理解长上下文的视觉信息仍然是视觉语言模型面临的根本性挑战，特别是在代理任务如GUI控制和网页导航中。尽管网页和GUI环境本质上是结构化的文档，但当前的VLMs通常在其训练目标中忽视了以决策为导向的文档理解。现有的方法主要扩展视觉嵌入以处理长且高分辨率的输入，但这些方法内存消耗大，不适用于本地部署的解决方案。为了解决这些问题，我们提出了SCoPE VLM，一种文档导航专家，利用新颖的滚动链机制来选择性地和递归地导航文档，仅专注于相关部分。我们引入了专门的数据生成管道来构建信息丰富的滚动链轨迹和Episodic Group Relative Policy Optimization，一种定制的强化学习方法，以弥合训练和推理之间的差距。我们的方法显著减少了内存使用，并有效建模了人类般的阅读行为。据我们所知，SCoPE VLM是第一个明确建模多页文档问答中代理阅读模式的框架，推动了多模态代理的能力。
英文摘要：
Understanding long-context visual information remains a fundamental challenge for vision-language models, particularly in agentic tasks such as GUI control and web navigation. While web pages and GUI environments are inherently structured documents, current VLMs typically neglect decision-oriented document understanding in their training objectives. Existing approaches primarily extend visual embeddings to process long, high-resolution inputs, but these methods are memory-intensive and impractical for locally deployable solutions. To address these issues, we propose SCoPE VLM, a document navigation expert that leverages a novel Chain of Scroll mechanism to selectively and recursively navigate documents, focusing exclusively on relevant segments. We introduce a dedicated data generation pipeline to construct informative Chain of Scroll trajectories and Episodic Group Relative Policy Optimization, a tailored reinforcement learning method to bridge the gap between training and inference. Our method substantially reduces memory usage and effectively models human-like reading behaviors. To the best of our knowledge, SCoPE VLM is the first framework to explicitly model agentic reading patterns in multi-page document question answering, advancing the capabilities of multimodal agents.
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
Department of Electrical and Computer Engineering, Seoul National University（首尔大学电气与计算机工程系）；Interdisciplinary Program in Artificial Intelligence, Seoul National University（首尔大学人工智能跨学科项目）
Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning
University of Southern California（南加州大学）；AI2（艾伦人工智能研究所）；Samaya AI（萨马亚人工智能公司）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
Scope: Selective Cross-modal Orchestration of Visual Perception Experts
ServiceNow；Université de Montréal（蒙特利尔大学）；École de Technologie Supérieure（高级技术学院）；University of Waterloo（滑铁卢大学）；McGill University（麦吉尔大学）；York University（约克大学）；CIFAR AI Chair（CIFAR人工智能主席）；Mila；Law Zero
StreamSense: Streaming Social Task Detection with Selective Vision-Language Model Routing
Singapore University of Technology and Design（新加坡科技设计大学）；University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）；University of Rochester（罗切斯特大学）
Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models
POSTECH（浦项科技大学）；Graduate School of Artificial Intelligence, POSTECH（浦项科技大学人工智能研究生院）；Department of Computer Science and Engineering, POSTECH（浦项科技大学计算机科学与工程系）
Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding
Beijing National Research Center for Information Science and Technology (BNRist), Department of Automation, Tsinghua University（清华大学自动化系北京信息科学与技术国家研究中心）；State Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院通用人工智能国家重点实验室）
Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
School of Software, Beihang University（北京航空航天大学软件学院）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）
How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
University of Aberdeen（阿伯丁大学）；International Institute of Information Technology Hyderabad（海德拉巴国际信息技术学院）；University of Technology Nuremberg（纽伦堡工业大学）；University of Southern California（南加利福尼亚大学）
GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；Juhaokan Technology Co.,Ltd（极皓科技有限公司）；Nanjing University（南京大学）；University of Science and Technology of China（中国科学技术大学）
Caption This, Reason That: VLMs Caught in the Middle
Integrated Program in Neuroscience (IPN) McGill University（神经科学联合计划 麦吉尔大学）；Mila, University of Montreal（蒙特利尔大学Mila）；Microsoft Research USA（微软研究院美国总部）；Department of Physiology McGill University（生理学系 麦吉尔大学）
WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室 (MAIS)）
