VLM Evaluation

Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative understanding requires grounding who is doing what, when, and where, maintaining coherent entity representations across dynamic visual and temporal contexts. We introduce NarrativeTrack, the first benchmark to evaluate narrative understanding in MLLMs through fine-grained entity-centric reasoning. Unlike existing benchmarks limited to short clips or coarse scene-level semantics, we decompose videos into constituent entities and examine their continuity via a Compositional Reasoning Progression (CRP), a structured evaluation framework that progressively increases narrative complexity across three dimensions: entity existence, entity changes, and entity ambiguity. CRP challenges models to advance from temporal persistence to contextual evolution and fine-grained perceptual reasoning. A fully automated entity-centric pipeline enables scalable extraction of temporally grounded entity representations, providing the foundation for CRP. Evaluations of state-of-the-art MLLMs reveal that models fail to robustly track entities across visual transitions and temporal dynamics, often hallucinating identity under context shifts. Open-source general-purpose MLLMs exhibit strong perceptual grounding but weak temporal coherence, while video-specific MLLMs capture temporal context yet hallucinate entities' contexts. These findings uncover a fundamental trade-off between perceptual grounding and temporal reasoning, indicating that narrative understanding emerges only from their integration. NarrativeTrack provides the first systematic framework to diagnose and advance temporally grounded narrative comprehension in MLLMs.

Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (VLMs) provide a promising foundation for this task because they can integrate visual observations with language-based social knowledge. However, existing untuned VLMs still struggle to reliably understand fine-grained social norms, making task-specific fine-tuning essential. At the same time, no large-scale egocentric dataset is available this task. To address these challenges, we introduce MUSON, a multimodal dataset for short-horizon social navigation containing 10,110 egocentric samples collected across diverse indoor and outdoor social scenes. MUSON adopts a structured five-step chain-of-thought annotation framework comprising perception, prediction, reasoning, action, and explanation. It explicitly models static physical constraints and employs a standardized six-action decision space. Compared with existing social-navigation datasets, MUSON provides consistent annotations for reasoning, actions, and explanations. We evaluate ten representative small-to-medium VLMs on MUSON. Qwen3-VL-8B achieves the strongest decision-level performance, attaining the highest action accuracy of 0.7765 and Macro-F1 score of 0.7490, as well as the lowest collision rate of 0.0609. These results demonstrate that MUSON is an effective and reusable benchmark for advancing socially compliant navigation. The dataset is publicly available at https://github.com/MUSON-dataset/MUSON/releases/tag/v1.0.

Vision-language models (VLMs) are increasingly integrated into clinical workflows. However, existing benchmarks primarily assess performance on common anatomical presentations and fail to capture the challenges posed by rare variants. To address this gap, we introduce AdversarialAnatomyBench, the first benchmark comprising naturally occurring rare anatomical variants across diverse imaging modalities and anatomical regions. We call such variants that violate learned priors about "typical" human anatomy natural adversarial anatomy. Benchmarking 25 state-of-the-art VLMs with AdversarialAnatomyBench yielded three key insights. First, when queried with basic medical perception tasks, mean accuracy dropped from 71% on typical to 28% on atypical anatomy. Even the best-performing models, GPT-5, Gemini 2.5 Pro, and Llama 4 Maverick, showed performance drops of 41-51%. Second, model errors closely mirrored expected anatomical biases. Third, neither model scaling nor interventions, including bias-aware prompting and test-time reasoning, resolved these issues. These findings highlight a critical limitation in current VLMs: their poor generalization to rare anatomical presentations. AdversarialAnatomyBench provides a foundation for systematically measuring and mitigating anatomical bias in multimodal medical artificial intelligence (AI) systems.

Large language models (LLMs) have demonstrated several emergent behaviors with scale, including reasoning and fluency in long-form text generation. However, they continue to struggle with tasks requiring precise spatial and positional reasoning. ASCII art, a symbolic medium where characters encode structure and form, provides a unique probe of this limitation. We introduce ASCIIBench, a novel benchmark for evaluating both the generation and classification of ASCII-text images. ASCIIBench consists of a filtered dataset of 5,135 class-labeled ASCII images and is, to our knowledge, the first publicly available benchmark of its kind. Alongside the dataset, we release weights for a fine-tuned CLIP model adapted to capture ASCII structure, enabling the evaluation of LLM-generated ASCII art. Our analysis shows that cosine similarity over CLIP embeddings fails to separate most ASCII categories, yielding chance-level performance even for low-variance classes. In contrast, classes with high internal mean similarity exhibit clear discriminability, revealing that the bottleneck lies in representation rather than generational variance. These findings position ASCII art as a stress test for multimodal representations and motivate the development of new embedding methods or evaluation metrics tailored to symbolic visual modalities. All resources are available at https://github.com/ASCIIBench/ASCIIBench.

How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distractors can intensify inverse scaling, causing models to reason longer but less effective reasoning traces. In this work, we investigate whether similar phenomena arise in multimodal settings. We introduce Idis (Images with distractors), a visual question-answering dataset that systematically varies distractors along semantic and numerical dimensions. Our analyses reveal that visual distractors affect reasoning VLMs in a fundamentally different way from textual distractors: although inverse scaling still emerges, visual distractors reduce accuracy without increasing reasoning length. We further show that attribute counts extracted from reasoning traces provide key insights into how distractors interact with reasoning length and accuracy. As a sanity check, we propose a simple prompting strategy that mitigates distractor-driven predictions in reasoning vision-language models.

While Multimodal Large Language Models (MLLMs) have become adept at recognizing objects, they often lack the intuitive, human-like understanding of the world's underlying physical and social principles. This high-level vision-grounded semantics, which we term visual knowledge, forms a bridge between perception and reasoning, yet remains an underexplored area in current MLLMs. To systematically evaluate this capability, we present VKnowU, a comprehensive benchmark featuring 1,680 questions in 1,249 videos, covering 8 core types of visual knowledge spanning both world-centric (e.g., intuitive physics) and human-centric (e.g., subjective intentions). Evaluation of 28 SOTA MLLMs reveals that leading models still fall short of human performance, with particularly notable gaps in the world-centric. To bridge this gap, we introduce a new dataset, VKnowQA, and VideoKnow+, a baseline model that explicitly incorporates visual knowledge into MLLMs. VideoKnow+ follows a structured See-Think-Answer paradigm and adopts reinforcement learning with visual knowledge reward, achieving a +3.7% improvement on VKnowU and consistent gains on MVBench (+5.4%), Video-MME (+7.0%), and MMVU (+5.7%). Our work highlights visual knowledge as a missing cornerstone for developing more generalizable MLLMs that can not only see but also truly understand our worlds.

Visual corruptions can change vision--language model (VLM) behavior in ways that top-1 accuracy does not capture. A model may keep the same answer while losing distributional support, or improve accuracy through unstable wrong-to-correct changes. We introduce Bench-C, a controlled multiple-choice testbed for studying these effects. It selects semantically diverse samples whose predictions respond to corruption, and evaluates them under 19 corruption types and five severity levels. To measure how corruption changes the option distribution, we introduce the Robustness Alignment Score (RAS), which combines confidence-correctness alignment with uncertainty direction. We further separate originally correct samples from originally wrong samples, and track whether changes are temporary or persistent across severity. Experiments across 13 VLMs reveal a counterintuitive pattern: mild corruptions can improve top-1 accuracy while degrading prediction structure. These failures include silent degradation, erroneous overconfidence, and severity-dependent persistence. Bench-C therefore supports robustness evaluation that goes beyond final answers and attributes where reliability changes occur. Code and data are available at https://github.com/xiangjieSui/Bench-C.

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal settings, their impact on multimodal foundation models, particularly vision-language models (VLMs), remains largely underexplored. In this work, we introduce BackdoorVLM, the first comprehensive benchmark for evaluating backdoor attacks and defenses on VLMs across a broad range of settings. It adopts a unified perspective that injects and analyzes backdoors across core vision-language tasks, including image captioning and visual question answering. BackdoorVLM organizes multimodal backdoor threats into 5 representative categories: targeted refusal, malicious injection, jailbreak, concept substitution, and perceptual hijack. Each category captures a distinct pathway through which an adversary can manipulate a model's behavior. We evaluate these threats using 12 representative attack methods spanning text, image, and bimodal triggers, tested on 2 open-source VLMs and 3 multimodal datasets along with 5 representative defense methods. Our analysis reveals that VLMs exhibit strong sensitivity to textual instructions, and in bimodal backdoors the text trigger typically overwhelms the image trigger when forming the backdoor mapping. Notably, backdoors involving the textual modality remain highly potent, with poisoning rates as low as 1% yielding over 90% success across most tasks. Moreover, existing defenses lack generalization across trigger types and backdoor scenarios, leading to unreliable protection against diverse triggers across modalities and forms. These findings highlight significant, underexplored vulnerabilities in current VLMs. We hope that BackdoorVLM can serve as a useful benchmark for analyzing and mitigating multimodal backdoor threats.

In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a new Visual Question-Answering (VQA) dataset specifically designed to elicit and evaluate Foresight Intelligence. Using FSU-QA, we conduct the first comprehensive study of state-of-the-art Vision-Language Models (VLMs) under foresight-oriented tasks, revealing that current models still struggle to reason about future situations. Beyond serving as a benchmark, FSU-QA also enables the assessment of world models by measuring the semantic coherence of their generated predictions, quantified through performance gains when VLMs are augmented with such outputs. Our experiments further demonstrate that FSU-QA can effectively enhance foresight reasoning: even small VLMs fine-tuned on FSU-QA surpass much larger, advanced models by a substantial margin. Together, these findings position FSU-QA as a principled foundation for developing next-generation models capable of truly anticipating and understanding future events. Furthermore, beyond model performance, we examine whether WM-generated predictions remain semantically consistent by using VLM-based proxy judges, and validate this evaluation protocol through shuffled control experiments. Fine-tuning models on FSU-QA leads to substantial improvements in foresight understanding, demonstrating the dataset's effectiveness and offering a principled foundation for future research.

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose RoadBench, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using Bird's-Eye View (BEV) and First-Person View (FPV) image inputs. This benchmark comprises eight tasks consisting of 3,040 strictly manually verified test cases, constructed from 2,137 unique BEV images and 721 unique FPV images collected from five Chinese cities with relatively consistent traffic conventions. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 20 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs.

Visual persuasion uses images to shape cognition, emotion, and behavior, with its effects depending on both visual attributes and semantic context. Despite recent progress, it remains unclear whether Vision-Language Models (VLMs) understand visual persuasiveness. This motivates us to ask: can VLMs assess whether an image persuasively supports an intended message, which visual factors shape this judgment, and do they align with human judgments? Through empirical analyses on image-message pairs where human raters consistently agree on the persuasiveness judgment, we show that VLMs exhibit a recall-oriented bias: they over-predict images as persuasive while achieving high recall. We introduce Visual Persuasive Factors (VPFs), a taxonomy informed by cognitive psychology for quantifying visual cues that shape persuasive judgments. Our factor-level analysis reveals that VPFs distinguish human persuasiveness judgments, whereas VLMs only partially reproduce these patterns, often generating false positives by treating persuasion-relevant cues as sufficient evidence. Building on this insight, we evaluate VPF-guided interventions and find that properly framed VPF knowledge can improve performance, but merely specifying visual cues or adding step-by-step reasoning is insufficient. By analyzing model rationales at the level of functional reasoning steps, we further identify a central bottleneck in connecting object identification to semantic message alignment.

Multimodal LLMs can answer many questions in vision-centric benchmarks without looking at the image, using linguistic priors and skewed answer distributions. Blind evaluation shows what a model already answers this way, but not what it could learn from the test set's own regularities. Extending partial-input auditing (e.g., hypothesis-only baselines in natural language inference), we argue that benchmark designers should "train on the test set": probe the artifact they release for exploitable patterns. Our Test-set Stress-Test (TsT) cross-validates a text-only Qwen2-7B on the test set's questions and answer options, yielding a benchmark-level score and a per-question bias score s(x); a random forest on hand-crafted features adds a fast, interpretable audit. On the template-based VSI-Bench and CV-Bench, the held-out score is 17.9 and 13.1 points above the model's own zero-shot score. On MMMU it learns little, even though GPT-4o correctly answers 52.3% of its multiple-choice questions without the image, so blind success there reflects pretrained knowledge rather than learnable test-set patterns. Iterative Bias Pruning (IBP) removes the questions with the highest s(x) and re-diagnoses; on VSI-Bench it widens a fine-tuned model's vision-blind gap more than random removal at the same rate. We also release VSI-Bench-Debiased, which lowers a fine-tuned model's blind score from 44.7 to 32.0 while its vision score falls only from 57.1 to 48.7.

The rapid advancement of long-context vision language models (LCVLMs) has led to a significant expansion of their context windows. However, an extended context window does not guarantee the effective utilization of the context, posing a critical challenge for real-world applications. Current evaluations of such long-context faithfulness in multimodal settings remain limited to short contexts. To bridge this gap, we introduce MMLongCite, the first benchmark evaluating the faithfulness of LCVLMs via multimodal citation generation. MMLongCite features 2,280 examples across 8 tasks and diverse modalities (image, video, interleaved), with context lengths scaled from 16K to 128K tokens. To test spatial localization capabilities of LCVLMs, we also introduce MMLongCite-HR, evaluating fine-grained visual grounding amidst dense pixel spaces. Through extensive benchmarking of cutting-edge LCVLMs, we provide a systematic analysis of current multimodal citation capabilities. Our results reveal a significant discrepancy between answer correctness and citation faithfulness. We also conduct attention pattern investigations and in-depth error analyses to reveal the underlying phenomena of failures in LCVLMs. MMLongCite establishes a rigorous foundation for diagnosing and advancing the faithfulness of LCVLMs. We hope our findings provide meaningful insights to drive further improvements in the long-context capabilities of LCVLMs.

Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers about 76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25-fold token reduction (25 Hz to 1 Hz). Across 10 benchmarks, with and without filtering, audio yields clear gains on tasks requiring speech comprehension or cross-modal grounding, while vision-centric suites remain largely unaffected. Our results show that speech encoders play a larger role in video understanding than current benchmarks suggest. We will open-source our work at https://github.com/naver-ai/unimambamia-av.

Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both language-guided and vision-only image classification with a diverse set of dual-encoder VLMs, including both well-established and recent models such as SigLIP 2 and RADIOv2.5. The performance is compared in a standard setup on the ImageNet-1k validation set and its label-corrected variant. The key factors affecting accuracy are analysed, including prompt design, class diversity, the number of neighbours in k-NN, and reference set size. We show that language and vision offer complementary strengths, with some classes favouring textual prompts and others better handled by visual similarity. To exploit this complementarity, we introduce a simple, learning-free fusion method based on per-class precision that improves classification performance. The code is available at: https://github.com/gonikisgo/bmvc2025-vlm-image-recognition.

Vision language models (VLMs) excel at zero-shot visual classification, but their performance on fine-grained tasks and large hierarchical label spaces is understudied. This paper investigates whether structured, tree-based reasoning can enhance VLM performance. We introduce a framework that decomposes classification into interpretable decisions using decision trees and evaluates it on fine-grained (GTSRB) and coarse-grained (CIFAR-10) datasets. Although the model achieves 98.2% accuracy in understanding the tree knowledge, tree-based reasoning consistently underperforms standard zero-shot prompting. We also explore enhancing the tree prompts with LLM-generated classes and image descriptions to improve alignment. The added description enhances the performance of the tree-based and zero-shot methods. Our findings highlight limitations of structured reasoning in visual classification and offer insights for designing more interpretable VLM systems.

Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current Video QA benchmarks genuinely require temporal frame selection, or can most questions be answered regardless of which frames are shown? We introduce Frame Selection Sensitivity (FSS), a per-sample diagnostic that measures how much VLM accuracy changes when the most relevant frames are replaced with the least relevant ones. Across six benchmarks and eight VLMs, we find that a large majority of samples are frame-agnostic: only a minority are genuinely sensitive to frame choice. Combining FSS with a Language Independence Score (LIS) reveals that merely 5.5--31% of samples are Temporally Sensitive. We construct TempCore, compact evaluation subsets that isolate these temporal samples from existing benchmarks, and will release code and per-sample annotations upon publication.

Existing plant-disease datasets target classification and detection, leaving vision-language models unable to support interactive, reasoning-based diagnosis. To address this, we present PlantExpertVQA, a large-scale visual question answering (VQA) dataset designed to advance vision-language models for agricultural decision-making. It is compiled from 45 open-source datasets, including the widely used PlantVillage corpus, and comprises 765,186 high-quality question-answer (QA) pairs grounded over 150,841 images spanning 38 crop species and 89 disease conditions. Questions are organized into 3 levels of cognitive complexity and 9 distinct categories. Each was phrased following expert guidance and generated via an automated two-stage pipeline: template-based QA synthesis from image metadata, followed by multi-stage linguistic re-engineering. The dataset was iteratively reviewed by domain experts for scientific accuracy and relevance. We find that current frontier vision-language models, including recent open-source instruction-tuned multimodal LLMs, perform poorly on PlantExpertVQA. However, parameter-efficient fine-tuning of a compact 2B-parameter model on a small fraction of the dataset yields substantial improvements across all question categories, demonstrating its effectiveness for domain adaptation.

Sign Language (SL) enables two-way communication for the deaf and hard-of-hearing community, yet many sign languages remain under-resourced in the AI space. Sign Language Instruction Generation (SLIG) produces step-by-step textual instructions that enable non-SL users to imitate and learn SL gestures, promoting two-way interaction. We introduce BdSLIG, the first Bengali SLIG dataset, used to evaluate Vision Language Models (VLMs) (i) on under-resourced SLIG tasks, and (ii) on long-tail visual concepts, as Bengali SL is unlikely to appear in the VLM pre-training data. To enhance zero-shot performance, we introduce Sign Parameter-Infused (SPI) prompting, which integrates standard SL parameters, like hand shape, motion, and orientation, directly into the textual prompts. Subsuming standard sign parameters into the prompt makes the instructions more structured and reproducible than free-form natural text from vanilla prompting. We envision that our work would promote inclusivity and advancement in SL learning systems for the under-resourced communities.

Medical report understanding from real-world document images is essential for generating patient-facing explanations and enabling structured information exchange in clinical systems. Existing VLMs and LLMs have shown strong performance on document understanding, but structured understanding of medical reports remains insufficiently benchmarked. Therefore, we introduce MedRepBench, a benchmark with 1,925 de-identified Chinese medical report images spanning diverse departments, patient demographics, and acquisition formats. In MedRepBench, we mainly focus on report-grounded interpretation rather than evaluating diagnostic reasoning, treatment recommendation, or the integration of patient history. The interpretation is defined as structured extraction of report fields (e.g., item, value, unit, reference range, abnormal flag) plus a patient-facing explanation grounded strictly in the report content. The benchmark primarily evaluates end-to-end VLMs, and also includes a controlled text-only setting (high-quality OCR + LLM) to approximate an upper bound when character recognition errors are minimized. Our evaluation framework provides two complementary protocols: (1) an objective protocol measuring field-level recall of structured items, and (2) an automated subjective protocol that uses an LLM-based judge to score factuality, interpretability, and reasoning quality under a fixed prompt. Using the objective metric as a reward signal, we also provide a lightweight GRPO-based alignment baseline for a mid-sized VLM, which improves field-level recall by up to 6%. Finally, we analyze practical limitations of OCR+LLM pipelines, including layout-related errors and additional system latency, showing the need for robust end-to-end vision-based medical report understanding. The dataset and evaluation resources are publicly available on https://huggingface.co/datasets/MedRepBench/MedRepBench.

We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) interpret and reason over visual and textual information beyond English. VMMU consists of 2.5k multimodal questions across 7 tasks, covering a diverse range of problem contexts, including STEM problem solving, data interpretation, rule-governed visual reasoning, and abstract visual reasoning. All questions require genuine multimodal integration, rather than reliance on text-only cues or OCR-based shortcuts. We evaluate a diverse set of state-of-the-art proprietary and open-source VLMs on VMMU. Despite strong Vietnamese OCR performance, proprietary models achieve only 66% mean accuracy. Further analysis shows that the primary source of failure is not OCR, but instead multimodal grounding and reasoning over text and visual evidence. Code and data are available at https://vmmu-bench.github.io/

Inspired by human categorization, visual reasoning about object properties, such as physical attributes and functions, involves identifying and recognizing low-level details and higher-level abstractions. While current visual question answering (VQA) studies consider multiple object properties, such as size, they typically blend perception and reasoning and lack representativeness with respect to reasoning levels and image categories, making it unclear whether and how vision-language models (VLMs) recognize and reason about depicted objects. To this end, we introduce a systematic evaluation framework comprising images of three representative types, three reasoning levels of increasing complexity, and four object property dimensions, informed by prior work on commonsense knowledge representation and reasoning. We develop a procedure to instantiate this framework in two VQA object-reasoning benchmarks: OPTICS-CNT, comprising 360 images paired with 1,080 multi-level, count-based questions, and OPTICS-CMP, comprising 2.1k comparison questions. Experiments with 12 state-of-the-art VLMs in zero-shot settings reveal significant limitations relative to humans, with the best-performing model achieving below 40% counting and 70% comparison accuracy. While newer reasoning models perform better, a 20% gap to human performance remains. VLMs struggle particularly with photographic images, counterfactual reasoning, physical and functional properties, and higher counts. We make the OPTICS benchmark data and code available to support future scalable benchmarking methods, generalized annotation guidelines, and advanced reasoning VLMs.

Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their real-world applicability. Although previous mitigation methods effectively reduce hallucinations in photographic images, they largely overlook the potential risks posed by stylized images, which play crucial roles in critical scenarios such as game scene understanding, art education, and medical analysis. In this work, we first construct a dataset comprising photographic images and their corresponding stylized versions with carefully annotated caption labels. We then conduct head-to-head comparisons on both discriminative and generative tasks by benchmarking 13 advanced LVLMs on the collected datasets. Our findings reveal that stylized images tend to induce significantly more hallucinations than their photographic counterparts. To address this issue, we propose Style-Aware Visual Early Revision SAVER, a novel mechanism that dynamically adjusts LVLMs' final outputs based on the token-level visual attention patterns, leveraging early-layer feedback to mitigate hallucinations caused by stylized images. Extensive experiments demonstrate that SAVER achieves state-of-the-art performance in hallucination mitigation across various models, datasets, and tasks.

Vision-Language Models (VLMs) are increasingly used in industry VLM applications such as retrieval systems, content generation platforms, and decision-support workflows, where model selection is commonly guided by benchmark rankings. These rankings are largely determined by retrieval, captioning, and reasoning downstream tasks; however, models with similar task performance often show substantially different behavior across datasets. This creates a Capability-Reliability Gap between benchmark performance and observed model stability. We present ARGUS-EVAL, a capability-reliability-oriented evaluation framework for VLMs that characterizes model behavior through Benchmark Capability P(M), Cross-Dataset Consistency CDC(M), Robustness Retention RR(M), and Efficiency E(M). We evaluate CLIP, BLIP, LXMERT, Gemma-3-4B, and Qwen-2.5VL-3B-Instruct across retrieval, captioning, and reasoning downstream tasks. The results reveal notable differences between capability-oriented and reliability-oriented rankings. Qwen-2.5VL-3BInstruct achieves the strongest overall capability (R@1 = 82.7%, BLEU-4 = 47.2%, CIDEr = 141.6, CDC = 0.91), whereas CLIP records the lowest latency (31 ms) and memory footprint (0.9 GB).

Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risks in everyday social media posts. Yet, a systematic evaluation of such risks is still lacking: existing benchmarks show coarse granularity, linguistic bias, and a neglect of multimodal privacy risks. To address these gaps, we introduce KoreaGEO, the first fine-grained, multimodal, and privacy-aware benchmark for geolocation, built on Korean street views. The benchmark covers four socio-spatial clusters and nine place types with rich contextual annotations and two captioning styles that simulate real-world privacy exposure. To evaluate mainstream VLMs, we design a three-path protocol spanning image-only, functional-caption, and high-risk-caption inputs, enabling systematic analysis of localization accuracy, spatial bias, and reasoning behavior. Results show that input modality exerts a stronger influence on localization precision and privacy exposure than model scale or architecture, with high-risk captions substantially boosting accuracy. Moreover, they highlight structural prediction biases toward core cities.

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving complex high-level reasoning tasks, yet existing benchmarks often include a mixture of reasoning questions, and VLMs can frequently exploit object recognition and activity identification as shortcuts to arrive at the correct answers, making it challenging to truly assess their causal reasoning abilities. To bridge this gap, we introduce VQA-Causal and VCR-Causal, two new benchmarks specifically designed to isolate and rigorously evaluate VLMs' causal reasoning abilities. Our findings reveal that while VLMs excel in object and activity recognition, they perform poorly on causal reasoning tasks, often only marginally surpassing random guessing. Further analysis suggests that this limitation stems from a severe lack of causal expressions in widely used training datasets, where causal relationships are rarely explicitly conveyed. We additionally explore fine-tuning strategies with hard negative cases, showing that targeted fine-tuning can improve model's causal reasoning while maintaining generalization and downstream performance. Our study highlights a key gap in current VLMs and lays the groundwork for future work on causal understanding.

Humans develop object orientation understanding progressively, from recognizing which way an object faces to reasoning about orientations across multiple objects. Yet existing vision-language benchmarks largely conflate orientation with broader spatial reasoning. We introduce Discriminative Orientation Reasoning Intelligence (DORI), a cognition-informed hierarchical benchmark that establishes object orientation as the primary evaluation target. DORI decomposes orientation into four dimensions, each evaluated at coarse (categorical) and granular (metric) levels, yielding 33,656 multiple-choice questions over 13,652 real-world and synthetic images from 14 sources. Its design isolates orientation from confounding factors through object isolation, standardized reference frames, and structured prompts. Evaluating 26 state-of-the-art vision-language models reveals a consistent limitation: models strong on general spatial benchmarks remain near-random on object-centric orientation reasoning. The best model achieves only 64.2% on coarse and 42.9% on granular judgments, with the largest drops on compound rotations and inter-object reference frame shifts. Large coarse-to-granular performance gaps further indicate reliance on categorical heuristics rather than geometric reasoning. These results establish object orientation understanding as a fundamental open challenge for multimodal systems. Dataset: https://huggingface.co/datasets/appledora/DORI-Benchmark

Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage or researchers screening conference videos can benefit from concise summaries that reduce cognitive load and save time. Yet current vision-language models (VLMs) often produce verbose, redundant outputs that hinder task performance. Existing video caption evaluation depends on costly human annotations and overlooks the summaries' utility in downstream tasks. We address these gaps with Video-to-text Information Bottleneck Evaluation (VIBE), an annotation-free method that scores VLM outputs using two metrics: grounding (how well the summary aligns with visual content) and utility (how informative it is for the task). VIBE selects from randomly sampled VLM outputs by ranking them according to the two scores to support effective human decision-making. Human studies on LearningPaper24, SUTD-TrafficQA, and LongVideoBench show that summaries selected by VIBE consistently improve performance-boosting task accuracy by up to 61.23% and reducing response time by 75.77% compared to naive VLM summaries or raw video.

Data visualization understanding, which requires integrating visual, numerical, and linguistic inputs, poses fundamental challenges to multimodal reasoning. Recently developed vision-language models (VLMs) are promising candidates for modeling the computations that underlie human data visualization understanding. However, whether they are useful as scientific models depends not only on whether they produce correct answers, but also whether they approximate the patterns of responses that people produce on the same tasks. This distinction has been ignored in recent evaluations of VLMs, which typically only report overall model performance (accuracy) without direct comparison to human behavioral patterns. Here we introduce a human-centered evaluation protocol that compares VLM and human responses on the same set of visualization understanding items. We apply this protocol to eight VLMs across six assessments: five established tests of human visualization literacy, plus one designed specifically for evaluating VLMs. Models performed worse than humans on average, and this gap persisted even under lenient criteria. Moreover, while relative performance across items was somewhat correlated between models and humans, all models produced error patterns that were reliably distinct from those of humans. We envision our evaluation protocol helping to identify artificial systems that might serve as promising scientific cognitive models of how humans reason about data visualizations.

Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential for such systems. Yet, despite decades of research, most machine learning models for this task are trained on small datasets and still struggle to generalize. Recently, vision-Language Models (VLMs) have brought transformative advances in reasoning across visual and textual modalities. Their unprecedented generalization capabilities suggest great potential for advancing intelligent robotic surgery. However, surgical VLMs remain under-explored, and existing models show limited performance, highlighting the need for benchmark studies to assess their capabilities and limitations and to inform future development. To this end, we benchmark the zero-shot performance of several advanced VLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification. Beyond standard evaluation, we integrate explainable AI to visualize VLM attention and uncover causal explanations behind their predictions. This provides a previously underexplored perspective in this field for evaluating the reliability of model predictions. We also propose several explainability analysis-based metrics to complement standard evaluations. Our analysis reveals that surgical VLMs, despite domain-specific training, often rely on weak contextual cues rather than clinically relevant visual evidence, highlighting the need for stronger visual and reasoning supervision in surgical applications.