VLM Evaluation

We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results. To this end, we propose MMGist, a curated benchmark that covers seven capability dimensions and contains 7,262 items. MMGist is constructed through a three-stage pipeline, which sequentially combines text-ablation filtering, cross-model saturation filtering, and anomaly detection filtering. We conduct extensive experiments on 27 leading LVLMs and compare MMGist with the raw pool of 23,250 items. The results show that MMGist preserves model rankings with high fidelity, with Spearman $ρ= 0.98$, while reducing evaluation items by 69% and improving cross-model discrimination by 78%. Further results indicate that Visual Logic remains a systematic weakness of current LVLMs, while knowledge-intensive dimensions such as Expert Knowledge dimensions remain important factors for distinguishing closed-source models from open-source models. These findings suggest that high-quality evaluation should prioritize visual dependency, discriminative power, and reliability, rather than simply pursuing benchmark scale.

Automated classroom engagement recognition holds substantial promise for scalable learning analytics, yet the suitability of modern Vision-Language Models (VLMs) for this task under zero-shot conditions remains largely unexplored. We present a systematic benchmark that evaluates five widely-used VLMs: CLIP, BLIP-VQA, GPT-4o, LLaVA-1.5-7B, and Qwen2.5VL-7B-Instruct across two complementary educational datasets: DAiSEE, an individual-student video dataset (300 sampled test clips), and the Student Classroom Behaviour dataset (SCB, 1,168 scene-level images). Each model is probed with three prompt variants spanning minimal, rubric-anchored, and chain-of-thought designs. Our experiments reveal three primary failure modes of zero-shot VLMs for engagement recognition: (1) near-random performance on individual students, with Cohen's kappa never exceeding 0.10 on DAiSEE; (2) severe class collapse, where models assign 85-100% of predictions to a single engagement level regardless of visual content; and (3) extreme prompt sensitivity, with accuracy swings of up to 32 percentage points on identical images depending solely on prompt phrasing. Remarkably, scene-level classification on SCB is substantially more tractable: CLIP and GPT-4o achieve kappa approximately 0.60 when prompted with behaviorally-grounded rubrics. We also document a practical barrier for deployment: GPT-4o's safety filters reject 98% of chain-of-thought requests involving individual student faces. Our findings provide a calibrated baseline and surface critical design considerations for the use of VLMs in educational observation systems.

Do people perceive the same facial expression in the same way? Should we expect vision models to be flexible in how they perceive facial expressions? Facial expressions are nonverbal social signals used in human interaction, but facial expression recognition datasets often focus on a single deterministic annotation per sample. We introduce Chehre, an emoji-prompted video dataset with a wide range of dynamic facial expressions for exploring perceptual variation. In Chehre, 203 participants were prompted to express and record 40 facial emojis. Later, their facial motions were transferred onto synthetic faces to preserve privacy. A separate group annotated the videos, resulting in 2,111 videos annotated by 1,242 perceivers, with ~30 annotators per video. Chehre enables us to define a new task: "distributional expression recognition", which tests whether a model can reproduce the variation observed across annotator responses. We test a selection of video language models on our task. Interestingly, we find that persona prompting can act as a controllable way to shift model perception while helping models better capture the variation observed across human annotators. The dataset and code are available at https://chehre-dataset.github.io/.

Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging results, evaluating whether Med-VLMs can bridge this Expert-Lay Gap is both urgent and clinically consequential for patient education and shared decision-making. To this end, we introduce MedLayXPlain, the first large-scale multimodal benchmark and evaluation framework for Medical Lay Language Generation (MLLG). MedLayXPlain-122K provides 122,789 region-grounded samples across 8 imaging modalities from 12 publicly available source datasets, each comprising a medical image with paired expert and lay captions anchored in a three-level Unified Medical Language System (UMLS) ontology hierarchy spanning 7 semantic groups, 43 semantic types, and 2,411 medical concepts. Lay captions are constructed via Hierarchical Ontology-Verified Refinement (HOVER), a three-step pipeline combining patient-centric vocabulary mapping, LLM-based constrained rewriting, and cross-model visual verification to enforce semantic equivalence while preventing hallucination. We further introduce MedLayEval, a lightweight 3B evaluator distilled from a 27B verifier that scores expert-lay alignment across five clinically grounded attributes, addressing the poor correlation between standard NLG metrics and clinical judgment. Benchmarking 33 VLMs on MedLayXPlain-122K reveals a systematic Expert-Lay Gap: medical VLMs achieve strong expert captioning but suffer significant lay-register degradation, while general-purpose VLMs produce more accessible language yet lack clinical precision, confirming that neither current paradigm adequately serves patient-facing communication.

The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visual grounding. Such evaluations fail to verify the expert-level lesion perception necessary to ensure the clinical reliability of VLMs. To address these limitations, we introduce CheXpercept, a sequential, multi-level perception benchmark that mirrors a radiologist's cognitive workflow across coarse-level detection, fine-level contour evaluation and revision, and semantic-level attribute extraction. To ensure high clinical fidelity at scale, we construct the dataset using a semi-automated generation pipeline paired with a review by six medical experts. CheXpercept contains 10,400 QA items derived from 2,100 CXRs, covering seven clinically critical pulmonary and cardiac lesions. To demonstrate the current landscape of VLM perception, we benchmark 14 general and medical VLMs on CheXpercept. The models achieve adequate performance only at the coarse level, with accuracy degrading precipitously on deeper visual tasks. Notably, medical VLMs show almost no perceptual advantage over their general-domain counterparts, highlighting a systemic flaw in current domain adaptation. The code and dataset will be publicly available.

As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how well will these systems generalize in new settings, in particular out-of-distribution (OOD) edge-case scenarios in new geographies? In this paper, we study this open question by providing a full factorial analysis with human drivers of Lima, human drivers from New York City, and VLMs and showing them dashcam footage collected from Lima and New York City -- prompting them with a variety of questions under a Visual Question Answering (VQA) paradigm. In particular, we pick these two cities as they are highly challenging driving locations where no Self-Driving Car company currently operates in, and ask questions that span 4 categories: Factual, Ratings, Counterfactual and Reasoning. We find that Humans and VLMs diverge in their responses -- though this is modulated by the type of questions asked, and that Humans answer similarly independent of where they are from (Lima/NYC). To our surprise, we did not find a strong difference in terms of answers (Humans or VLMs) that was modulated by geography, likely due to their high out-of-distribution nature. Our dataset is available at: https://huggingface.co/datasets/Artificio/robusto-2

A companion study established a de-biased, cross-model VLM-as-3D-judge that reliably ranks single-image-to-3D mesh quality where cheap geometry and CLIP proxies fall short. This paper asks: can that judge's preferences specialize a strong open generator, TRELLIS, on one asset class (furniture), cheaply and without human labels? Taking the judge from ranking to optimization is where the work lives. Pushing a VLM judge into the training and evaluation loop exposes failure modes ranking never triggered, so our contribution is an optimization-grade hardening of the judge: a training judge (Qwen2.5-VL-7B) held distinct from an evaluation judge (InternVL3-8B) to break circularity; position-bias correction; and fixes for three failure modes (image overload, geometry-hiding splat renders, and reference-free judging that rewards clean-but-wrong outputs), with calibration evidence (clear-gap win-rate 0.83-1.0; base-vs-base ~0.5). Using this protocol as an independent evaluator, and working only from public models and data with lightweight parameter-efficient adaptation, we find our methods match the strong base rather than exceed it. Independent base samples carry essentially no learnable preference (0.94 order-flip rate), so signal must be engineered by quality-contrastive construction. Across six adaptation methods, two input regimes, and a severity sweep, the most targeted - conditioner repair under severe degradation - reaches parity (0.50) with the base, while no method clears the >=65% win-rate target. The result is mechanistic: clean inputs saturate the judge, flow-DIT fine-tuning washes out through the sampler, and conditioning repair is the locus that moves geometry. Win-rates are directional at n=8 objects. Matching a strong public-data base with cheap adaptation is itself informative: exceeding it needs more than lightweight PEFT on public data, and the judge protocol is reusable.

Current Vision-Language Models (VLMs) are celebrated for their multilingual capabilities, yet they operate under a flawed assumption: that one language corresponds to a single writing system. This overlooks billions of users of multi-script languages like Punjabi, Serbian, Hindi-Urdu, Kurdish, among many others, for whom a model's capability may be fractured by orthographic bias. We introduce PuMVR (Punjabi Multimodal Visual Reasoning), the first benchmark designed to quantify script-dependent bias through 375 culturally grounded image-reasoning tasks across Punjabi's three active scripts (Gurmukhi, Shahmukhi, Roman). Evaluating 10 state-of-the-art VLMs, we expose a substantial Script Gap: models frequently solve visual puzzles in one script while failing identical tasks in another, with accuracy deltas reaching 16% and Script Consistency Rates (SCR) as low as 24.8%. Crucially, visual input boosts absolute performance but does not close this gap, the relative bias persists. Our analysis suggests reasoning patterns show limited cross-script transferability, and Chain-of-Thought pathways diverge based on script alone. We propose SCR as a core metric for script-agnostic evaluation, challenging current multilingual assessment paradigms and providing a framework for equitable AI.

Structural ambiguity arises when a single sentence admits multiple valid interpretations due to its syntactic structure, posing a fundamental challenge for language understanding. Visual scenes serve as useful cues for resolving such ambiguity, and Vision and Language Models (VLMs) need to be capable of deriving possible semantic interpretations from visual scenes. We introduce Language and Vision Structural Ambiguity (LaViSA), a benchmark designed to evaluate the ability of VLMs to resolve structural ambiguity leveraging visual scenes. LaViSA consists of ambiguous sentences, their disambiguated sentences, and corresponding images of these disambiguated sentences across seven ambiguity categories. Using LaViSA, we conduct a comprehensive evaluation of diverse VLMs, including both proprietary and open-source models with varying parameter scales and reasoning capabilities. Experimental results show that although recent VLMs can leverage visual scenes to resolve structural ambiguity to a some extent, they still struggle with certain ambiguity types and visually subtle semantic distinctions, indicating remaining limitations in resolving structural ambiguity using visual scenes.

Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information across the VLM backbone and action head. In a large-scale study of 7 VLA models and 9 VLM baselines, we systematically rank models across categories, finding that VLAs show solid performance on simple concepts while exhibiting larger gaps on richer semantic categories relative to their source VLMs, that VQA co-training is associated with better knowledge retention, and that answer-relevant signals peak in middle VLA layers but attenuate in upper layers. Act2Answer is available at https://tttonyalpha.github.io/act2answer/.

Static visual question answering (VQA) benchmarks age quickly: Once the items leak into training corpora, scores can reflect memorization rather than genuine visual ability, thus obscuring real progress. Rebuilding high-quality benchmarks such as VBench requires substantial human annotation, yet each static release can quickly become another leaked artifact. We propose ReKey, a live benchmark protocol that randomly regenerates the answer-bearing local detail, or visual key, in real images at evaluation time. Using human-validated edit slots, ReKey samples fresh instances with new answers, construction-grounded labels, and controlled visual-search difficulty. On VBench, the ReKey regenerated benchmark reveals a sharp score jump across eight frontier vision-language models (VLMs): The original items score 9.5--18.8 percentage points higher than the regenerated variants. By making the visual key renewable, ReKey keeps evaluation fresh as models and training data evolve.

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception and reasoning capabilities. While numerous benchmarks have evaluated LVLMs from holistic or task-specific perspectives, their capabilities on fine-grained image tasks-fundamental to computer vision-remain insufficiently understood. To address this gap, we introduce FG-BMK, a comprehensive fine-grained evaluation benchmark containing 1.01 million questions and 0.28 million images, covering diverse scenarios from common object-centric domains to specialized domains. FG-BMK jointly evaluates dialogue-level fine-grained semantic recognition and feature-level visual discriminability through human-oriented and machine-oriented paradigms, enabling diagnostic analysis of whether LVLM failures arise from insufficient visual representations, weak visual-to-semantic grounding, or limited fine-grained knowledge. Through extensive experiments on a diverse set of representative LVLMs/VLMs, we find that current LVLMs remain inadequate fine-grained recognizers, with failures arising from intertwined bottlenecks in visual representations, semantic grounding, modality alignment, and category-level knowledge. We further analyze training design factors for improving fine-grained capabilities and examine how visual and linguistic perturbations affect LVLM predictions. These findings provide diagnostic insights into the limitations of current LVLMs and offer guidance for future data construction and model design in developing more reliable LVLMs for fine-grained visual tasks. Our code is open-source and available at https://fg-bmk.github.io/.

We introduce a compact empirical model that quantifies how answer accuracy degrades as a function of frame budget B and temporal distance D in long video understanding -- analyzing performance when recalling content from D seconds in the past using a fraction B of total frames. Long-form models operate under strict budgets, yet no prior framework predicts how accuracy degrades as B shrinks and events recede. We fit a weighted least-squares model on ~155,000 binary predictions across ten models and three sampling strategies, deriving a law where logit-accuracy scales linearly in log-budget with a distance-dependent exponent that decays log-linearly with distance. This budget exponent α(D) captures the marginal value of extra frames at distance D. The law achieves cell-level weighted R^2 = 0.05-0.75 across models. Notably, budget effectiveness at D = 1000 s differs by \approx 7.4\times between the best streaming and base models. STREAMINGVLM achieves α(1000) = 1.26 (95% CI: [1.06, 1.58]), meaning a tenfold budget increase substantially improves long-distance accuracy, while the best Qwen3-VL base model reaches only α(1000) = 0.17 (CI: [0.04, 0.34]). In accuracy space, a 10\times budget increase at D = 1000 s yields +29 percentage points for STREAMINGVLM versus +4 pp for the base model. Sampling strategies show model-dependent trade-offs: random sampling yields higher base sensitivity but steeper distance decay. We demonstrate how α(D) enables principled budget allocation, including a model-ranking reversal at long distance, and propose it as a diagnostic metric for streaming video models.

Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular characteristics, and infection risk. Recent advances in Vision-Language Models (VLMs) have introduced the possibility of automated multimodal wound analysis through image understanding combined with clinical reasoning. This study evaluates the performance of several general-purpose and medically specialized open-source and proprietary VLMs for clinical wound assessment using an expanded, curated dataset of 20 clinically diverse wounds spanning vascular, surgical, ischemic, venous, lymphedema, and amputation-related etiologies. Six VLMs were evaluated using a structured twelve-question clinical framework covering wound classification, infection risk, vascular intervention recommendations, debridement urgency, wound therapy selection, and advanced management planning. Across 20 wound cases and 240 clinician-graded wound-analysis decisions, ChatGPT achieved the highest overall performance with 174/240 correct responses (72.50%), followed by Claude with 149/240 (62.08%). Among the open-source and medically specialized models, HuluMed achieved the strongest performance with 96/240 correct responses (40.00%), followed by Gemma 3 (81/240, 33.75%), MedGemma 4B (62/240, 25.83%), and MedGemma 27B (42/240, 17.50%). The findings suggest that frontier general-purpose multimodal systems currently demonstrate substantially stronger wound-analysis performance than medically specialized alternatives, highlighting the continued importance of broad multimodal reasoning capabilities alongside domain-specific medical knowledge. Although current VLMs demonstrate promising potential for clinical decision support, substantial limitations remain in advanced wound-management reasoning, procedural planning, and autonomous clinical reliability.

Single-image-to-3D generators are improving quickly, but there is no agreed, human-free way to tell whether one generated mesh is better than another. Practitioners commonly rely on cheap automatic proxies (render-space CLIP similarity and mesh geometry-validity statistics), yet how well these track perceived quality is unestablished. We make two contributions. First, we propose and validate a reproducible VLM-judge evaluation protocol: a fixed 24-view headless render rig, two independent vision-language judge families, and a mandatory position-bias correction that queries both presentation orders and keeps only order-consistent verdicts. The two judge families agree substantially with each other (Cohen's kappa = 0.66), well above the chance-agreement floor. Second, using this protocol as the reference, we show the cheap proxies do not substitute for it. Geometry validity is only a weak signal on average (because, as we show, it is bimodal) and stays below our pre-registered target, while render-CLIP is at chance. A learned Bradley-Terry head collapses onto a single manifoldness statistic (giving render-CLIP a negative weight) and matches geometry-only exactly, so learning the feature weights buys nothing. The proxy is also bimodal: it is significantly above chance on contrasts with visible geometric defects but at chance on ambiguous contrasts, consistent with geometry validity tracking the judge only when the defect is visually salient. We therefore recommend the VLM-judge protocol as a reliable, reproducible evaluator under the conditions tested (two feed-forward generators on Google Scanned Objects, with a face-drop degradation regime) and advise against geometry/CLIP proxies as optimization targets.

Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of-thought and retrieval-augmented methods only partially address this, as they neither enforce step-level citation grounding nor route verification failures back to retrieval for correction. We present CaVe-VLM-CoT, a modular reflection-based agentic-RAG framework that enforces evidence-grounded reasoning through a five-stage closed-loop pipeline: Extractor, Retriever, Solver, Citation Injector, and Verifier, in which detected ungrounded claims trigger structured feedback to the Extractor for targeted re-retrieval. Since no existing framework jointly measures retrieval quality, step-wise citation faithfulness, and cross-modal grounding, we propose a suite of 23 component-wise metrics across all stages, anchored by CaVeScore, a composite metric weighting accuracy, citation precision and recall, attribution, and evidence grounding. Without any architectural or prompt modifications, CaVe-VLM-CoT achieves 87.1% accuracy and 56.6% CaVeScore on ScienceQA , and 55.2% accuracy and 35.7% CaVeScore on MMMU (30 subjects).

Recent vision-language models (VLMs) have shown promising progress in generating webpages from visual inputs, yet existing evaluations mainly focus on short, single-screen, and largely static webpages. We introduce LongWebBench, a benchmark for evaluating long-horizon webpage generation from both structural and functional perspectives. LongWebBench contains 490 real-world long webpages for structural fidelity evaluation and 507 goal-oriented interaction tasks over 129 webpages for functional evaluation. It employs two complementary protocols: a multi-dimensional VLM-based metric for assessing long-range structural coherence, and a DOM-augmented agent-based pipeline for end-to-end functional verification. We further examine the automatic evaluation protocols through human agreement analysis. Experiments with state-of-the-art open-source and proprietary VLMs under single-image and multi-image settings reveal that structural fidelity degrades as webpage length increases, while visually plausible generations often fail to support executable multi-step interactions. These results highlight the need to evaluate long webpage generation beyond visual similarity, with executable interaction as a core criterion. Our code and data are available at https://github.com/zheny2751-dotcom/LongWebBench.

Vision-language models that answer questions about chest radiographs are evaluated by their accuracy on labels derived from radiology reports. High benchmark accuracy is often interpreted as evidence that the model uses the image. A model that answers from the finding named in the question can score as well as a model that uses the radiograph. Keeping the question fixed, we audit eight open-weight systems by swapping in another patient's radiograph with the same or the opposite label, occluding the radiologist-marked region or an equal region elsewhere, and removing the radiograph or replacing it with noise or a photograph. On 2,548 yes-or-no questions from MIMIC-CXR, one multimodal model answers Yes regardless of the image, another multimodal model changes its answers without following the label, and four systems use the image but keep about half of their correct answers when the radiograph is swapped for an opposite-label radiograph. A medical model that receives only the question text scores 55.3% on the pooled questions, higher than two multimodal systems. It scores 91.8% where every finding is present, and answering Yes to every question scores 100% there. Where the image is necessary, the best multimodal system exceeds this model by 10.4% in balanced accuracy. The categories are unchanged on CheXpert. Confidence is not higher when a correct answer depends on the marked region. In a reader study with three radiologists, the two radiologists who read a balanced set of 200 cases score 86.0% and 82.0%, and the systems score 50.0% to 73.0%. Accuracy does not establish image use, but an intervention on the image can test it.

Large Vision Language Models (VLMs) excel at visual question answering and semantic grounding, but their capacity for autonomous logical reasoning remains underexplored. Existing anomaly benchmarks emphasize visual errors or direct prompting rather than the physical and social common sense needed for open-world deployment. To address this, we introduce LAD-bench, a benchmark of more than 1,000 curated synthetic images with logical anomalies across four domains: Residential, Urban, Collaborative, and Nature. We further propose a Tiered Prompting Protocol based on progressive disclosure, which measures how much explicit assistance a model needs to localize and reason about a logical fault. Evaluating leading foundation models reveals substantial weaknesses: even the best achieves only 70.11% overall accuracy, showing that implicit logical fault detection remains unsolved. Crucially, models often fail to identify anomalies even after receiving explicit hints in deeper tiers. By surfacing these limitations in sequential multimodal reasoning, LAD-Bench offers a rigorous framework for advancing the safety, reliability, and cognitive alignment of autonomous visual systems. Dataset and Code: https://huggingface.co/datasets/SahasraK/LADBench

Visual perception depends on top-down goals and bottom-up sensory mechanisms. Vision-language models implement both, allowing us to treat each component as a separable hypothesis about what drives where we look. We compared spatial attention maps from six vision-language models against human fixation heatmaps recorded on 200 images during two tasks (general description and social captioning). The six models spanned a 2$\times$2 factorial of CNN vs.\ ViT encoders crossed with LSTM vs.\ Transformer decoders, plus Molmo 7B-D and Qwen3.5 9B. We found that both decoder and encoder architecture shaped alignment, but decoder choice dominated. LSTM vs.\ Transformer decoders increased alignment by 40--50 percentage points (80--87% vs.\ 40--59% of the human noise ceiling). In contrast, CNN vs.\ ViT encoders contributed a secondary 5--20 point advantage depending on decoder family, with CNN-LSTM the most aligned model overall (85--87%). Despite their alignment advantage, LSTM-decoder attention maps were spatially diffuse and minimally task-differentiated; ViT-Transformer, the weakest in alignment, showed the sharpest spatial concentration and strongest task differentiation. A hemispatial-neglect simulation confirmed that ablating attention impacted LSTM decoders more than Transformer decoders. In an exploratory extension using TRIBE-simulated synthetic neural responses, fixation alignment and neural relevance dissociate: CNN-Transformer attention maps better predicted synthetic brain activity despite lower fixation alignment, with attention maps best predicting early visual cortex. Together, top-down and bottom-up components trade off what they predict in behavioral and synthetic neural data.

Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical. A common intuition, which we call the Attention-Confidence Assumption, holds that reliability follows from "structural" visual perception: tight attention on relevant regions should signal a trustworthy answer, while scattered attention signals confusion. We challenge this through the VLM Reliability Probe (VRP), a systematic cross-family study of reliability signals in contemporary Vision-Language Models (VLMs). We introduce structural-attention metrics, cluster counts (C_k) and spatial entropy (H_s), to quantify the visual encoder's gaze, and track its evolution (Delta H_s) across layers. This reveals a "Symbolic Detachment": models often "Early Lock" visual features only to diffuse attention later, severing early perception from final generation. Contrary to the grounding hypothesis, we find a "Cluster Failure": spatial attention has near-zero correlation (R approx 0.001) with accuracy. Instead, reliability is a phenomenon of generation dynamics and internal-state distributions. Self-Consistency, the agreement rate across sampled reasoning paths, is the dominant predictor of truth (R = 0.429). Scaling causal interventions exposes a sharp architectural divergence: LLaVA locks its prediction in a fragile late-stage bottleneck, whereas PaliGemma and Qwen2-VL distribute reliability globally, staying resilient even when ~50% or more of their most predictive layer is destroyed. For current VLMs, reliability signals are detached from visual grounding maps and are best inferred from generation-time dynamics and hidden-state probes.

Current multilingual evaluations for Vision-Language Models (VLMs) assume a one-to-one mapping between language and orthography, overlooking billions of users of multi-script languages. We introduce PuMVR (Punjabi Multimodal Visual Reasoning), a benchmark of 1,000 strictly parallel image-text instances across Punjabi's three active scripts: Gurmukhi, Shahmukhi, and Roman. Evaluating 10 state-of-the-art VLMs, we expose a substantial and systematic Script Gap. Models frequently solve visual tasks in one script while failing identical tasks in another, with accuracy deltas reaching 16%. Crucially, visual input boosts absolute performance uniformly yet does not close the orthographic gap. Furthermore, cross-script in-context transfer is highly brittle, exposing script-locked knowledge representation. Supported by McNemar tests across all script pairs, our findings demonstrate that current "multilingual" VLMs are not truly multi-script. We propose the Script Consistency Rate (SCR), which falls as low as 24.8% on our benchmark, as a mandatory metric for script-agnostic evaluation to ensure equitable AI access. Data and code are available at: https://github.com/prabhjotschugh/Not-Truly-Multilingual-PuMVR.

Existing vision-language model (VLM)-based AI-generated image quality assessment (AIGIQA) methods suffer from a fundamental semantic-distortion dimensional conflict: monolithic representations optimized for semantic discrimination inherently entangle compositional understanding with low-level perceptual sensitivity, rendering them blind to fine-grained quality degradations. We introduce MST-CLIPIQA, a multi-scale two-stream framework that achieves hierarchical vision-language alignment through explicit representational decoupling. Our architecture leverages dual CLIP encoders with complementary patch granularities: coarse-grained streams capture global semantic coherence while fine-grained streams preserve textural signatures and artifact patterns. An information bottleneck-inspired gated fusion mechanism performs adaptive cross-scale distillation, with optional cross-attention enabling prompt-anchored correspondence evaluation when generation prompts are available. Extensive experiments across five benchmarks establish new state-of-the-art results, achieving average improvements of 1.11 percent SRCC on quality and 2.35 percent SRCC on text-image correspondence prediction, while maintaining efficiency with only 0.8M trainable parameters. Our project is available at https://github.com/YMlinfeng/MST-CLIPIQA.

Safe deployment of clinical vision-language models (VLMs) requires reliable uncertainty estimation (UE): a signal indicating when predictions should be trusted or escalated to a clinician. We test whether current UE methods actually deliver this signal. Benchmarking 8 methods across 12 VLMs on clinical visual question-answering (VQA), we find that UE quality is not an intrinsic property of the UE method: it tracks model accuracy, degrading precisely where the model performance is weakest, and therefore where reliability is most needed. When we stress-test models by hiding the correct option among the multiple-choice answers (NOTA perturbations), accuracy collapses while uncertainty barely changes, leaving models systematically miscalibrated. Yet, we find that uncertainty on the unperturbed input reliably anticipates which predictions will collapse under NOTA, indicating that UE in current VLMs carries diagnostic information about model fragility. Our results position UE as a diagnostic tool for identifying fragile predictions and motivate perturbation-based evaluation as a path toward safe clinical deployment.

Knowledge-based visual question answering (KB-VQA) lets vision-language systems answer questions that exceed their parametric knowledge by conditioning a reader on passages retrieved from a Wikipedia-derived knowledge base. In pure-text long-context LLMs, retrieved-context use follows the U-shaped lost-in-the-middle effect of Liu et al. (2024): information at the start and end of context is used, the middle is lost. Whether this transfers to deployed multimodal KB-VQA is open. To close this gap, we design the first controlled probe of reader-side position dependence in multimodal KB-VQA: a gold-position protocol in which only the gold passage's prompt slot varies within question. We run it on three open-source 7B/8B VLM readers and two KB-VQA benchmarks with up to 20 retrieved passages. The shape flips from U to primacy: gold-at-first beats gold-at-last by 16 to 26 points on all six combinations of reader and benchmark, an effect we call Lost at the End; the gap holds at every scale we test, 3B to 32B, attenuating at 32B. Three targeted ablations narrow the cause. A text-only control that removes the image and changes nothing else shows the primacy is already present in text mode and does not depend on the image. Image-position and distractor-shuffle ablations trace the effect to prompt slot 0 of the instruction-tuned reader, where a second answer-bearing passage placed later is largely wasted. On a frozen reader, three retrieval-side fixes (MMR, oracle reranking, rank-based reordering) all fail to improve on the deployment default. Our findings indicate that recall@k is the wrong metric for deployed KB-VQA and that the remaining headroom sits on the reader side; we release our protocol as a controlled instrument for evaluating reader-side interventions.

Human perception of visual scenes is inherently temporal. We instinctively recognise whether a fruit is ripening or rotting, whether construction is progressing or being demolished, and approximately how much time separates two photographs of the same subject. Whether large vision-language models (VLMs) share this competence remains an open and practically important question. We introduce CHRONOSIGHT, a rigorously controlled benchmark evaluating five dimensions of visual temporal reasoning: CHRONORANK (chronological ordering of image sequences), CHRONOLOCATE (ordinal stage localisation from a single image), CHRONODELTA (estimation of time elapsed between two images on a logarithmic scale), CHRONOREVERSE (detection of temporally reversed sequences), and CHRONOODD (identification of a temporal outlier within a set). The benchmark comprises 1{,}000 items across eight process families (biological growth, food transformation, physical weathering, construction, environmental change, human ageing, astronomical phenomena, and urban dynamics) spanning timescales from minutes to millennia. We evaluate eight open-source VLMs (500 M to 19 B parameters) under two prompting regimes and collect human performance baselines. Human performance averages 0.89 across tasks; the best open model (Qwen2.5-VL-7B) reaches 0.40 under direct prompting, a gap we term chronological blindness. Lightweight LoRA fine-tuning on 151 examples raises CHRONODELTA accuracy from near-zero to 0.43, transferring zero-shot to related tasks (CHRONOODD: 0.37; CHRONOREVERSE: 0.64)suggesting the bottleneck is partly instruction following rather than visual perception. Benchmark, code, and predictions will be released upon acceptance.

High-quality time series forecasting is pivotal for real-world decision-making. However, traditional point-wise metrics often fail to reveal complex temporal patterns and align poorly with human intuitive preferences. While the ''LLM-as-a-Judge'' paradigm has revolutionized text evaluation by providing flexible, human-aligned judgment, its application to time series remains largely unexplored. In this paper, we leverage Vision-Language Models (VLMs) as judges for time series forecasting, harnessing their ability to comprehend time series plots grounded in textual information. Specifically, we propose a novel framework integrating micro- and macro-level judgments informed by contextual information to evaluate time series forecasting. To this end, we introduce TimeVista, a comprehensive VLM-as-a-Judge benchmark comprising 5563 time series samples paired with detailed evaluation rubrics. Extensive meta-evaluations demonstrate that VLMs are highly reliable judges, achieving significantly higher consistency with human preferences than conventional metrics. Building upon our benchmark, we comprehensively assess recent Time Series Foundation Models (TSFMs) under the VLM-as-a-Judge paradigm. Our results demonstrate that VLMs serve as robust and interpretable judges, providing a comprehensive, human-aligned standard for evaluating time series models.

Real-world documents combine text with tables, charts, photographs, and diagrams arranged in diverse layouts, yet existing research on multimodal large language models (MLLMs) for document QA predominantly produces text-only responses, underutilizing these visual elements. We introduce VinQA, a dataset for long-form answer generation where cited visual elements are explicitly interleaved with their supporting text and grounded in relevant document pages. To support this task, we study two encoding methods for feeding raw document page images into an MLLM, along with their visual-element citation mechanisms: (1) Page Encoding, which directly encodes full-page images with bounding boxes of visual elements and treats these boxed regions as citable units; and (2) Modality Encoding, which parses each page to extract text and crop visual elements, encodes them separately, and uses these cropped elements as citable units. In our experiments, we propose M-GroSE, a multimodal evaluation framework extending GroUSE to assess answers along four dimensions: completeness, answer relevancy, faithfulness, and unanswerability. We additionally report Visual Source F1 to directly measure visual citation accuracy. Although proprietary frontier models still achieve the best overall scores on the VinQA test split, fine-tuning open Qwen2.5-VL models on the training split substantially improves their performance and narrows this gap. Modality Encoding is initially more robust for complex documents with long text, many visual elements, and diverse citation requirements. After training on VinQA, however, Page Encoding reaches a comparable level, competing effectively even without the explicit parsing used in Modality Encoding. Finally, Visual G-Eval, an MLLM-based judge, confirms that fine-tuned models insert visual elements at semantically appropriate positions with faithful supporting text.

A vision-language model can answer a question about a medical image fluently and confidently while barely using the image, leaning instead on language priors. In medicine this is the failure that matters most, because the answer looks trustworthy and is not, and the only protection is a confidence score reliable enough to tell the system when to abstain. We ask a deployment question rather than an accuracy one: how much imaging work a model can safely handle alone, and which confidence signal makes that possible. We evaluate seven confidence estimators across five open-weight LVLMs and three medical visual-question-answering datasets spanning broad clinical imaging, radiology, and pathology, with every probe trained only on natural images and applied without adaptation. Recast as bounded selective prediction (automate a case only when confidence clears a threshold, defer the rest), the comparison is cautionary. The standard metrics are poor guides: discrimination barely separates the methods, and the weak calibration of a cheap self-report is cheaply removed by off-domain temperature scaling without changing deployable yield. What distinguishes a usable estimator is the high-confidence region a clinician acts on: the weakest baselines are confidently wrong on 41 to 45 percent of their errors against 1 to 4 percent for the best probe, and no estimator is reliably best across domains or models. Safe handoff is governed at two levels: base-model competence sets a ceiling, so a well-calibrated score recovers roughly a third of radiology cases at a 20 percent error tolerance but almost none of pathology; the confidence layer then decides how much of that ceiling is reachable. The usable role today is calibrated triage, not autonomy: automate the cases a calibrated score marks safe, route the rest to a clinician. We release all outputs, correctness judgments, and confidence scores, with code.

Human visual attention plays an important role in how people perceive and respond to environments containing potential risks. This study investigates whether large vision-language models can identify the same regions of a scene that attract human attention in safety-relevant environments. Eye-tracking data were collected from ten participants viewing 33 scene images representing environments with varying levels of potential risk using Pupil Invisible wearable glasses. Gaze coordinates were mapped onto stimulus images to generate population-averaged human gaze heatmaps. In parallel, GPT-4o was prompted through the OpenAI Vision Application Programming Interface (API) to generate spatial predictions of visual attention, which were converted into saliency maps for comparison with human gaze patterns. Spatial alignment between human gaze heatmaps and model-generated saliency maps was evaluated using four complementary metrics: Pearson correlation (r = 0.515 +- 0.117), Normalised Scanpath Saliency (NSS = 0.988 +- 0.323), Kullback-Leibler divergence (KL = 1.766 +- 0.844), and Area Under the Receiver Operating Characteristic Curve using the Judd formulation (AUC-Judd = 0.806 +- 0.076). A cross-model comparison with Gemini Pro, Gemini Flash, and Claude showed that all models exceeded the AUC-Judd chance baseline of 0.5 and achieved positive NSS scores. Gemini Pro demonstrated the strongest spatial localisation according to three of the four metrics, whereas GPT-4o produced the closest distributional match to human attention as measured by KL divergence. These findings suggest that large vision-language models can identify regions that broadly correspond to where humans direct visual attention in safety-relevant scenes without requiring eye-tracking training data. The results highlight the potential of vision-language models as a scalable tool for approximating human attentional patterns.