论文检索

Xinhe Wang, Jin Huang, Xingjian Zhang, Tianhao Wang, Jiaqi W. Ma

Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called “fluid” reasoning abilities. Despite their apparent simplicity for humans, these tasks remain challenging for frontier vision-language models (VLMs), a gap commonly attributed to deficiencies in machine reasoning. We challenge this interpretation and hypothesize that the gap arises primarily from limitations in visual perception rather than from shortcomings in inductive reasoning.To verify this hypothesis, we introduce a two-stage experimental pipeline that explicitly separates perception and reasoning. In the perception stage, each image is independently converted into a natural-language description, while in the reasoning stage a model induces and applies rules using these descriptions. This design prevents leakage of cross-image inductive signals and isolates reasoning from perception bottlenecks. Across three ARC-style datasets, Mini-ARC, ACRE, and Bongard-LOGO, we show that the perception capability is the dominant factor underlying the observed performance gap by comparing the two-stage pipeline with against standard end-to-end one-stage evaluation. Manual inspection of reasoning traces in the VLM outputs further reveals that approximately 80 percent of model failures stem from perception errors. Together, these results demonstrate that ARC-style benchmarks conflate perceptual and reasoning challenges and that observed performance gaps may overstate deficiencies in machine reasoning. Our findings underscore the need for evaluation protocols that disentangle perception from reasoning when assessing progress in machine intelligence.

Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang

Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the “one-to-many” nature of video description, where high-quality captions are often penalized for lexical mismatches or valid shifts in visual focus. Furthermore, such assessments are typically one-dimensional, failing to provide a fine-grained analysis of caption quality. To address this, we redefine caption quality through the lens of information fidelity: A caption must maximize the coverage of salient visual information while ensuring strict factuality. We introduce CapQuiz, a novel reference-free benchmark that assesses captions based on their utility in answering human-verified, fine-grained, multiple-choice questions derived from the video. CapQuiz features a hierarchical taxonomy of 10 question types (spanning Descriptive and Inferential categories) across 24 diverse video domains. Extensive experiments demonstrate that CapQuiz correlates significantly better with human judgments than existing metrics and offers interpretable insights into model performance. We will release the benchmark to facilitate reproducible research.

António Loison, Quentin Macé, Antoine Edy, Victor Xing, Tom Balough, Gabriel de Souza P. Moreira, Bo Liu, Manuel Faysse, Celine Hudelot, Gautier Viaud

Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval, such as interpreting visual elements (tables, charts, images), synthesizing information across documents, and providing accurate source grounding. Existing benchmarks fail to capture this complexity, often focusing on textual data, single-document comprehension, or evaluating retrieval and generation in isolation. We introduce ViDoRe V3, a comprehensive multimodal RAG benchmark featuring multi-type queries over visually rich document corpora. It covers 10 datasets across diverse professional domains, comprising ~26,000 document pages paired with 3,099 human-verified queries, each available in 6 languages. Through 12,000 hours of human annotation effort, we provide high-quality annotations for retrieval relevance, bounding box localization, and verified reference answers. Our evaluation of state-of-the-art RAG pipelines reveals that visual retrievers outperform textual ones, late-interaction models and textual reranking substantially improve performance, and hybrid or purely visual contexts enhance answer generation quality. However, current models still struggle with non-textual elements, open-ended queries, and fine-grained visual grounding. To encourage progress in addressing these challenges, the benchmark is released under a commercially permissive license.

Wei He

Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of noun compounds. To study whether high visual fidelity interferes with idiomatic compositionality under visual abstraction, we introduce DIVA, a controlled benchmark that replaces high-fidelity visual detail with schematic iconicity by generating paired, sense-anchored visualizations for literal and idiomatic readings.We further propose Semantic Alignment Gap (\Delta), an architecture-agnostic metric that quantifies divergence between literal and idiomatic visual grounding.We additionally introduce a directional signed bias b(t) to separately measure the direction and strength of literal preference.Evaluating 8 recent VLMs, we reveal a consistent Literal Superiority Bias: model scale alone does not resolve literal preference, and increased visual fidelity is associated with weaker symbolic alignment, suggesting cognitive interference from hyper-realistic imagery. Our findings suggest that improving compositional understanding requires iconographic abstraction of visual input and anchoring interpretation and generation in intended meaning.

Chahat Raj, Bowen Wei, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu

While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less attention. Existing VLM bias studies often focus on portrait-style images and gender-occupation associations, overlooking broader and more complex social stereotypes and their implied harm. This work introduces Vignette, a large-scale VQA benchmark with 30M+ images for evaluating bias in VLMs through a question-answering framework spanning four directions: factuality, perception, stereotyping, and decision making. Beyond narrowly-centered studies, we assess how VLMs interpret identities in contextualized settings, revealing how models make trait and capability assumptions and exhibit patterns of discrimination. Drawing from social psychology, we examine how VLMs connect visual identity cues to trait and role-based inferences, encoding social hierarchies, through biased selections. Our findings uncover subtle, multifaceted, and surprising stereotypical patterns, offering insights into how VLMs construct social meaning from inputs.

Cheng Qian, Emre Can Acikgoz, Bingxuan Li, Xiusi Chen, Yuji Zhang, Bingxiang He, Qinyu Luo, Gokhan Tur, Dilek Hakkani-Tür, Yunzhu Li 等

Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external simulators to foresee outcomes before acting. This paper empirically examines whether current agents can leverage such world models as tools to enhance their cognition. Across diverse agentic and visual question answering tasks, we observe that some agents rarely invoke simulation (fewer than 1%), frequently misuse predicted rollouts (approximately 15%), and often exhibit inconsistent or even degraded performance (up to 5%) when simulation is available or enforced. Attribution analysis further indicates that the primary bottleneck lies in the agents’ capacity to decide when to simulate, how to interpret predicted outcomes, and how to integrate foresight into downstream reasoning. These findings underscore the need for mechanisms that foster calibrated, strategic interaction with world models, paving the way toward more reliable anticipatory cognition in future agent systems.

Tianyu Yang, Terry Ruas, Yijun Tian, Jan Philip Wahle, Daniel Kurzawe, Bela Gipp

While Vision–language models (VLMs) interpret text-rich images effectively, they struggle with reasoning across long, multi-page documents. We present \textbf{A}ctive \mathbf{L}ong \mathbf{D}ocum\mathbf{E}nt \mathbf{N}avigation (ALDEN), a multi-turn reinforcement learning framework that fine-tunes VLMs as interactive agents capable of actively navigating long, visually rich documents rather than passive readers. ALDEN features a novel fetch action that allows direct page indexing, complementing the classic \textbf{search} action and better exploiting document structure. To ensure training efficiency and stability, we introduce a rule-based cross-level reward for dense supervision and a visual-semantic anchoring mechanism utilizing dual-path KL-divergence constraints. We train ALDEN on a curated corpus built from open-source datasets where trivial samples are filtered, and queries are rewritten to incentivize multi-turn navigation and fetch usage. Empirically, ALDEN achieves state-of-the-art results on five long-document benchmarks, offering a more accurate and efficient path for long-document understanding.

Tianyi Ma, Yue Zhang, Zehao Wang, Parisa Kordjamshidi

Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3D environments. While recent progress has been driven by large-scale pre-training and data augmentation, current methods still struggle to generalize to unseen scenarios, particularly when complex spatial and temporal reasoning is required. In this work, we propose SkillNav, a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents. Our method decomposes navigation into a set of interpretable atomic skills (e.g., Vertical Movement, Area and Region Identification, Stop and Pause), each handled by a specialized agent. To support targeted skill training without manual data annotation, we construct a synthetic dataset pipeline that generates diverse, linguistically natural, skill-specific instruction-trajectory pairs. We then introduce a novel training-free Vision-Language Model (VLM)-based router, which dynamically selects the most suitable agent at each time step by aligning sub-goals with visual observations and previous actions. SkillNav obtains competitive results on commonly used benchmarks and establishes state-of-the-art generalization to the GSA-R2R, a benchmark with novel instruction styles and unseen environments.

Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu 等

We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. SPUR features three key innovations: (1) Panel-Level Fine-Grained Perception: evaluating the visual perception of multimodal large language models (MLLMs) across three dimensions (numerical, morphological, and information localization) on six fine-grained panel types; (2) Cross-Panel Relation Understanding: utilizing complex images with an average of 14.3 panels per sample to evaluate MLLMs’ ability to decipher intricate cross-panel relations; (3) Expert-Level Reasoning: assessment of qualitative and quantitative reasoning across five experimental paradigms to determine if models can infer conclusions from evidence as human experts do. Comprehensive evaluation of 20 MLLMs and four multimodal Chain-of-Thought (MCoT) methods reveals that current models fall significantly short of the expert-level requirements for scientific image interpretation, underscoring a critical bottleneck in AI for Science (AI4S) research.

Haomin Zuo, Yidi Li, Luoxiao Yang, Xiaofeng Zhang

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional autoregressive models that produce sequential activations, diffusion-based architectures generate tokens via parallel denoising, resulting in smooth, distributed activation patterns across the entire sequence. Consequently, existing Class Activation Mapping (CAM) methods, which are tailored for local, sequential dependencies, are ill-suited for interpreting these non-autoregressive behaviors. To bridge this gap, we propose Diffusion-CAM, the first interpretability method specifically tailored for dMLLMs. We derive raw activation maps by differentiably probing intermediate representations in the transformer backbone, accordingly capturing both latent features and their class-specific gradients. To address the inherent stochasticity of these raw signals, we incorporate four key modules to resolve spatial ambiguity and mitigate intra-image confounders and redundant token correlations. Extensive experiments demonstrate that Diffusion-CAM significantly outperforms SoTA methods in both localization accuracy and visual fidelity, establishing a new standard for understanding the parallel generation process of diffusion multimodal systems.

Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu

While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning. Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.

Zhen Yang, Ping Jian, Zhongbin Guo, Zuming Zhang, Chengzhi Li, Yonghong Deng, Xinyue Zhang, Wenpeng Lu

Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual inputs. However, in the absence of visual information, whether linguistic intelligence alone is sufficient to endow models with spatial intelligence, and how models perform relevant tasks with text-only inputs still remain unexplored. Therefore, in this paper, we focus on a fundamental and critical capability in spatial intelligence from a linguistic perspective: viewpoint rotation understanding (VRU). Specifically, LLMs and VLMs are asked to infer their final viewpoint and predict the corresponding observation in an environment given textual description of viewpoint rotation and observation over multiple steps. We find that both LLMs and VLMs perform poorly on our proposed dataset while human can easily achieve 100% accuracy, indicating a substantial gap between current model capabilities and the requirements of spatial intelligence. To uncover the underlying mechanisms, we conduct a layer-wise probing analysis and head-wise causal intervention. Our findings reveal that although models encode viewpoint information in the hidden states, they appear to struggle to bind the viewpoint position with corresponding observation, resulting in a hallucination in final layers. Finally, we selectively fine-tune the key attention heads identified by causal intervention to improve VRU performance. Experimental results demonstrate that such selective fine-tuning achieves improved VRU performance while avoiding catastrophic forgetting of generic abilities.

Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Bo Zhang, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang 等

Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of Large Language Models and Vision–Language Models to interpret full musical notation remains insufficiently examined.We introduce Musical Score Understanding Benchmark (MSU-Bench), a human-curated benchmark for score-level musical understanding across textual (ABC notation) and visual (PDF) modalities. MSU-Bench contains 1,800 generative question–answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others, organised into four levels of increasing difficulty, ranging from onset information to texture and form. Evaluations of more than fifteen state-of-the-art models, in both zero-shot and fine-tuned settings, reveal pronounced modality gaps, unstable level-wise performance, and challenges in maintaining multilevel correctness. Fine-tuning substantially improves results across modalities while preserving general knowledge, positioning MSU-Bench as a robust foundation for future research in multimodal reasoning. The benchmark and code are available at https://github.com/Congren-Dai/MSU-Bench.

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou

The identification of harmful memes extends beyond a mere classification task, encompassing challenges related to multi-perspective semantic comprehension and hierarchical reasoning. Prevailing approaches predominantly depend on modal alignment or black-box classifiers, which fail to capture implicit biases and lack interpretability. In this study, we propose BPDMoE-Hate, a novel framework grounded in dual-space mixture-of-experts, which innovatively conceptualizes harmful meme detection as an integrated process of “viewpoint decoupling and hierarchical fusion”. Our approach generates adversarial binary perspectives via Visual-Language Models (VLMs) and incorporates an adaptive viewpoint gating to facilitate viewpoint selection, thereby enabling the model to autonomously discern implicit semantic inclinations. Moreover, we propose the Hyperbolic-Euclidean space expert to effectively capture the hierarchical structural relationships and semantic correlations between multimodal and viewpoint features, thereby enabling interpretable reasoning at the geometric representation level. Empirical evaluations conducted on three mainstream datasets demonstrate that BPDMoE-Hate not only substantially surpasses existing methodologies in performance but also offers visual explanations for viewpoint selection and hierarchical structuring, thereby advancing the field of interpretable multimodal content analysis.

Wenrui Zhou, Mohamed Hendy, Shu Yang, Qingsong Yang, Zikun Guo, Yuyu Luo, Lijie Hu, Di Wang

As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistency and reliability is of critical importance. However, sycophancy, the tendency of these models to align with user input even when it contradicts the visual evidence, undermines their trustworthiness in such contexts. Current sycophancy research has largely overlooked its specific manifestations in the video-language domain, resulting in a notable absence of systematic benchmarks and targeted evaluations to understand how Video-LLMs respond under misleading user input. To fill this gap, we propose ViSE (Video-LLM Sycophancy Benchmarking and Evaluation), the first benchmark designed to evaluate sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks. Specifically, ViSE pioneeringly brings linguistic perspectives on sycophancy into the video domain, enabling fine-grained analysis across multiple sycophancy types and interaction patterns. Furthermore, we propose two potential training-free mitigation strategies revealing potential paths for reducing sycophantic bias: (i) enhancing visual grounding through interpretable key-frame selection and (ii) steering model behavior away from sycophancy via targeted, inference-time intervention on its internal neural representations. Our code is available at https://github.com/William030422/Video-Sycophancy.

Fanxiao Li, Jiaying Wu, Tingchao Fu, Dayang Li, Herun Wan, Wei Zhou, Min-Yen Kan

Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation, yet remains underexplored. To address this gap, we develop a multi-stage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-Misleading benchmark. Using MM-Misleading, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection. We further propose OMGuard, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions. Experiments show that OMGuard lifts an 8B model’s detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction. Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions.

Minghui Jia, Qichao Zhang, Ali Luo, Linjing Li, Shuo Ye, Hailing Lu, Wen Hou, Dongbin Zhao

Due to the limited generalization and interpretability of deep learning classifiers, the final vetting of rare celestial object candidates still relies on manually intensive expert visual inspection, which has become a primary bottleneck as modern spectroscopic surveys continue to scale.To bridge this gap, we propose Spec-o3, a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection via interleaved multimodal chain-of-thought reasoning.Spec-o3 is trained with a two-stage post-training recipe: cold-start supervised fine-tuning on expert inspection trajectories followed by outcome-based reinforcement learning on rare-type verification tasks.Evaluated on five rare-object identification tasks from LAMOST, Spec-o3 establishes a new State-of-the-Art, boosting the macro-F1 score from 28.3 to 76.5 with a 7B parameter base model and outperforming both proprietary VLMs and specialized deep models. Beyond accuracy, Spec-o3 processes spectra at \sim0.2 s per sample on an 8\timesH100 server, a \sim50\times throughput gain over expert manual inspection. The agent also demonstrates strong generalization to unseen inspection tasks across survey shifts (from LAMOST to SDSS/DESI). Expert evaluations further confirm that its reasoning traces are coherent and physically consistent, supporting transparent and trustworthy decision-making.Code, data, and models are available at Project HomePage.

Ido Andrew Atad, Itamar Zimerman, Shahar Katz, Lior Wolf

Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet, most existing analyses focus on individual attention heads or layers, failing to account for the model’s global behavior. While prior efforts have extended attention formulations across multiple heads via averaging and matrix multiplications or incorporated components such as normalization and FFNs, a unified and complete representation that encapsulates all transformer blocks is still lacking. We address this gap by introducing TensorLens, a novel formulation that captures the entire transformer as a single, input-dependent linear operator expressed through a high-order attention-interaction tensor. This tensor jointly encodes attention, FFNs, activations, normalizations, and residual connections, offering a theoretically coherent and expressive linear representation of the model’s computation. TensorLens is theoretically grounded and our empirical validation shows that it yields richer representations than previous attention-aggregation methods. Our experiments demonstrate that the attention tensor can serve as a powerful foundation for developing tools aimed at interpretability and model understanding.

Houxing Ren, Mingjie Zhan, Zimu Lu, Ke Wang, Yunqiao Yang, Haotian Hou, Hongsheng Li

Spreadsheets are central to real-world applications such as enterprise reporting, auditing, and scientific data management. Despite their ubiquity, existing large language model based approaches typically treat tables as plain text, overlooking critical layout cues and visual semantics. Moreover, real-world spreadsheets are often massive in scale, exceeding the input length that LLMs can efficiently process. To address these challenges, we propose SpreadsheetAgent, a two-stage multi-agent framework for spreadsheet understanding that adopts a step-by-step reading and reasoning paradigm. Instead of loading the entire spreadsheet at once, SpreadsheetAgent incrementally interprets localized regions through multiple modalities, including code execution results, images, and LaTeX tables. The method first constructs a structural sketch and row/column summaries, and then performs task-driven reasoning over this intermediate representation in the Solving Stage. To further enhance reliability, we design a verification module that validates extracted structures via targeted inspections, reducing error propagation and ensuring trustworthy inputs for downstream reasoning. Extensive experiments on two spreadsheet datasets demonstrate the effectiveness of our approach. With GPT-OSS-120B, SpreadsheetAgent achieves 38.16% on Spreadsheet Bench, outperforming the ChatGPT Agent baseline (35.27%) by 2.89 absolute points. These results highlight the potential of SpreadsheetAgent to advance robust and scalable spreadsheet understanding in real-world applications. Code is available at https://github.com/renhouxing/SpreadsheetAgent.

Shuhang Chen, Hangjie Yuan, Yunqiu Xu, Pengwei Liu, Tao Feng, Jun Cen, Zeying Huang, Yi Yang

Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and interpreting diagrams. Inspired by human problem-solving, we hypothesize that the ability to extract meaningful information from diagrams is pivotal, as it directly conditions subsequent inference.Hence, we introduce FlowVerse, a comprehensive benchmark that provides a fine-grained evaluation of MLLMs’ perception and reasoning capabilities. Our preliminary results on FlowVerse reveal that existing MLLMs exhibit substantial limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs. In response, we introduce MathFlow, a modular problem-solving pipeline that decouples perception and inference into distinct stages, thereby optimizing each independently. Given the perceptual limitations observed in current MLLMs, we trained MathFlow-P-7B as a dedicated perception model.Experimental results indicate that MathFlow-P-7B yields substantial performance gains when integrated with various closed-source and open-source inference models. This demonstrates the effectiveness of the MathFlow pipeline and its compatibility with diverse inference frameworks. Project page: https://github.com/MathFlow-zju/MathFlow.