EgoPro-Bench：基于眼动视频流的个性化主动交互基准测试
EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams
AI总结：
本文提出EgoPro-Bench，通过模拟用户画像生成多样化意图，构建高保真人机交互数据，评估主动交互能力，提升多模态大语言模型的意图理解与交互时机识别能力。
摘要：
现有多模态大语言模型（MLLMs）主要反应式，无法持续感知环境或主动协助用户。尽管新兴基准测试解决主动性问题，但大多局限于警报场景，忽视个性化上下文，无法评估人机交互（HMI）的精确时间。本文引入EgoPro-Bench，一个基于流式眼动视频的新型基准测试，包含2400个评估视频和超过12000个训练视频。不同于以往工作，EgoPro-Bench利用模拟用户画像生成多样化用户意图，构建12个不同领域内的高保真HMI数据。随后，我们提出专门的评估协议和指标，训练适用于流式视频数据的高效推理和低延迟交互模型，并进行全面评估。此外，我们引入交互原则“短思考，更好交互”，在意图识别前分配有限的token预算，从而提升交互性能。实验表明，EgoPro-Bench显著增强了MLLMs的意图理解能力，并能够准确识别HMI的合适时机，从而为下一代以用户为中心的主动交互代理奠定了坚实基础。
英文摘要：
Existing Multimodal Large Language Models (MLLMs) remain primarily reactive, failing to continuously perceive environments or proactively assist users. While emerging benchmarks address proactivity, they are largely confined to alert scenarios, neglect personalized context, and fail to evaluate the precise timing of human-machine interactions (HMI).In this paper, we introduce EgoPro-Bench, a novel benchmark for training and evaluating proactive interaction capabilities based on streaming egocentric videos; it comprises 2,400 videos in the evaluation set and over 12,000 videos in the training set.Unlike previous works, EgoPro-Bench leverages simulated user profiles to generate diverse user intentions and to construct high-fidelity HMI data across 12 distinct domains.Subsequently, we propose a specialized evaluation protocol and metrics, train proactive interaction models designed for efficient reasoning and low-latency interaction on streaming video data, and conduct comprehensive evaluations.Furthermore, we introduce an interaction principle termed "short thinking, better interaction", which allocates a limited token budget prior to intent recognition, thereby enhancing interaction performance.The experiments demonstrate that EgoPro-Bench substantially enhances the intention understanding capabilities of MLLMs and enables accurate identification of appropriate timings for HMI, thereby laying a solid foundation for next-generation user-centric proactive interactive agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
