EventFlash: Towards Efficient MLLMs for Event-Based Vision
Xidian University（西安电子科技大学）；Tsinghua University（清华大学）；Beijing Institute of Technology（北京理工大学）；Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)（广东人工智能与数字经济实验室（深圳））
Shaoyu Liu, Jianing Li, Guanghui Zhao, Yunjian Zhang, Wen Jiang, Ming Li, Xiangyang Ji
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like processing paradigms, overlooking the spatiotemporal sparsity of event streams and resulting in high computational cost. In this paper, we propose EventFlash, a novel and efficient MLLM to explore spatiotemporal token sparsification for reducing data redundancy and accelerating inference. Technically, we build EventMind, a large-scale and scene-diverse dataset with over 500k instruction sets, providing both short and long event stream sequences to support our curriculum training strategy. We then present an adaptive temporal window aggregation module for efficient temporal sampling, which adaptively compresses temporal tokens while retaining key temporal cues. Finally, a sparse density-guided attention module is designed to improve spatial token efficiency by selecting informative regions and suppressing empty or sparse areas. Experimental results show that EventFlash achieves a $12.4\times$ throughput improvement over the baseline (EventFlash-Zero) while maintaining comparable performance. It supports long-range event stream processing with up to 1,000 bins, significantly outperforming the 5-bin limit of EventGPT. We believe EventFlash serves as an efficient foundation model for event-based vision.
Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning
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）
LM4LV: A Frozen Large Language Model for Low-level Vision Tasks
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Nanjing University（南京大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Vision-Centric Activation and Coordination for Multimodal Large Language Models
MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University（人工智能MoE实验室，上海交通大学）；Ant Group（蚂蚁集团）；Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo（宁波数字孪生研究所，东部技术研究所，宁波）
Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Zhongguancun Academy（中关村学院）；Southeast Academy of Information Technology, Beijing Institute of Technology（北京理工大学信息科技东南学院）；Zhongguancun Laboratory（中关村实验室）
One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
National Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学新型软件技术国家重点实验室）；School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
OpenGVLab（开放通用视觉实验室）；Shanghai AI Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；Nanjing University（南京大学）；The University of Hong Kong（香港大学）；Beijing Institute of Technology（北京理工大学）；The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）
VisionLLM v2 提出端到端通用多模态大模型，通过 super link 机制连接 MLLM 与任务专用解码器，并在数百个视觉语言任务上联合训练，以共享参数实现目标定位、姿态估计、图像生成编辑等多样化任务，性能可比肩专用模型。
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
Sydney AI Centre, The University of Sydney（悉尼大学悉尼人工智能中心）；Institute of Image Communication and Network Engineering, Shanghai JiaoTong University（上海交通大学图像通信与网络工程研究所）
Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion
ZIP Lab, Zhejiang University（浙江大学 ZIP 实验室）；South China University of Technology（华南理工大学）；Pazhou Lab（琶洲实验室）；Key Laboratory of Big Data and Intelligent Robot, Ministry of Education（大数据与智能机器人教育部重点实验室）
EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model
University of Science and Technology of China（中国科学技术大学）；WeChat, Tencent Inc.（腾讯微信）；Fudan University（复旦大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence（计算机学院、多媒体软件国家工程研究中心、人工智能研究院）；Hubei Key Laboratory of Multimedia（湖北多媒体重点实验室）；Network Communication Engineering, Wuhan University, China（网络通信工程、武汉大学，中国）；The University of Sydney, Australia（悉尼大学，澳大利亚）；Nanyang Technological University, Singapore（南洋理工大学，新加坡）
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
South China University of Technology（华南理工大学）；Institute for Infocomm Research (I 2 R), A*STAR（信息通信研究所（I 2 R），A*STAR）；WeChat Vision, Tencent Inc.（微信视觉，腾讯公司）；Foshan University（佛山大学）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）
Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（上海交通大学图像通信与网络工程研究所）；Nanyang Technological University（南洋理工大学）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
School of Software, Tsinghua University（清华大学软件学院）；BNRist, Tsinghua University（清华大学BNRist）；Department of Automation, Tsinghua University（清华大学自动化系）
Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision-language tasks, garnering significant attention in the computer vision. However, their efficient deployment remains a substantial challenge due to high computational costs and memory requirements. Recognizing the redundancy of information within the vision modality, recent studies have explored methods for compressing visual tokens in MLLMs to enhance efficiency in a training-free manner. Despite their effectiveness, existing methods like Fast rely on the attention between visua…
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
OpenGVLab（开放视觉实验室）；Shanghai AI Laboratory（上海人工智能实验室）；MMLab（多媒体实验室）；The Chinese University of Hong Kong（香港中文大学）；Nanjing University（南京大学）；Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）
HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs
Netaji Subhash Engineering College (NSEC)（奈尔贾伊·萨布哈工程学院）；TCG Crest；Electronics and Communication Sciences Unit (ECSU)（电子与通信科学单位）；Indian Statistical Institute（印度统计研究所）
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models
University of Chinese Academy of Sciences（中国科学院大学）；Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室）
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
Shanghai AI Laboratory（上海人工智能实验室）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai Jiao Tong University（上海交通大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；Nanjing University（南京大学）；Shanghai Innovation Institute（上海创新研究院）
HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
Institute of Digital Twin, Eastern Institute of Technology（数字孪生研究所，东部技术研究所）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative（宁波空间智能与数字衍生关键实验室）；University of Science and Technology of China（中国科学技术大学）；Shanghai Jiao Tong University（上海交通大学）；Munich Center for Machine Learning, LMU Munich（慕尼黑大学机器学习中心，慕尼黑大学）
MVTamperBench: Evaluating Robustness of Vision-Language Models
Liverpool John Moores University（利物浦约翰·穆里斯大学）；Birla Institute of Technology（比拉理工学院）；Christ University（基督大学）；Columbia University（哥伦比亚大学）；New York University（纽约大学）；University of Washington（华盛顿大学）；Hanyang University（翰阳大学）
