While attention has been an increasingly popular component in deep neural networks to both interpret and boost performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes. We first define an evaluation metric based on a sequence of atomic reasoning operations, enabling quantitative measurement of attention that considers the reasoning process. We then collect human eye-tracking and answer correctness data, and analyze various machine and human attentions on their reasoning capability and how they impact task performance. Furthermore, we propose a supervision method to jointly and progressively optimize attention, reasoning, and task performance so that models learn to look at regions of interests by following a reasoning process. We demonstrate the effectiveness of the proposed framework in analyzing and modeling attention with better reasoning capability and task performance. The code and data are available at https://github.com/szzexpoi/AiR
Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration
Sun Yat-sen University（中山大学）；Shanghai Jiao Tong University（上海交通大学）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Peking University（北京大学）；The Hong Kong University of Science and Technology（香港科技大学）；University of Chinese Academy of Sciences（中国科学院大学）
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；The University of Hong Kong（香港大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳分校）；Huawei Technologies Co., Ltd（华为技术有限公司）
Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；NLPR&MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所NLPR&MAIS）；School of Advanced Interdisciplinary Science, University of Chinese Academy of Sciences（中国科学院大学交叉学科学院）；Zhongguancun Academy（中关村学院）
MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
Technical University of Munich (TUM)（慕尼黑工业大学（TUM））；TUM University Hospital（慕尼黑工业大学医院）；University of Oxford（牛津大学）；Imperial College London（伦敦帝国学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Sheffield（谢菲尔德大学）
R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO
Nanyang Technological University（南洋理工大学）；ByteDance（字节跳动）；Tsinghua University（清华大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；The University of Sydney（悉尼大学）
NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
AIML, University of Adelaide（阿德莱德大学AIML）；Adobe Research（奥多比研究院）；University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）
