic, meaning-based encoder reproduces it, so it is not specific to symbolic obfuscation. Attaching a decoy unconditionally is not deployable --- it raises benign refusal to

20

--

79\%

, an inflation of

+10

to

+67

pp --- but gating attachment on a lightweight encoded-input detector returns benign refusal to the text baseline while preserving the safety gain wherever the detector fires, making detector recall the binding constraint. Under adaptive attacks that target the caption-mediated re-check, the effect degrades but holds. We frame this as an observation about pipeline interaction, not as a robust defense.

Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2

VLM Robustness Adversarial Attacks on VLMs Vision-Language Models Black-Box Adversarial Attacks

Aug 2, 2026cs.CV

MonitorVLM-v2: A Deployed Vision-Language Framework for Real-Time Safety Violation Detection

Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) approach is poorly suited to safety-critical, rule-governed settings such as industrial surveillance, where decisions must be bounded, deterministic, and low-latency. Because CoT inference cost scales jointly with reasoning length and the number of concurrent streams, it creates a throughput bottleneck that precludes the real-time, multistream monitoring required for industrial accountability. Here we present MonitorVLM-v2, a deployment-oriented framework that recasts VLM-based safety assessment as probabilistic inference over a finite regulatory decision space, compressing multimodal reasoning into single-step rule-ID predictions and reducing decoding from a variable-length sequence to a single token. We introduce symbolic policy optimization (SymPO), a novel contrastive policy optimization algorithm that sharpens decision boundaries within this finite symbolic space, together with an entropy-driven triage mechanism that routes uncertain predictions to human reviewers for expert confirmation. In a four-month prospective deployment across 10 concurrent camera feeds in an operational underground mining facility, MonitorVLM-v2 achieved a 19.45-fold increase in inference speed and identified 2.78 times as many confirmed violations as the site's routine manual inspection workflow, demonstrating the practical value of compressed symbolic decision-making for real-time, auditable industrial monitoring.

Jiang Wu, Sichao Wu, Yinsong Ma +2

School of Mechanical Engineering, University of Science and Technology Beijing · The Laboratory for Computational Sensing and Robotics, Johns Hopkins University

Vision-Language Models Efficient VLM Inference Policy Optimization Video Surveillance

Aug 1, 2026cs.CV

Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

Vision-language MoE batches contain different numbers of image and text tokens. Image resolution, image count, tiling, and prompt length all change this token mix. We call the standard token-level Switch auxiliary loss Std-Aux. Std-Aux balances only the mixed load, so large image and text load errors can cancel at one mix. On our main model, the same trained router shows more than a fivefold change in load imbalance across image resolutions. We hold the image and text load profiles fixed and derive the exact load curve as the token mix varies. The image-text load gap controls sensitivity to the token mix. Physical preprocessing can also change the conditional profiles. The fixed-profile law excludes such changes. To design a remedy, we examine the router input structure. Image and text occupy distinct regions, while visual tokens group strongly by source image. The modality boundary motivates separate image and text terms. The image boundary motivates one equal-weight routing instance per image. ReBA, or Relax Within, Balance Across, implements both choices. Across four split backbones, ReBA lowers load on every reported benchmark input while keeping mean task accuracy comparable to Std-Aux. ReBA also lowers average load over the tested range and worst physical load under resolution and tiling shifts. Code is available at https://github.com/ZiangWu-77/ReBA.

Ziang Wu, Peng Jin, Qishen Yin +4

2Peng Cheng Laboratory · School of Software and Microelectronics, Peking University · 1Shenzhen Graduate School, Peking University +2

Expert Load Balancing Vision-Language Models Expert Routing

Aug 1, 2026cs.AI

Through the LENS: Local Geometric Decomposition of Vision-Language Model Representations

Vision-language models (VLMs) process image patches and text tokens in a shared residual stream, but the local geometry through which the two modalities interact remains poorly understood. Most interpretability methods identify global linear directions, which may miss representations that are globally high-dimensional but locally low-dimensional. We introduce LENS (Local Explanation of Neighborhood Subspaces), a method that decomposes VLM activations into local low-rank Gaussian neighborhoods using a Mixture of Factor Analyzers. Applied to LLaVA-1.5-7B and Qwen3-VL-8B, LENS reveals distinct depth-dependent fusion trajectories consistent with each model's fusion mechanism: LLaVA progressively mixes modalities at later layers, whereas Qwen3-VL mixes them early, partially re-segregates them, and recombines them near the output. An automated multimodal labeling pipeline assigns concise semantic descriptions to these neighborhoods. Interpolating activations toward neighborhood centroids causally redirects generation within and across modalities and outperforms difference-in-means and VL-SAE in most evaluated conditions; in one LLaVA vision-to-vision setting, MFA achieves 5.7 times the VL-SAE score. Human evaluation finds MFA steering competitive with prompting and substantially stronger than the other intervention baselines. Finally, the MFA coefficient space improves Qwen3-VL image-to-rendered-text retrieval at the deepest evaluated layer from 14.9% to 48.6% R@1. Ablations show that the reported fusion trajectories are stable across component counts, local ranks, and modality-purity thresholds. These results support local geometric neighborhoods as useful interpretable and causal units for analyzing cross-modal representations in the evaluated VLMs.

Shalom Kachko, Raz Lapid, Margarita Vald +2

1Ben-Gurion University of the Negev · 2Intuit Inc. · 3Deepkeep

Vision-Language Models VLM Interpretability Vision-Language Alignment Activation Steering

Jul 31, 2026cs.CV

Attention-Steered Vision-Language Models for Sign Language Translation

Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language translation task, where we identify a key failure mode of existing VLMbased translators: poor spatial-temporal visual grounding. In particular, we find that standard next-token cross-entropy does not directly provide signal for where and when the model should attend, causing models to overlook sign-relevant regions and frames. To address this challenge, we propose AttnSign, a VLM-based spatial-temporal attention steering framework for sign language translation. AttnSign first introduces spatial attention supervision for sign-relevant regions, such as face and hands, in each frame; then develops an RL-based motion-cadence steering method that encourages the model to explore and focus on sign-level keyframes. Experimental results on How2Sign and OpenASL benchmarks show that our proposed AttnSign consistently outperforms existing methods.

Meibo Hu, Guohao Sun, Annemarie D. Ross +2

Rochester Institute of Technology · National Technical Institute for the Deaf / Rochester Institute of Technology · University of Virginia

Sign Language Translation Vision-Language Models

Jul 31, 2026cs.CL

Sycophancy Undermines Epistemic Vigilance in Cooperative Vision-Language Tasks

To maintain common ground in cooperative conversation, humans iteratively update their beliefs as conversation participants share new information; participants who are epistemically vigilant detect when new information conflicts with prior beliefs and take steps to repair these conflicts. In order for AI systems to serve as reliable partners in complex cooperative tasks, they must similarly weigh incoming information against their own private evidence and shared context and appropriately surface inconsistencies when they arise. To measure the epistemic vigilance of vision-language models in cooperative settings, we present an information-asymmetric, dialog-based "spot-the-difference" task. Two models are privately shown one image each, and must determine through conversation whether the images are identical or, if not, identify the difference. Models routinely fail at this: they frequently overlook key evidence in their private image in favor of agreeing with their conversational partner, even when their agreement is unwarranted. We relate these violations of epistemic vigilance to the broader behavior of sycophancy, which manifests itself in cooperative goal-oriented dialog as over-accommodation and weak evidential grounding. Our results show that model steering to reduce sycophancy with a vector learned from task-agnostic sycophancy examples can reduce epistemic vigilance-related errors, making models more faithful reporters of their evidence, and in turn, more reliable partners in information-asymmetric cooperative tasks.

Rupak Sarkar, Neha Srikanth, Saloni Gupta +3

University of Maryland, College Park · Army Research Lab

VLM Evaluation Vision-Language Models VLM Reasoning

Jul 31, 2026cs.CV

Counting the Cost of War Under Satellite Embargo: Zero-Shot Estimation of Impacted Infrastructure

Rapid estimation of impacted structures - critical for conflict-zone humanitarian response - is frequently hindered by post-strike satellite data embargoes and imagery blackouts. We bypass this operational bottleneck by reframing impacted building mapping as a zero-shot geometric projection task on archival, pre-strike maps. Using coordinate and incident text from LiveUAMap and ArcGIS, Large Language Models extract weapon payloads (W) to project kinetic blast perimeters via Hopkinson-Cranz scaling (R_base = Z * W^(1/3)). To count exposed structures within these zones without post-strike imagery, we introduce two technical innovations: Adaptive Field-of-View to eliminate resolution (zoom) bias in 2D segmentation (SAMGeo), and 2.5D pseudo-height depth maps combined with segmentation masks to help Large Vision-Language Models (LVLMs) resolve overlapping, dense rooftops. Evaluated on 2026 Middle East conflict data, depth-augmented LVLMs dramatically outperform traditional segmentation in congested urban centers. This establishes a powerful hybrid paradigm for zero-shot crisis mapping: ultra-fast 2D segmentation for sparse rural zones, and depth-augmented LVLMs for dense urban environments.

Saleh Sakib Ahmed, M. Sohel Rahman

Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Palashi, Dhaka, 1000, Bangladesh.

Remote Sensing Image Understanding Vision-Language Models Remote Sensing Image Segmentation Disaster Damage Assessment Object Counting

Jul 30, 2026cs.CV

ReToken: Improving Long-Context VLMs with Visual Retrieval Token

Long visual contexts challenge vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once can exceed GPU memory limits. We present RETOKEN, a single learnable embedding that extracts retrieval signals from the VLM's internal representations to select query-relevant visual tokens from the pre-filled KV cache. This enables retrieval within the answering VLM, without a separate retriever or re-encoding. Despite being trained on only a small image-QA dataset, RETOKEN generalizes across image and video benchmarks. On Visual Haystacks, it improves Qwen3VL-8B by 13.4 points and InternVL3.5 by 12.4 points (>20% relative). On LVBench, it transfers zero-shot to long video and improves Qwen3VL-8B by 8.0 points. Thanks to its lightweight design, both training and long-video inference fit on a single H100. Code is available at: https://github.com/avaxiao/ReToken

Yao Xiao, Reuben Tan, Zhen Zhu +3

University of Illinois at Urbana-Champaign · Microsoft Research · Google DeepMind

Vision-Language Models Vision-Language Retrieval Visual Token Pruning Long-Context VLMs

Jul 30, 2026cs.CV

MarkushGlyph and OCSRGlyph: Improved Chemical Structure Recognition

Chemical structures appear in patents and the scientific literature as images. For programmatic usage, such as indexing in databases or constructing machine learning model training sets, they must be transformed into line notations. The two common forms of this task are translating an image of a single molecule (optical chemical structure recognition - OCSR) and translating a Markush structure that represents a family of molecules. While prior work in the former case is quite mature, Markush structure parsing remains a challenging task. In this work, we treat both tasks as an image-to-text translation problem. We then propose OCSRGlyph, a state-of-the-art OCSR model, improving performance over prior methods by carefully considering stereochemistry. For the Markush task, we introduce MarkushGlyph, a vision-language model that reads the entire Markush structure as an image. This contrasts with prior systems, which often use multiple stages to separately process visual and text input content. Finally, we introduce a new metric for determining the accuracy of Markush structure translations, handling failure modes present in prior metrics.

Alex Andonian, Samuel G Rodriques, Andrew D White +1

1Edison Scientific

Vision-Language Models Optical Character Recognition

Jul 30, 2026cs.CV

Scaling Vision-Language Models Is Not Enough to Mitigate Bias

Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present the first large-scale empirical study of 194 publicly available VLMs, including 16 model families, covering a wide range of model sizes, 24 training datasets, and three evaluation benchmarks, namely ImageNet (overall performance), CelebA (typical single-attribute bias), and UrbanCars (complex multi-attribute biases). Across these settings, the Spearman correlation between model scale and performance weakens as evaluation shifts from ImageNet (

ρ{=}0.68

) to single-attribute (

ρ{=}0.48

) and further to multi-attribute (

ρ{=}0.05

) bias benchmarks. In contrast, properties of the training data (size and quality) show more consistent relationships with worst-group accuracy across both bias benchmarks. Notably, curated datasets yield improvements of up to 25% over uncurated alternatives at a comparable scale. Finally, the effect of architectural choices (e.g., patch size, image resolution) is highly context-dependent, varying with the nature of the benchmark, including the type of bias and its spatial distribution within images.

Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos

Information Technologies Institute, CERTH Thessaloniki, Greece

VLM Evaluation VLM Robustness Vision-Language Models

Jul 30, 2026cs.AI

MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes

Large vision-language models have improved at describing visual content, but accurate descriptions do not ensure interpretation when meaning depends on knowledge beyond the pixels. Memes expose this gap because they rely on cultural entities, background knowledge, and community conventions. Most meme benchmarks reduce interpretation to labels or holistic scores, obscuring where an explanation breaks down. We introduce MemeBench, a diagnostic benchmark of 1,253 Chinese and English memes with human-written references and quality-controlled VIKR annotations, centered on anime, comics, games, and adjacent online subcultures. Its VIKR schema decomposes explanations into Visual clues, Identity links, Knowledge units, and Reasoning mechanisms. Across 26 LVLMs, every model covers visible content more reliably than the knowledge needed to interpret it, and even the strongest retains a 22.6% Visual-Knowledge gap. To test whether this diagnosis can guide improvement, we introduce KAR, an entity-guided retrieval baseline built on CultureBase. Across four controlled models, KAR raises VIKR Success by 3.6-7.4% and, compared with generic retrieval, repairs more answers and breaks fewer. Yet both retrieval conditions improve Identity and Knowledge while reducing Visual coverage in every comparison. MemeBench reveals whether an interpretation succeeds, what is missing, and whether targeted evidence fills the diagnosed gap.

Weihang Wang, Kainan Tu, Jielei Zhang +9

1Bilibili · 2Fudan University · 3Peking University

VLM Evaluation Vision-Language Models VLM Reasoning Cultural Knowledge in Language Models

Jul 29, 2026cs.CV

Prior Directions: Why GUI Grounding Gets Locked in the Past

Vision-language models often use descriptions of earlier visual states to make decisions about the current scene. When the scene changes, stale language can redirect an otherwise correct visual judgment toward an outdated answer. We study this failure as visual lock-in in a controlled grounding setting where only the verbalized prior varies. Across models, stronger lock-in accompanies smaller changes in the model representation before the final answer. This reversal suggests that lock-in depends not on how far this representation moves, but on how that movement is organized. In models that are harder to correct, prior-induced changes concentrate along a compact set of directions that repeatedly appear across examples. We call these recurrent axes the Prior Directions. They recur on held-out examples, while a descriptive four-model comparison associates greater concentration with stronger lock-in. Controlled interventions show that removing the component aligned with the Prior Directions restores visual grounding, whereas removing an equally large orthogonal component has little effect. Prior control thus arises when prior-induced changes form a coherent and reusable pattern in the representation used to produce the answer. This account explains why the same prior remains revisable in one model yet becomes dominant in another.

Weile Gong, Zijian Lu, Mingcai Chen +3

Nanjing University of Posts and Telecommunications, Nanjing, China

Vision-Language Models GUI Grounding Vision-Language Grounding

Jul 27, 2026cs.CV

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model

Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process them inefficiently. We present Mage-VL, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction. At its core, our custom tokenizer, Mage-ViT, replaces uniform frame sampling by selectively encoding dynamic, entropy-rich regions using motion vectors and residual energy across sparse anchor (I) and predicted (P) frames. Operating at a 16 x 16 patch level, this reduces visual token consumption by over 75% while preserving spatiotemporal context. Trained from scratch on approximately 560M unlabeled images and 100M unlabeled video frames, Mage-ViT matches or outperforms flagship encoders trained on billions of image-text pairs. We establish AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes. Furthermore, through a bio-inspired dual-system architecture - a lightweight System 1 event gate and a causal System 2 decoder - Mage-VL enables proactive streaming perception. Extensive evaluations show that Mage-VL-4B matches Qwen3-VL-4B on static tasks while achieving strong gains in video understanding and 2D/3D spatial reasoning, with up to a 3.5x wall-clock inference speedup, and comprehensively surpasses the 15B Phi-4-reasoning-vision baseline. Beyond model artifacts, we deliver seven key empirical findings covering pre-training data efficiency, variable-resolution scaling, codec system acceleration, VideoQA SFT redundancy, motion-spatial synergy, AI4AI data pipelines, and Zero-Vision SFT for multimodal RL.

Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20

Microsoft Mage Team

Vision-Language Models Efficient VLM Inference Visual Tokenization Video-Language Models

Jul 25, 2026cs.CV

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

Large Vision-Language Models (LVLMs) remain bottlenecked by massive computational footprints, precluding their deployment on resource-constrained edge devices. While efforts to compress LVLMs focus heavily on vision token reduction or smaller language models, the vision encoder is largely overlooked, typically deployed as a monolithic, computationally heavy feature extractor. Moreover, there is no previous effort that designs a vision encoder for LVLMs directly optimized for on-device latency. In this paper, we present UltraViT, a vision encoder for LVLMs, explicitly designed and optimized for on-device performance. Specifically, by taking into account real on-device latencies, we systematically design a pyramidal architecture that strategically integrates and adapts heterogeneous spatial mixers at the macro-block level. Furthermore, to pre-train UltraViT, we propose a novel two-stage generative pre-training strategy: cultivating rich spatial features via dense distillation, followed by direct generative supervision from a capacity-mixed frozen LLM. Compared to standard contrastive and SSL, we show that our pre-training is much more effective for achieving high-level semantic grounding for UltraViT needed for the subsequent generative multimodal alignment of LVLM training. Extensive experiments demonstrate that our on-device latency-informed design combined with our tailored training strategy establishes a new state-of-the-art for efficient LVLM encoding, significantly outperforming existing encoder-centric baselines while operating on-device at nearly 1.7xthe speed.

Ioannis Maniadis Metaxas, Adrian Bulat, Alberto Baldrati +4

Samsung AI Cambridge · Technical University of Iasi · Queen Mary University of London

Vision-Language Models Efficient VLM Inference Efficient ViTs Vision-Language Pretraining

Jul 25, 2026cs.CV

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features

Contrastive vision-language models such as CLIP map semantically opposite phrases (e.g., "a dog" vs. "not a dog") to nearly identical embeddings, rendering them insensitive to negation. We attribute this failure to a phenomenon we call Representational Collapse: by tracking compositional divergence and visual alignment across the CLIP text encoder, we show that middle layers build compositional syntax, but the final layers collapse this structure as visual alignment rises, producing a syntax-blind final representation. To recover the lost negation signal without altering pretrained weights, we propose PeakPatch, a lightweight post-hoc correction system that intercepts the encoder at its compositional peak. An Embedding Correction Network (ECN) uses cross-attention to extract a negation-specific signal from the peak layer, anchored to a stable baseline, and predicts a deviation vector that re-injects the lost syntax into the final-layer embedding space. A complementary Score Correction Network (SCN) predicts bounded scalar score offsets for discriminative tasks. Both modules are trained jointly end-to-end while all CLIP parameters remain frozen, adding only 5.2M parameters (3.5% of the backbone) and preserving the standard cosine similarity interface. On NegBench, PeakPatch achieves 74.3% on COCO MCQ (+35.1 over CLIP, +17.8 over the best encoder fine-tuning method) and 65.5% on VOC MCQ, while outperforming all fine-tuning baselines on fully out-of-distribution negation retrieval despite training only 3.5% of the parameters. The corrected embeddings also transfer to text-to-image generation (+18.4 negation score) and generalize across ViT-B/32, ViT-L/14, and SigLIP backbones. Project URL: https://stevencylu.github.io/PeakPatch/.

Chen-Yi Lu, Yueh-Shao Chen, Somali Chaterji

Purdue University, West Lafayette, IN 47907, USA

Vision-Language Models VLM Adaptation VLM Reasoning Vision-Language Alignment

Jul 25, 2026cs.CV

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable. We trace this to an interface-level Bag-of-Concepts effect, where similarity scores approximate mean pooling of concept evidence regardless of operators. Although operator-dependent signals exist in text embeddings, they are too weak or misaligned to affect rankings. Fine-tuning does not reliably resolve this failure because the dominant bottleneck is how similarity aggregates evidence rather than what encoders represent. We propose factored inference, which separates evidence extraction from constraint execution, and introduce LCSE (Logic-Constrained Score Editing), a training-free method that executes constraints externally using concept scores from frozen encoders. We also introduce FACTOR-Bench, where LCSE achieves 85.5% accuracy versus 73.2% for the best fine-tuned baseline, 90.7% when applied to SigLIP 2, and improves NegBench COCO MCQ accuracy from 27.2% to 65.2% while preserving retrieval performance.

Sultan Alshehri, Zhantao Yang, Han Zhang +1

Carnegie Mellon University, Pittsburgh, PA, USA.

Vision-Language Models VLM Reasoning Vision-Language Retrieval VLM Inference

Jul 24, 2026cs.CV

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should defer rather than answer. We evaluate two small open-weight VLMs -- Qwen2-VL-2B-Instruct and SmolVLM-Instruct -- across six realistic photographic degradations at three severity levels, comparing two confidence signals: the confidence the model states in natural language, and the model's own mean token probability over its generated answer. Across 3,800 predictions, we find a large and consistent gap. Verbalized confidence in Qwen2-VL is almost constant (mean 0.87-0.90 across all conditions) and detects its own errors at chance level (AUROC 0.39-0.75, typically ~0.50), while internal token probability from the same model separates correct from incorrect answers with AUROC 0.92-0.99. In SmolVLM, verbalized confidence proved largely unobtainable: across three prompt templates, only one of five pilot attempts produced a parseable confidence value, while internal probability again yielded above-chance error detection (AUROC 0.54-0.92). Both models fail in the same place: under severe underexposure, accuracy collapses (0.99->0.22 for Qwen2-VL, 0.97->0.42 for SmolVLM) while both confidence signals barely move, and internal error-detection falls to chance. We conclude that small VLMs encode usable self-knowledge that their verbalized output does not express, that internal probability is therefore the better deferral signal in constrained deployment, and that neither signal should be trusted under severe low-light conditions.

M M Asif Ferdous

Independent Researcher

VLM Robustness Vision-Language Models Confidence Estimation in Language Models VLM Calibration

Jul 23, 2026cs.CV

SCALE: Self-Supervised Constraint-Aware Layout GEneration for Local P&R DRV Fixing at Advanced Nodes

As semiconductor manufacturing advances toward sub-2nm nodes, local place-and-route (P&R) design-rule violation (DRV) fixing is increasingly limited by complex rule interactions, dense multi-layer routing geometries, and foundry-specific constraints. While Large Language Models (LLMs) have recently demonstrated strong capabilities in EDA scripting and documentation, their application to visual layout understanding remains largely unexplored: diagnosing DRC violations from layout imagery demands precise geometric reasoning and foundry-specific rule knowledge absent from general-purpose VLM training. We propose SCALE, a framework with a self-supervised layout-generation stage for local DRV fixing at advanced nodes. Multi-layer layout geometry is serialized into structured text, and a fine-tuned language model learns to reconstruct randomly masked polygons from surrounding BEOL context alone without violation labels. At inference, natural-language rule constraints and high-temperature sampling steer generation toward diverse, violation-prone layout variants validated by an industrial signoff DRC checker, producing DRC-annotated layout--violation pairs used to fine-tune a domain-adapted DRC-VLM. This VLM provides rule-aware geometric guidance for local DRV repair, boosting state-of-the-art agents' solve rates by +12--25% (up to 97%) on 100 real sub-2nm cases spanning enclosure, spacing, width, and color-spacing violations.

Chia-Tung Ho, Haoyu Yang, Guanglei Zhou +6

1NVIDIA · 2Duke University

Vision-Language Models Self-Supervised Learning Electronic Design Automation

Jul 22, 2026cs.CV

ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models

Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true, or even meaningful. Recently, it has been identified and given a mechanistic account in unimodal language models. Whether and how it manifests in vision-language models (VLMs) is, by contrast, largely unexamined, and the field lacks a purpose-built instrument with which to investigate it. We take the position that studying contextual entrainment in VLMs requires more than porting an existing text-only benchmark to the multimodal setting: it requires a taxonomically structured, dual-modality instrument whose conditions are constructed around the item at hand (the depicted image in the textual stream, the textual query in the visual stream). We argue that the move to VLMs is substantive rather than incremental. It makes entrainment a dual phenomenon, drivable independently by textual and by visual context, and it opens a veracity distinction (context that is false of the depicted scene yet possible in the world) that has no counterpart in the unimodal, world-knowledge-only formulation of prior work. To make this position concrete and actionable, we introduce ENTRAP-VL (ENTRainment Assessment Probe for Vision and Language), a manually curated dataset of 1,500 items across eight categories, organized by a taxonomy that spans two axes, i.e., the association of context with the item and its relationship to truth, and split into a textual-entrainment stream (eight context conditions) and a visual-entrainment stream (three context conditions). We do not claim to measure entrainment in any particular model; we provide the instrument, the taxonomy that motivates it, and the evaluation protocols it enables, so that the community can investigate the phenomenon rigorously. We will release the dataset and its documentation publicly.

Karan Goyal, Afreen Hossain, Debojyoti Das +1

IIIT Delhi, India · Dr. Ambedkar Institute of Technology, India · Heritage Institute of Technology, India +1

VLM Evaluation Vision-Language Models

Jul 21, 2026cs.CV

An Interactive Vision Language Platform for Cognitive Remediation in Schizophrenia

Cognitive remediation tasks often require patients to perform structured actions involving object manipulation and sequential reasoning. For patients diagnosed with schizophrenia, these tasks are crucial for addressing severe cognitive deficits. However, evaluating the correctness of these physical actions generally relies on manual observation by clinicians, which introduces subjectivity and limits the scalability of therapeutic interventions. In this paper, we propose an automated framework based on Vision-Language Models for action verification in cognitive remediation tasks tailored for schizophrenia rehabilitation. The proposed system relies on a camera-monitored tabletop environment composed of structured miniature scenes including roads, a roundabout, a park, and toy vehicles. Patients receive audio instructions describing goal-oriented spatial actions to perform by manipulating a toy vehicle. These interactive physical activities are specifically designed to stimulate targeted cognitive functions, such as sustained attention, motor coordination, spatial navigation, and cognitive flexibility. To verify the correctness of the performed actions without requiring continuous clinical oversight, the system analyzes the video feed tracking the patient's hand and toy movements. A fine-tuned Vision-Language Model interprets the recorded video sequences and generates semantic descriptions of the observed activities, enabling high-level verification of the executed actions with respect to the initial textual instructions. A dedicated dataset of 4634 tabletop cognitive remediation video scenarios was collected to evaluate the proposed approach. Experimental results demonstrate that our specialized framework effectively bridges low-level physical telemetry with high-level clinical feedback, presenting a scalable and objective solution for advanced cognitive rehabilitation.

Nassira Ait Mehdi, Milissa Temmam, Slimane Larabi

RIIMA Laboratory, Computer Science Faculty, USTHB University, 16111, Algeria

Vision-Language Models Mental Health Video Reasoning

Jul 21, 2026cs.CV

No Training, Better Flights: Test-Time Scaled VLMs for UAV Navigation

Test-time scaling offers a promising method to improve the inference performance of Vision-Language Models (VLMs) without additional training. Existing approaches to vision-language navigation (VLN) for Unmanned Aerial Vehicle (UAV) typically relies on a single inference pass, which can falter in complex environments by producing suboptimal or unsafe trajectories. In this paper, we explore a simple and effective approach to apply test-time scaling to VLN for UAV. We enhance navigation reasoning through an iterative refinement process that requires no extra model training, guiding the model to re-evaluate its initial navigation plan for better accuracy and safety. Our method first prompts the model to generate multiple parallel candidates and then performs a self-correction step, achieving deeper and more robust planning without changing the underlying model. To further strengthen decision-making, we design a multi-criteria scoring function to evaluate the refined candidates based on safety, goal alignment, and forward-progress. This simple yet powerful combination enables a frozen UAV navigation VLMs to self-correct and generate more accurate and reliable flight plans, achieving SOTA performance in this task.

Feinan Cheng, Dongliang Xu, Wenli Nong +4

Shandong University Weihai, China · China University of Petroleum (East China) Qingdao, China · MBZUAI Abu Dhabi, United Arab Emirates

Vision-Language Models UAV Navigation Test-Time Scaling for VLMs Test-Time Scaling Vision-Language Navigation VLM Reasoning+1

Jul 21, 2026cs.AI

Linguistic Context Recodes Visual Representations in Vision-Language Models

Goal-directed visual processing is a hallmark of human visual intelligence, resulting in representations that support downstream tasks such as categorization or search. Though vision-language models (VLMs) are often faced with these same tasks, their ability to recode visual representations when presented with goal-directed language remains poorly characterized. Indeed, prior work largely treats visual representations in VLMs as static repositories of visual information that are manipulated by language representations. In the present work, we provide evidence for two concrete instances of language-induced recoding of visual representations. First, we identify an abstract reference representation that denotes which objects are goal-relevant under a natural language prompt. We extract contrastive steering vectors corresponding to this reference representation and demonstrate that they are causally implicated in model predictions. These reference representations are abstract in that they generalize to different objects, different task contexts, and even from synthetic to naturalistic images. Second, we demonstrate language-induced attribute modulation: later layers selectively amplify goal-relevant attributes in visual representations of objects. We demonstrate this phenomenon across a range of different prompts. Finally, we provide a causal intervention that demonstrates that attribute modulation mediates a VLM's response distribution. Together, our results support a more dynamic account of cross-modality processing in VLMs -- rather than vision tokens serving as static repositories of information, they are modulated to support queries articulated in language.

Brian Song, Michael A. Lepori, Ellie Pavlick

Brown University

Vision-Language Models VLM Interpretability