通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2604.26250cs.CV
超越捷径：通过定性推理缓解冻结VLM中的视觉错觉
Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究院，合肥国家科学中心）；Anhui Polytechnic University（安徽理工大学）；Hefei University of Technology（合肥工业大学）；Anhui University（安徽大学）；IGS, Imperial College London（帝国理工学院伦敦分校）
While Vision-Language Models (VLMs) have achieved state-of-the-art performance in general visual tasks, their perceptual robustness remains remarkably brittle when confronted with optical illusions. These failures are often attributed to shortcut heuristics, where models prioritize linguistic priors and memorized prototypes over direct visual evidence. In this work, we propose Structured Qualitative Inference (SQI), a training-free, data-centric framework designed to fortify visual grounding in frozen VLMs. SQI addresses perceptual anomalies through three systematic modules: (1) Axiomatic Constraint Injection, which suppresses erroneous metric estimations and quantitative hallucinations; (2) Hierarchical Scene Decomposition, which decouples target visual manifolds from complex background distractors; and (3) Counterfactual Self-Verification, an adversarial reasoning step that mitigates confirmation bias. By orchestrating these qualitative constraints at inference time, SQI effectively aligns high-level linguistic reasoning with low-level visual perception. Our framework was evaluated on the DataCV 2026 Challenge (Task I: Classic Illusion Understanding), where it ranked 2nd place overall. Experimental results demonstrate that SQI not only significantly enhances accuracy across diverse illusion categories but also provides superior diagnostic interpretability without any model fine-tuning. Our success underscores the potential of structured qualitative grounding as a robust paradigm for developing next-generation, illusion-resistant vision-language systems.
UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs
National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing（国家空间智能信息处理科技重点实验室）；Beijing Institute of Technology（北京理工大学）；School of Computer Science（计算机学院）；Wuhan University（武汉大学）；Zhongguancun Academy（中关村学院）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing（测绘遥感信息工程国家重点实验室）；Hong Kong Polytechnic University（香港理工大学）
Spatial Colour Mixing Illusions as a Perception Stress Test for Vision-Language Models
National University of Science and Technology POLITEHNICA Bucharest（波兰布加勒斯特技术大学）；IDSIA, The Dalle Molle Institute for Artificial Intelligence（达摩信息技术研究所）
Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
University of Southern California（南加州大学）；University of California San Diego（加州大学圣地亚哥分校）；Carnegie Mellon University（卡内基梅隆大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Seeing Time: Benchmarking Chronological Reasoning and Shortcut Biases in Vision-Language Models
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computing Technologies, RMIT University（皇家墨尔本理工学院计算技术学院）
The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
University of Science and Technology of China（中国科学技术大学）；NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs
Shenzhen campus of Sun Yat-sen University（中山大学深圳校区）；Huawei Noah’s Ark Lab（华为诺亚实验室）；MBZUAI；Peng Cheng Laboratory（鹏城实验室）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）
本文分析以 3D 场景为中心的 VLM 性能受限原因，发现其弱用 3D 编码器、依赖语言捷径，并提出 3D Relevance Discrimination QA 数据集以促进真实 3D 理解。
Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs
The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）；Eisai Inc.（卫材株式会社）；IISc, Bangalore（印度科学研究所班加罗尔分校）；Cohere Labs Community（Cohere实验室社区）
SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
Universidade Federal de Mato Grosso (UFMT)（马托格罗索联邦大学）；Universidade Federal de Goiás (UFG)（戈亚斯联邦大学）；Advanced Knowledge Center for Immersive Technologies (AKCIT)（沉浸式技术高级知识中心）
Contextualized Visual Personalization in Vision-Language Models
Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea（电气电子工程系，首尔国立大学，首尔，韩国）；Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Korea（人工智能交叉学科项目，首尔国立大学，首尔，韩国）
