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

Jun 8, 2026cs.CV

Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection

Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination. In this study, we propose a two-stage vision-language framework that combines initial defect detection with prediction refinement. In the first stage, Qwen3-VL is fine-tuned with LoRA as a vision-language adapter to predict defect counts, defect categories, and normalized bounding boxes from lithography images. However, direct fine-tuning may still produce common test-time errors, including false positives, missed defects, and incorrect defect types. To address this limitation, the second stage trains a refinement module using first-stage prediction failures and their corrected labels, allowing the model to review and revise initial outputs. By learning from cases where the initial adapter fails, the refinement process improves defect inference beyond single-stage fine-tuning.

Pangyun Jeong, Jiyeong Kong, Yuehua Hu +2

1HYU-KITECH Joint Department, Hanyang University, Ansan, 15588, Korea · 4Korea Institute of Industrial Technology, Ansan, 15588, Korea · 2Micro/Nano System Department, Korea University, Seoul 02841, Korea +1

Vision-Language Models VLM Adaptation Semiconductor Manufacturing Industrial Inspection

Jun 6, 2026cs.CV

One Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling

Vision-language models (VLMs) enable visual recognition from semantic class descriptions, which makes them attractive when target annotations are scarce or unavailable. Most deployment pipelines, however, first choose a single VLM and then adapt that model to the unlabeled target set. This single-backbone paradigm hides a critical assumption: the selected VLM is already compatible with the target domain. In realistic cross-domain deployment, several general-purpose and domain-specialized VLMs may be plausible, yet no instance-level target labels are available to identify the reliable ones. Deployment therefore requires a coupled solution for model selection, target adaptation, and prediction integration. We revisit this problem from a system-level multi-VLM perspective. Our central observation is that the three decisions above depend on the same latent object: a trustworthy sample-class structure in the target set. Different VLMs may encode different transfer biases and produce conflicting predictions, but their outputs can still provide complementary evidence for estimating this structure. We propose One Stone, Three Birds, a training-free framework based on self-adaptive optimal transport. Given a pool of frozen candidate VLMs, OSTB estimates a consensus sample-to-class transport plan without updating VLM parameters. The learned transport structure is then reused for all deployment objectives: model selection is performed by ranking the combined semantic and visual reliability induced by the consensus plan; target adaptation is obtained by fitting transport-conditioned visual classifiers; and ensembling is implemented through reliability-aware probabilistic integration. Extensive experiments on natural-image, remote-sensing, and medical-pathology benchmarks show that OSTB improves model ranking, adaptation stability, and ensemble robustness under heterogeneous candidate pools.

Qiyu Xu, Zhanxuan Hu, Yu Duan +4

School of Computer Science and Technology and the Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China · School of Information Science and Technology, Yunnan Normal University, Chenggong, Kunming, Yunnan 650500, China · School of Telecommunications Engineering, Xidian University, Xi’an 710071, China +1

Vision-Language Models Unsupervised Domain Adaptation VLM Adaptation

Jun 6, 2026cs.CV

Vision-Language Asymmetry in Bistable Image Captioning

Wittgenstein's duck-rabbit poses a question for vision-language models: when a model captions an ambiguous image, where in the model is the commitment to one aspect made? We address this with a 3,320-generation behavioral baseline over 83 bistable stimuli that surfaces three regimes (default-dominant, force-dominant, force-balanced) under neutral vs forced-choice prompting, then probe the underlying representations using a TopK sparse autoencoder we train on the CLIP layer that LLaVA-1.6-7B actually consumes (validation EV 0.93). Across 69 bistable stimuli with both per-aspect feature pools available, 72% (50/69) show simultaneous activation of both pools at the vision tower, including 12/12 default-dominant duck/rabbit and 7/8 force-balanced young/old. Causal steering at CLIP layer 22 flips captions on default-dominant stimuli (33% rabbit-flip rate under a fluency guard) but cannot flip captions on force-balanced young/old at any tested coefficient, despite their vision-side superposition. The dominance bottleneck lives downstream of the vision tower; the gap between vision-side representation and language-side commitment is an empirical handle on the seeing/seeing-as distinction. We also flag a methodological note: rank-based statistics on TopK SAE outputs require tie-corrected ranking to avoid silent row-order bias.

Arohan Agate

University of Washington.

Image Captioning Vision-Language Models VLM Interpretability

Jun 5, 2026cs.CV

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems for tasks such as image geolocation and spatial reasoning. In this work, we analyze the geospatial representations acquired by three model families: vision-only architectures (e.g., ViT), vision-language models (e.g., CLIP), and large-scale multimodal foundation models (e.g., LLaVA, Qwen, and Gemma). By evaluating across image clusters, including people, landmarks, and everyday objects, grouped based on the degree of localizability, we reveal systematic gaps in spatial accuracy and show that textual supervision enhances the learning of geospatial representations. Our findings suggest the role of language as an effective complementary modality for encoding spatial context and multimodal learning as a key direction for advancing geospatial AI.

Marcelo Sartori Locatelli, Fernando Tonucci, Jea Kwon +5

Max Planck Institute for Security and Privacy (MPI-SP), Bochum, Germany · Universidade Federal de Minas Gerais, Belo Horizonte, Brazil · Changwon National University, Changwon, South Korea +1

Vision-Language Models Geospatial Representation Learning Multimodal Large Language Models Geospatial Reasoning VLM Reasoning

Jun 5, 2026cs.AI

NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observation

As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged between onboard collection and actionable ground intelligence. This paper presents NAVI-Orbital, a software system deployed on a Low Earth Orbit (LEO) spacecraft. On April 16, 2026, NAVI-Orbital achieved what is, to the authors' knowledge, the first in-orbit demonstration of a vision-language model performing autonomous multi-modal inference entirely onboard. NAVI-Orbital uses a local vision-language model (Gemma 3) to classify each captured scene, produce a text description of its content and the relationships between its features, and respond to operator follow-up via natural-language dialogue. The system is re-tasked through plain-English prompts in place of conventional command sequences, and is orchestrated by a graph-based state machine (LangGraph) coordinating dedicated agents for detection and dialogue. Results across ground benchmarking (88.16% accuracy on the 7,960-image curated AID benchmark), Flatsat validation, and live in-orbit captures of newly acquired, previously unseen Earth imagery (including uncorrected YAM-9 imagery, processed onboard with hardware-accelerated GPU inference and no fine-tuning for the flight instrument) demonstrate the feasibility of running foundation models on satellite-class edge computers to invert the conventional acquire-then-downlink-everything bandwidth profile through semantic compression of Earth observations in-orbit.

Juan Manuel Delfa Victoria, Taran Cyriac John, Andrew W. Herson

Jet Propulsion Laboratory California Institute of Technology Pasadena, CA, USA · School of Engineering and Computer Science Victoria University of Wellington Wellington 6140, New Zealand · Loft Orbital 321 11th St, San Francisco, CA 94103

Remote Sensing Image Understanding Vision-Language Models VLM Inference

Jun 4, 2026cs.CV

Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception

Human perception of surface slant from texture exhibits systematic, graded biases that emerge reliably in psychophysical experiments. Prior work showed that unsupervised CNNs reproduce several human-like biases, while supervised CNNs do not. Do Vision-Language Models (VLMs) exhibit similar competences? Across multiple VLM families and model scales, zero-shot and in-context prompting both produce distinctive failures: slant is predicted at only a small set of anchors (e.g., 0\degree,

\pm

25\degree,

\pm

45\degree) with little dependence on stimulus field of view, optical slant, or surface curvature. Supervised fine-tuning partially remediates the failure, but residual anchoring persists. While success in high-level vision-language benchmarks might not require sensitivity to low-level geometric cues, we interpret anchoring as a failure at the representation-to-output language interface: not necessarily an absence of geometric encoding, but a failure to express it in a graded form.

Qian Zhang, Michal Golovanevsky, Fulvio Domini +1

Brown University Computer Science · Harvard University · Brown University Cognitive Science

VLM Evaluation Vision-Language Models Fine-Grained Visual Perception

Jun 4, 2026cs.CV

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens. While text-based output interfaces enable scalable pretraining and strong zero-shot generalization across diverse tasks, they are poorly suited for problems that require precise continuous outputs, such as localizing temporal boundaries of events or generating robotic control actions. To address this challenge, we propose DRIFT, a general framework for adapting pretrained VLMs to continuous decoding tasks. DRIFT combines a base predictor, which provides a coarse estimate of the target output, with a generative refinement module based on flow matching that iteratively improves the prediction. This residual formulation transforms the generative modeling problem from learning a global output distribution to modeling a localized residual distribution around a strong prior, substantially simplifying optimization. We evaluate DRIFT on both perception and planning tasks, including visual grounding and robotic control. Across multiple tasks and architectures spanning MLLMs, VLAs, and WAMs, DRIFT consistently outperforms a strong set of regression- and generative-based solutions.

Zhuoming Liu, Jinhong Lin, Kwan Man Cheng +3

University of Wisconsin–Madison · 2West Lafayette Jr./Sr. High School

Vision-Language Models VLM Adaptation VLMs for Robotics

Jun 4, 2026cs.AI

Seeing Time: Benchmarking Chronological Reasoning and Shortcut Biases in Vision-Language Models

Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning remains under-explored. In this paper, we introduce a novel benchmark specifically designed to evaluate how VLMs perceive and reason about chronological information within and across images. Unlike existing video-based benchmarks that focus on frame sequencing, our work delves into the underlying logic of chronological judgment and the expansion toward multimodal integration. To facilitate this, we construct three specialized datasets: one containing visually similar objects spanning long historical durations, another categorized by diverse event and object types, and a third pairing images with time-sensitive news text for cross-modal alignment. Through extensive experiments, we analyze whether models exhibit performance disparities across categories and, crucially, explore whether they rely on ``incorrect shortcuts'', such as image color rather than genuine chronological features. Our results reveal that while VLMs show promise, they frequently exploit superficial cues like grayscale versus color filters to bypass authentic chronological reasoning. By providing these high-quality datasets and a rigorous evaluation framework, we offer a diagnostic tool to identify current limitations and guide the development of more robust, logically grounded multimodal models. The source code is shown in https://github.com/LuoRenqiang/ChronoVision.

Haoyu Zhou, Qing Qing, Caichong Li +6

College of Computer Science and Technology, Jilin University, Changchun 130012, China · College of Computing and Data Science, Nanyang Technological University, 639798, Singapore · School of Computer Science, Wuhan University, China +1

VLM Evaluation Vision-Language Models VLM Reasoning

Jun 3, 2026cs.CV

Would you still call this Dax? Novel Visual References in VLMs and Humans

Vision-language models (VLMs), like human learners, are frequently exposed to new visual concepts, but how they map novel visual references to language after exposure remains largely underexplored, particularly when those references contradict prior knowledge from pre-training. To study this, we present the Novel Visual References Dataset (NVRD): 19,176 images spanning 90 visual concepts across different levels of visual novelty, each with up to 20 increasingly perturbed versions of the original object to probe generalization. Unlike prior work on visual augmentations of familiar concepts, NVRD comprises entirely novel, open-ended stimuli constructed from scratch, mirroring how humans encounter genuinely new concepts. We evaluate 3 open- and 2 closed-source models alongside 2,400 human judgments for direct human-model comparison, and find that (i) models struggle to acquire novel concepts in-context when they contradict prior knowledge, and (ii) while models and humans show correlated sensitivity to visual perturbations, models significantly overgeneralize, extending learned labels to stimuli that humans reject. We contribute NVRD as a corpus and benchmark for research on visual concept learning in both humans and machines.

Ada Defne Tür, Gaurav Kamath, Joyce Chai +2

McGill University · Mila Quebec AI Institute · University of Michigan - Ann Arbor +1

VLM Evaluation Vision-Language Models Domain Generalization In-Context Learning

Jun 3, 2026cs.CV

Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning

Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reasoning and generalization capabilities. Moreover, high-quality large-scale nutritional annotations remain scarce. To address these issues, we introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations. To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning. We also propose Food-R1, a unified food VLM trained in a multi-task learning paradigm to equip the model with broad capabilities. Food-R1 undergoes CoT-based cold-start instruction tuning, followed by reinforcement fine-tuning (RFT) using Group Relative Policy Optimization (GRPO) to improve reasoning and performance. Experiments on CalorieBench-80K and representative benchmarks show that Food-R1 consistently outperforms strong baselines across food-related tasks. The code, model weights, and benchmark annotations are available at the project repository.

Yu Zhu, Yongkang Li, Wenjie Zhu +5

Huazhong University of Science and Technology, Wuhan, China

Vision-Language Models VLM Reasoning

Jun 3, 2026cs.CV

Stateful Visual Encoders for Vision-Language Models

Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the language model, while the visual encoder itself remains stateless: each image is encoded independently, without access to the prior visual context. As a result, small but task-critical changes may be attenuated before the language model has a chance to compare them, especially when those changes do not affect the high-level semantics of the scene. We introduce a Stateful Visual Encoder, which conditions each visual representation on prior visual features. Under supervised finetuning, VLMs equipped with stateful encoders achieve consistent improvements on controlled tasks involving cross-image spatial aggregation, multi-object visual differencing, and visual trajectory behavior cloning. These improvements are consistent across input resolutions, language model sizes, and VLM backbones. Finally, we validate our model on real-world tasks, including longitudinal radiology, fine-grained image comparison, and remote sensing, where stateful encoders consistently improve generalist VLM baselines and can match or surpass specialized models in selected domains. Project page: https://statefulvisualencoders.github.io/

Zirui Wang, Junwei Yu, Adam Yala +3

1Voio, Inc. · 2UC Berkeley · 3UCSF

Vision-Language Models Visual Representation Learning VLM Adaptation

Jun 2, 2026cs.CV

A Dataset for Dynamic Human Preferences for Vision Language Models

Given the increased adoption of Vision Language Models (VLMs) in human-interactive settings, it is important that we evaluate how well these models can adapt to real-time preferences for different users. While an increasing number of vision-language benchmarks have recently been introduced, they focus largely on evaluating static capabilities and generally-held preferences learned from extensive training data. This work introduces a new benchmark for evaluating the ability of VLMs to understand dynamic human-preferences, i.e. preferences that are passed in-context at inference time. We provide an automated pipeline for generating this benchmark with variations on image dependence, a dynamic multi-modal human-preference dataset, and evaluations of state-of-the-art models on the novel benchmark.

Hannah Gao, Dylan Hadfield-Menell, Rachel Ma

Massachusetts Institute of Technology · MIT Cambridge, MA

VLM Evaluation Human Preference Evaluation Vision-Language Models

Jun 2, 2026cs.CV

HorusEye: Language as Dynamic Attention for Emergency Visual Analysis

We introduce HorusEye, Language as Dynamic Attention for Emergency Visual Analysis. Our investigation followed five stages. The first one is benchmarking RefCOCO-Degraded, a dataset of 15,244 images (3,811 base images x 4 conditions: Clean, Fog, Smoke and Thermal) with systematic visual degradation. Through four research questions, we evaluate multiple VLMs (Gemini, Qwen2-VL, BLIP-2, LLaVA, Kosmos-2) across visual grounding the second stage, language feedback recovery the third one, health VQA tasks the fourth, and hallucination analysis the final stage. Our key finding is that language feedback effectiveness is model-dependent: Gemini achieves +47.3% improvement in thermal conditions through iterative language feedback, while Qwen2-VL shows -5.1% degradation under the same protocol. We also identify the 'Thermal Paradox' where cropping strategies that improve RGB performance catastrophically fail in thermal imagery. Furthermore, BLIP-2 uniquely hallucinates more under degradation, making it unsuitable for emergency deployment

Armel Yara

VLM Robustness Vision-Language Models Object Hallucination in VLMs Vision-Language Grounding

Jun 2, 2026cs.CV

MAOAM: Unified Object and Material Selection with Vision-Language Models

Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existing vision-language-model (VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In this work, we thus present Mask Any Object And Material (MAOAM), a unified selection framework that enables precise object and material-level selection across both text- and click-based interactions. MAOAM leverages a VLM with a segmentation head to produce pixel-accurate masks from user prompts: the VLM interprets the user's selection intent (object or material-level) and encodes visual entities, attributes, and spatial relations, while the segmentation head decodes the output token into a mask. A key challenge is the lack of material selection datasets with text annotations. We propose a scalable data generation pipeline: we collect real and synthetic images with material masks, and leverage VLMs to generate material descriptions with rich visual-semantics. We train MAOAM with a multi-task objective over click and text-based selection, along with an auxiliary VQA task derived from the material descriptions to facilitate deeper material understanding. Despite being trained with uni-modal prompts, our model exhibits an emergent improvement in selection when combining text and clicks at inference, enabling flexible image editing workflows. Experiments demonstrate accurate and coherent selections across diverse objects, materials, and interaction scenarios, highlighting robustness in practice.

Jaden Park, Valentin Deschaintre, Jason Kuen +5

University of Wisconsin-Madison, USA · Adobe Research, United Kingdom · Adobe Research, USA

Vision-Language Models Text-Guided Image Segmentation Promptable Image Segmentation

Jun 2, 2026cs.CV

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled design. Yet large vision-language models (LVLMs) currently lack the tools to do so, and parameter-efficient encoder configurations remain hard to identify before training. To re-examine encoder roles under joint training, on the 16-benchmark Cambrian-1 suite we retrain and evaluate all 31 non-empty subsets of five common vision encoders under a unified pipeline (~20k GPU-hours total), and report three findings. First, retraining each subset from scratch reveals encoder rankings that differ from those obtained by masking encoders on a fixed checkpoint, including which encoder ranks first overall. Second, we decompose each encoder's contribution into two axes, Capacity, the score an encoder reaches on its own, and Necessity, the drop when it is removed from the full pool. The two axes are not interchangeable. Pairing the two highest-Capacity encoders is suboptimal, while pairing a high-Capacity anchor with an adaptive complement matches the full five-encoder model. Adding further encoders beyond this pair yields only marginal gains. Third, at fixed parameter count, per-encoder pre-projector effective rank explains the residual score variation. The strongest pairs combine an anchor whose rank survives joint training with a complement whose rank expands under it, suggesting that higher-rank, less-collapsed projector inputs correspond to a more favorable optimization regime at the encoder-projector interface. Together, the Capacity-Necessity decomposition and the pre-projector rank analysis, along with comprehensive evaluation through retraining, expose a methodological gap in multi-encoder LVLM design, and offer concrete primitives for closing it.

Wei Ding, Yudong Zhang, Ruobing Xie +3

Tsinghua University Beijing, China · Tsinghua University, Tencent Beijing, China · University of Science and Technology Beijing Beijing, China

VLM Evaluation Vision-Language Models Large Vision-Language Models Multimodal Foundation Models

Jun 2, 2026cs.CV

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics

Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores. This single-metric paradigm presents a critical flaw: high attention scores inherently collapse onto semantically similar regions, thereby severely reducing feature diversity and discarding vital contextual details. To address this, we introduce Structure-to-Semantics (STS), a novel two-stage visual token pruning framework that explicitly decouples the pruning process. The first stage employs a repulsion-based sampling mechanism to maximize spatial and structural diversity. The second stage leverages instruction-aware cross-attention to precisely filter out prompt-irrelevant tokens. This two-stage synergy constitutes the core of STS, first ensuring geometric coverage and then refining the retained tokens according to semantic relevance. Extensive evaluations demonstrate that STS mitigates the redundancy caused by attention-based selection, improving both structural diversity and fine-grained task alignment of the preserved visual tokens.

Jiahui Wang, Kai Zhang, Mai Han +1

1Shandong University · 2National University of Singapore (Suzhou) Research Institute

Vision-Language Models Efficient VLM Inference Visual Token Pruning

Jun 2, 2026cs.CV

SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation

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

Hyunwoong Kim, Seongeun Lee, Hannah Yun +2

DEEPNOID Inc., Seoul, South Korea

Vision-Language Models Group Relative Policy Optimization Credit Assignment RL for VLMs

Jun 2, 2026cs.CV

Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy

Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over visual evidence or factual priors learned during training. Current evaluations mix these two sources, obscuring when correct visual interpretation is overridden by memorized facts. We present a framework that isolates visual correctness from factual correctness, revealing validity limitations in existing visualization literacy assessments. Across three experiments with 15 state-of-the-art LVLMs: (1) several models reach human-level performance on standard tests (VLAT), but this may reflect factual recall rather than visual understanding, while randomized-data tests (reVLAT) underestimate literacy when correct visual interpretation is superseded by factual priors. (2) Using our Counterfactual Visualization Literacy Assessment Test (CVLAT) with capability-normalized arbitration metrics, we classify models by the sign of their visual-factual reliance index (VFRI), revealing a visualization-oriented majority and a factual knowledge-oriented minority, though several near-zero cases warrant caution. A human baseline (N=30) on the same counterfactual items confirms that people overwhelmingly follow the chart under conflict, providing a human reference point. (3) Prompt-based intervention can shift prioritization, but its effectiveness is highly model-dependent and direction-asymmetric, and high chart-reading capability does not predict prompt-controllability. Overall, high visualization accuracy is not sufficient evidence of faithful visual reasoning: reliable integration into visual analytics requires evaluating not only visualization literacy but also how models arbitrate between visual evidence and factual priors when the two diverge. Benchmark and code: https://github.com/JaeyoungKim-HCIL/CVLAT

Soohyun Lee, Jaeyoung Kim, Seokhyeon Park +5

Seoul National University · MADI Co., Ltd. · Hankuk University of Foreign Studies +1

VLM Evaluation Data Visualization Vision-Language Models VLM Reasoning Chart Understanding

Jun 2, 2026cs.CV

TGV-KV: Text-Grounded KV Eviction for Vision-Language Models

Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory consumption that scales linearly with context length. This issue is particularly pronounced in VLMs due to substantial redundancy in the visual modality. Although KV cache eviction approaches can effectively reduce inference memory, they often incur significant performance degradation in VLMs, as most are designed for language models and overlook the inherent gap between text and vision. By systematically analyzing the modality gap in VLMs in this work, we argue that the importance of visual information should be grounded in textual guidance and accordingly propose a Text-Grounded KV Eviction method for VLMs (TGV-KV). TGV-KV comprises three submodules: (1) Text-Vision Budgeting (TVB) assigns budget to each layer based on the mutual information interaction. (2) Text-Weighted Ranking (TWR) assesses the priority of text and ranks vision importance based on weighted text-image attention. (3) Text-Prioritised Retention (TPR) policy strategically preserves text KV to avoid acute information loss. We evaluate TGV-KV across five models with different sizes and architectures, showing that TGV-KV preserves 99.2% full-KV accuracy on the VizWiz-VQA task with LLaVA-NeXT and boosts end-to-end throughput by 52.6% with an extreme retention budget of 5%. Code is available at https://github.com/Danielement321/TGV-KV.

Jizhihui Liu, Ruizi Han, Miao Zhang +4

Harbin Institute of Technology, Shenzhen · Peng Cheng Laboratory

Vision-Language Models Efficient VLM Inference KV-Cache Eviction

Jun 2, 2026cs.CV

FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction

The scarcity of hard negative samples in current vision-language datasets significantly hinders fine-grained perception. To address this, we propose FineGen, a VLM-based Multi-Agent framework for automated dataset construction. By employing a collaborative Generation-Verification-Correction pipeline with a closed-loop feedback mechanism, FineGen ensures synthesized hard negatives are semantically valid yet strictly contradictory to visual content. Applying this to ImageNet, we construct FineGen-100K, a hierarchical dataset containing over 147,000 attribute-specific hard negatives with a rigorous 1:10 positive-to-negative ratio. Extensive evaluations confirm a 96.7% attribute validity rate. Crucially, downstream validation on the FG-OVD benchmark shows that fine-tuning on FineGen-100K yields a substantial +14.4% accuracy improvement on hard samples, significantly outperforming state-of-the-art methods.

Chang Kong, Yuebing Li, Peng Mo +2

Shenzhen Polytechnic University, Shenzhen, China · Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong Macao2026 Greater Bay Area, Shenzhen, China · Shenzhen University, China

Synthetic Data Augmentation Vision-Language Models Fine-Grained Visual Perception

Jun 1, 2026cs.CV

FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty

Vision-language models (VLMs) are playing an increasingly important role across multiple domains. In many applications, such as robotics, it is crucial to quantify the uncertainty in the output of these models. } We develop FUSE, a probabilistic framework for capturing two complementary sources of uncertainty in vision-language modeling: (i) aleatoric embedding-level uncertainty derived from input data vision-language ambiguity, and (ii) epistemic model-level uncertainty estimated from the semantic response diversity of VLMs. Our approach formulates a Bayesian fusion mechanism that analytically combines these uncertainty sources to produce a scalar measure of uncertainty. This measure can be used to reliably predict the model's output correctness for downstream applications. We demonstrate that our method outperforms baselines and achieves SOTA uncertainty calibration.

Harry Zhang, Luca Carlone

Massachusetts Institute of Technology

Uncertainty Estimation for VLA Models Vision-Language Models Uncertainty Quantification VLM Calibration Uncertainty Calibration

Jun 1, 2026cs.CV

Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View

Assessing built-environment interaction, such as wheelchair accessibility, is difficult because real-world mobility is shaped by distributed, context-dependent, and temporary barriers that are hard to capture at scale. To support scalable assessment, this paper examines whether vision-language models (VLMs) can identify accessibility barriers from Google Street View (GSV) imagery. We propose an expert-guided retrieval-augmented framework that combines GSV images, ADA-informed guidance, and expert-derived rubrics to evaluate accessibility dimensions. We collect a campus-scale dataset at the University of Florida, linking 407 unique GSV locations with GPS-derived wheelchair dwell behavior as a mobility-friction signal. Results show that VLM ratings are both negatively correlated and distributionally similar with dwell time, indicating partial but consistent alignment with a behavioral proxy for mobility friction. Visual cue analysis shows that certain environmental objects, such as curb ramps and crosswalks, are associated with higher VLM accessibility scores, while alignment remains limited for subtle surface conditions, transient obstructions, and viewpoint-dependent barriers. Overall, our findings show the potential of expert-guided VLMs for scalable accessibility assessment aligning with sensor-derived indicators of real-world wheelchair navigation.

Dongdong Wang, Alina Hagen, Isabelle Gatmaitan +5

University of Florida · University of South Florida · University of Illinois Urbana-Champaign

VLM Evaluation Vision-Language Models

Jun 1, 2026cs.CV

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models

Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps. For instance, UI-TARS-1.5-7B consumes 76 GB of GPU memory on merely five screenshots, approaching the capacity of mainstream 80 GB accelerators. Existing KV compression methods share two structural assumptions: aggregating visual-token importance into a single shared saliency map, and applying a fixed top-B cutoff to the fused score distribution. Pilot measurements refute both: spatial specialization lives at the attention-subspace level and migrates across layers, while the score distribution drifts in shape along a trajectory. We propose STaR-KV (Spatio-Temporal Adaptive Re-weighting), a training-free KV cache compression framework that calibrates token importance along three axes: (i) subspace-aware scoring driven by online spatial mutual information; (ii) a temporal stability discount that suppresses redundant cache entries from persistently attended subspaces; and (iii) an entropy-derived temperature that adaptively reshapes the score distribution. Across four GUI benchmarks, STaR-KV achieves the strongest average accuracy among state-of-the-art KV compression methods (e.g., GUIKV, SnapKV) at matched budgets, with no compression-stage FLOPs overhead (-0.07%) and cutting peak GPU memory by nearly 40% at a 20% KV-cache budget. Code is available at https://github.com/kawhiiiileo/STaR-KV.

Yuhang Han, Wenzheng Yang, Yujie Chen +4

1EPIC Lab, SJTU · 2HKUST (GZ) · 3The University of Sydney +3

Vision-Language Models KV Caching KV-Cache Compression GUI Automation

Jun 1, 2026cs.CV

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification. However, their predictions remain sensitive to spurious correlations, where contextual cues dominate over semantic content. Earlier solutions typically rely on fine-tuning or prompt engineering, which either undermine the advantages of pre-trained models or are prone to hallucination. In this work, we propose Density-Aware Translation (DAT) that refines image-text similarity scores using a local geometric density term derived from group reference sets. Our approach is motivated by the phenomenon that CLIP embeddings exhibit a modality gap and lie on an anisotropic shell in the feature space: common patterns cluster near the mean, while rare patterns are pushed outward. This geometry creates uneven alignment, where spurious correlations are amplified while semantically meaningful but rare cues are marginalised. To address this, we employ a relative measure to rescale similarities based on embedding density, suppressing overconfident scores in diffuse regions while preserving dense, semantically consistent matches. Experimental results on benchmark datasets demonstrate consistent improvements in worst-group and average accuracy, highlighting density-aware translation as a simple and effective calibration mechanism for reliable zero-shot classification using multimodal models.

Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1

School of Computing and Information Systems, The University of Melbourne, Victoria, Australia.

VLM Robustness Vision-Language Models Modality Gap in VLMs Zero-Shot Image Classification VLM Calibration

May 31, 2026cs.CV

On the Limits of Token Reduction for Efficient Unified Vision Language Training

Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective. In this work, we study the feasibility and limits of token-reduction-based acceleration for unified VLM training. Through a systematic analysis of layerwise attention allocation, we uncover a fundamental asymmetry: visual understanding exhibits substantial late-layer visual redundancy, whereas visual generation maintains persistent dependence on image tokens across depth. Guided by this observation, we design task-specific accelerators that selectively reduce image-token computation for each objective. While these methods achieve significant efficiency gains in isolated settings, we observe a consistent synergy loss under unified training -- task-specific token dropping necessitates divergent parameter pathways and eliminates the mutual performance gains typically observed in joint optimization. Our findings suggest that efficient unified modeling requires preserving shared cross-task structures, highlighting the need for synergy-aware acceleration strategies. Project page: https://chicychen.github.io/TokenReductionUnifiedVLM/.

Siyi Chen, Weiming Zhuang, Jingtao Li +1

University of Michigan · Sony AI

Vision-Language Models Unified Multimodal Models Multimodal Token Compression Visual Token Pruning

May 31, 2026cs.CL

Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining

Biomedical figures are explained not by captions alone but by body-text passages that discuss them. Yet current multimodal corpora typically reduce figures to isolated image-caption pairs, discarding this crucial context. Existing pipelines either omit this context or append it without enforcing the figure references that support each attachment, which can create unsupported image-text attachments and incoherent discourse. We introduce context-grounded reconstruction, a source-grounded framework that converts PubMed Central Open Access (PMC-OA) records into referentially coherent interleaved sequences. It recovers captions and source text, attaches context only through article-native figure references, repairs non-contiguous context, and prunes unsupported images. Starting from these reconstructed sequences, PMC-InterCPT first filters records for text quality and medical relevance, then applies evidence-aware allocation to form a 9.63B-token corpus for continued pretraining (CPT) of generative medical MLLMs. With fixed supervised fine-tuning (SFT), PMC-InterCPT improves Qwen3.5-4B-Base by 1.46 medical-average points and 3.11 general/scientific-average points over a token-matched raw source control, and surpasses a 42% larger raw-data run. Gains transfer to Qwen3.5-2B-Base and LLaVA-OneVision-1.5-4B-Base. Controlled ablations show that context-grounded reconstruction, rather than simply appending article context, is central to useful biomedical multimodal CPT.

Guanghao Zhu, Zeyu Liu, Zhitian Hou +10

The Hong Kong Polytechnic University · Sun Yat-sen University · PolyU-Daya Bay Technology and Innovation Research Institute

Vision-Language Models Multimodal Pretraining Medical VLMs Continued Pretraining Multimodal Learning

May 30, 2026cs.CV

Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated

Vision-language models (VLMs) are increasingly used to generate structured descriptions of street-level imagery for tasks such as streetscape auditing, mapping, and public consultation. These uses combine observable attributes with appraisal categories, and the human targets are often distributions of judgments with disagreement and explicit non-response. This paper argues that benchmarking VLMs for urban perception should treat disagreement and abstention as measurement outcomes, report inter-annotator reliability alongside model alignment, and treat the label space and scoring policy as negotiable artifacts when outputs are intended to inform urban governance. We ground the argument in a benchmark of 100 Montreal street scenes annotated along 30 dimensions by 12 participants from seven community organizations, and in a deterministic zero-shot evaluation of seven VLMs. Across dimensions, model agreement with human consensus co-varies with dimension-level human reliability, and for the appraisal dimension Overall Impression models and annotators exhibit distributional mismatch including different rates of Not applicable. We close with actions for benchmark creators, model developers, and institutions to make uncertainty and benchmark assumptions visible in evaluation reports.

Rashid Mushkani

Université de Montréal, Montréal, Québec, Canada · Mila – Québec AI Institute, Montréal, Québec, Canada

VLM Evaluation Inter-Rater Reliability Vision-Language Models

May 30, 2026cs.CV

T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining

Thermal imaging offers a powerful alternative to visible-spectrum vision under challenging conditions such as low illumination and adverse weather, yet foundational vision-language models like CLIP fail to align thermal images with textual descriptions due to a fundamental thermal perception gap. We identify three major challenges: the lack of captioned thermal datasets, the inability of standard LLMs to reason about thermal phenomena, and a key representational challenge in thermal imaging where global scene context and object-level heat signatures conflict when learned together in a single embedding space. To address these, we introduce IR-Cap, the first physics-aware thermal captioning pipeline and dataset providing complementary global and fine-grained thermal descriptions across three public benchmarks, and T-CLIP, a decoupled dual-LoRA framework that independently adapts CLIP for scene-level and object-level thermal understanding. T-CLIP achieves consistent improvements over all baselines across three thermal benchmarks in cross-modal retrieval, and we provide an exploratory demonstration of its applicability to text-conditioned thermal image generation.

Tayeba Qazi, Ayush Maheshwari, Prerana Mukherjee +1

Indian Institute of Technology Delhi, India · NVIDIA AI Technology Center, India · Jawaharlal Nehru University, India

Thermal Imaging Image Captioning Vision-Language Models VLM Adaptation Cross-Modal Retrieval

May 30, 2026cs.LG

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models

Vision-language models (VLMs) deliver strong multimodal reasoning capabilities, but their large computational cost and high parameter counts make deployment challenging on resource-constrained devices. Low-rank decomposition has emerged as a promising compression technique, yet existing methods often optimize local matrix reconstruction error, rely on uniform or heuristic rank allocation, and focus mainly on attention projections while leaving feed-forward networks underexplored. In this paper, we propose~\textit{LASER} (\textbf{L}oss-\textbf{A}ware \textbf{S}ingular-value d\textbf{E}composition and \textbf{R}ank allocation), a low-rank compression framework for efficient low-precision VLM inference. LASER derives a curvature-weighted SVD objective from a second-order approximation of the model loss and uses Kronecker-factored Fisher information to guide decomposition toward downstream performance rather than reconstruction alone. We further introduce a loss-aware cross-layer rank allocation strategy based on calibration gradients, enabling more effective parameter budgeting across layers. Finally, we extend low-rank compression to FFN layers through a hybrid scheme that combines SVD with quantization. The evaluation results show that LASER achieves more than

2.3\times

decoding speedup over previous work while preserving strong accuracy under low-precision inference.

Haiyu Wang, Yutong Wang, Leshu Li +2

Tandon School of Engineering, New York University · Courant Institute of Mathematical Sciences, New York University · Brookhaven National Laboratory

Vision-Language Models Efficient VLM Inference Low-Rank Matrix Decomposition Low-Rank Compression Singular Value Decomposition

May 29, 2026cs.CV

Detect Before You Leap: Mirage Detection in Vision-Language Models

Vision-language models (VLMs) can produce confident answers without relevant visual evidence, a failure mode known as mirage reasoning (Asadi et al., 2026). To that end, we study pre-release mirage detection: deciding whether a VLM answer should be released or withheld. Our model-agnostic method, Text-Conditioned Layer-wise Internal Alignment (TC-LIA), tracks question-image alignment across the layers of a frozen CLIP ViT-H/14 encoder, summarizing patch-text alignment by final similarity, late-layer top-k alignment, early-to-late gain, and slope. TC-LIA is purely unsupervised (fixed projections, fixed scoring weights, no labels, no training) and already delivers strong detection independently. Additionally, when combined with blank/noise detection, domain routing, and VLM self-assessment, it forms an ensemble whose supervised training improves performance but is an optional add-on. On 19,004 samples spanning ten VQA domains, fourteen state-of-the-art VLMs exhibit 57.3-75.0% base mirage rates. Our proposed TC-LIA alone cuts this to 7.5% with 83.5% Related/Unrelated/Blank-Noise classification accuracy, and the ensemble reaches 84.3-88.4% accuracy with 5.9-7.2% mirage rates (best joint result: 88.4% accuracy, 6.4% mirage rate). Notably, an ensemble trained on a single backbone transfers well to unseen backbones, with the best-transferring source staying within 1.2% accuracy points of per-backbone training across thirteen held-out VLMs.

Md. Shaown Miah, S. M. Taiabul Haque, Syed Ishtiaque Ahmed +1

Indiana University Indianapolis · University of Toronto

Hallucination Detection in VLMs Vision-Language Models Hallucination Detection Vision-Language Alignment VLM Hallucination Mitigation