扩散力场用于多智能体交互序列建模
Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
AI总结：
本文提出MAGNet框架，通过灵活的条件和采样生成多智能体运动序列，支持多种交互任务，实现长序列生成和智能体间协调。
摘要：
理解并生成多人互动是机器人和社交计算中的基本挑战。现有运动生成方法多为任务特定，难以灵活生成多智能体序列。本文提出MAGNet，一种统一的自回归扩散框架，支持多种交互任务，通过灵活的条件和采样进行二元和多元预测、伙伴补全、伙伴预测和代理生成。MAGNet在自回归去噪过程中显式建模智能体间耦合，从而实现跨智能体的连贯协调。MAGNet能够捕捉紧密同步活动（如跳舞、拳击）和松散结构的社会互动。在二元基准上与专用方法表现相当，自然扩展到三人或更多人交互的多元场景。请观看补充视频，以最佳欣赏生成互动的时间动态和空间协调。项目页面：https://von31.github.io/MAGNet/
英文摘要：
Understanding and generating multi-person interactions is a fundamental challenge with broad implications for robotics and social computing. While humans naturally coordinate in groups, modeling such interactions remains difficult due to long temporal horizons, strong inter-agent dependencies, and variable group sizes. Existing motion generation methods are largely task-specific and do not generalize to flexible multi-agent generation. We introduce MAGNet (Multi-Agent Generative Network), a unified autoregressive diffusion framework for multi-agent motion generation that supports a wide range of interaction tasks through flexible conditioning and sampling. MAGNet performs dyadic and polyadic prediction, partner inpainting, partner prediction, and agentic generation all within a single model, and can autoregressively generate ultra-long sequences spanning hundreds of motion steps. We explicitly model inter-agent coupling during autoregressive denoising, enabling coherent coordination across agents. As a result, MAGNet captures both tightly synchronized activities (e.g., dancing, boxing) and loosely structured social interactions. Our approach performs on par with specialized methods on dyadic benchmarks while naturally extending to polyadic scenarios involving three or more interacting people. Please watch the supplemental video, where the temporal dynamics and spatial coordination of generated interactions are best appreciated. Project page: https://von31.github.io/MAGNet/
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。
