V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators
AI Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)人工智能方向);International Digital Economy Academy(国际数字经济学院);MedVisAI Lab, Lee Kong Chian School of Medicine, Nanyang Technological University, and Centre of AI in Medicine(医学视觉人工智能实验室,南洋理工大学Lee Kong Chian医学院,以及人工智能在医学中的中心);South China University of Technology(华南理工大学);Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电子与电气工程系)
Jiazhou Zhou, Yucheng Chen, Hongyang Li, Qing Jiang, Hu Zhou, Ying-Cong Chen, Lei Zhang
Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely restricted to the language domain, treating visual input as a static, reasoning-agnostic preamble rather than a dynamic participant. Consequently, current models act as passive observers, unable to re-examine visual details to ground their evolving reasoning states. To overcome this, we propose V-Reflection, a framework that transforms the MLLM into an active interrogator through a "think-then-look" visual reflection mechanism. During reasoning, latent states function as dynamic probes that actively interrogate the visual feature space, grounding each reasoning step for task-critical evidence. Our approach employs a two-stage distillation strategy. First, the Box-Guided Compression Module (BCM) establishes stable pixel-to-latent targets through explicit spatial grounding. Next, a Dynamic Autoregressive Compression (DAC) module maps the model's hidden states into dynamic probes that interrogate the global visual feature map. By distilling the spatial expertise of the BCM teacher into the DAC student, V-Reflection internalizes the ability to localize task-critical evidence. During inference, both modules remain entirely inactive, maintaining a purely end-to-end autoregressive decoding in the latent space with optimal efficiency. Extensive experiments demonstrate the effectiveness of our V-Reflection across six perception-intensive benchmarks, significantly narrowing the fine-grained perception gap. Visualizations confirm that latent reasoning autonomously localizes task-critical visual evidence.
Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement
College of Computer Science, Sichuan University(四川大学计算机科学学院);Engineering Research Center of Machine Learning(机器学习工程研究中心);China Telecom Institute of AI(中国电信人工智能研究院)
Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs
Emory University(埃默里大学);University of Electronic Science and Technology of China(电子科技大学);University of Illinois Chicago(伊利诺伊大学香槟分校);The Hong Kong Polytechnic University(香港理工大学)
MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong Polytechnic University(香港理工大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Can a Large Language Model Assess Urban Design Quality? Evaluating Walkability Metrics Across Expertise Levels
Singapore-ETH Centre, Future Cities Lab Global Programme, CREATE campus(新加坡-ETH中心,未来城市实验室全球计划,CREATE校区);National University of Singapore(新加坡国立大学);Takenaka Corporation(Takenaka公司);Department of Architecture, National University of Singapore(新加坡国立大学建筑系)
Unveiling and Bridging the Functional Perception Gap in MLLMs: Atomic Visual Alignment and Hierarchical Evaluation via PET-Bench
School of Biomedical Engineering, Southern Medical University(生物医学工程学院,南方医科大学);School of Biomedical Engineering, Shanghai Jiaotong University(生物医学工程学院,上海交通大学);Department of Electronic Engineering, Chinese University of Hong Kong(电子工程系,中国香港大学);Faculty of Dentistry, The University of Hong Kong(牙科学院,香港大学);Department of Nuclear Medicine, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine(核医学科,广州中医药大学第二附属医院);PET Center, Department of Nuclear Medicine, Guangdong Provincial People’s Hospital, Southern Medical University(PET中心,核医学科,广东省人民医院,南方医科大学);Department of Nuclear Medicine, Nanfang Hospital, Southern Medical University(核医学科,南芳医院,南方医科大学);Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospitals(核医学与分子影像学部,日内瓦大学医院);Departments of Radiology, Physics, and Biomedical Engineering, The University of British Columbia(放射学、物理和生物医学工程系,不列颠哥伦比亚大学);Medical Artificial Intelligence Laboratory, Westlake University(医学人工智能实验室,西湖大学)
Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks
Huazhong University of Science and Technology(华中科技大学);Zhongguancun Academy(中关村学院);East China Normal University(华东师范大学);Zhengzhou University(郑州大学);Zhongguancun Institute of Artificial Intelligence(中关村人工智能研究院)
UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
Center for Data Science, Peking University(北京大学数据科学中心);Alibaba Group(阿里巴巴集团);CASIA;Center for Machine Learning Research, Peking University(北京大学机器学习研究中心);State Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室)