While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and multi-screen collaboration, inherently demand continuous, multi-stream interactions. However, existing benchmarks are confined to single-stream paradigms, leaving a critical gap in evaluating online, cross-stream reasoning. To bridge this, we introduce X-Stream, the first benchmark dedicated to multi-stream streaming understanding. Comprising 4,220 rigorously curated QA pairs across 932 videos, X-Stream evaluates 11 subtasks across multi-window, multi-view, and multi-device scenarios. Crucially, our dataset is constructed using a novel dual-verification pipeline that prevents over-reliance on a single stream. Furthermore, we pioneer the conceptualization of multi-modal large language models (MLLMs) as naive multiplexers, systematically evaluating their performance through the lens of Signal Multiplexing Theory. Our extensive online inference experiments reveal a stark reality: state-of-the-art MLLMs struggle significantly with concurrent streams, achieving only about 50% score and exhibiting poor proactive ability. Ultimately, X-Stream exposes the trade-off of current multiplexing schemes, providing both a practical evaluation protocol and empirical guidance for next-generation multi-stream agents.
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))
A Benchmark Dataset for MLLM-Generated Image Detection: GPT Image2 & Nano Banana2
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(南京航空航天大学人工智能学院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)
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);Baichuan Inc.(百川智能);Renmin University of China(中国人民大学)
Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));University of Freiburg(弗莱堡大学);Hangzhou City University(杭州城市大学);XGRIDS(XGRIDS公司);Fudan University(复旦大学);Hong Kong Baptist University(香港浸会大学)
EventVL: Understand Event Streams via Multimodal Large Language Model
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));KU Leuven(根特大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Carleton University(卡尔顿大学)
Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference
Sun Yat-sen University(中山大学);Peng Cheng Laboratory(鹏城实验室);OPPO AI Center(OPPO人工智能中心);Research Institute(研究 institute);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Harbin Institute of Technology(哈尔滨工业大学);Shenzhen Key Laboratory of Digital Living Network and Content Service(深圳数字生活网络与内容服务重点实验室);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)
Ningbo Institute of Digital Twin, Eastern Institute of Technology(东方理工大学宁波数字孪生研究院);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Anhui University(安徽大学);Tsinghua University(清华大学)
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
Sun Yat-sen University(中山大学);OPPO AI Center(OPPO人工智能中心);Shenzhen Loop Area Institute(深圳河套学院);Guangdong Key Laboratory of Big Data Analysis and Processing(广东大数据分析与处理重点实验室)
StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding
Tsinghua University(清华大学);Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院);Beijing University of Posts and Telecommunications(北京邮电大学)
Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
Australian Artificial Intelligence Institute (AAII)(澳大利亚人工智能研究所);Faulty of Engineering and Information Technology(工程与信息技术学院);University of Technology Sydney(悉尼技术大学);Australia(澳大利亚)
CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院);Shanghai Open University(上海开放大学);ZhuQingTing Data Technology (Zhejiang) Co., Ltd(朱清庭数据科技(浙江)有限公司)
PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation
Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学);University of Adelaide(阿德莱德大学);Wuhan University(武汉大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Beijing Jiaotong University(北京交通大学);AIR Wuxi Innovation Center, Tsinghua University(清华大学无锡创新中心);Lenovo(联想集团)
GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video
City University of Hong Kong(香港城市大学);Huawei Research(华为研究院);University of Science and Technology of China(中国科学技术大学);Chinese University of Hong Kong(香港中文大学);City University of Hong Kong (Dongguan)(香港城市大学(东莞))
Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens
AIML, University of Adelaide(AIML,阿德莱德大学);Monash University(墨尔本大学);Australian National University(澳大利亚国立大学);Tiktok, Australia(Tiktok,澳大利亚);Zhejiang University(浙江大学)
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
Zhejiang University(浙江大学);University of California, San Diego(加州大学圣地亚哥分校);University of California, Irvine(加州大学伊维特分校);The University of Hong Kong(香港大学)