一个模型搞定多人交互动作生成，支持任意人数和场景
Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
- 用扩散模型实现自回归多智能体动作生成，统一处理多种交互任务
- 可生成超长序列（数百步），保持多人间协调一致的动作节奏
- 适合机器人协作、虚拟角色生成等需要灵活互动的场景
理解与生成多人交互是机器人和社交计算中的基础挑战。尽管人类在群体中自然协作，但建模此类交互仍因长时序、强智能体依赖及可变群体规模而困难。现有运动生成方法多为特定任务设计，难以泛化至灵活的多智能体生成。本文提出MAGNet（多智能体生成网络），一种统一的自回归扩散框架，通过灵活条件输入与采样，支持多种交互任务。MAGNet可进行二元与多元预测、伙伴补全、伙伴预测及自主生成，在单一模型中实现。其在自回归去噪过程中显式建模智能体间耦合，实现跨智能体的连贯协调。结果表明，MAGNet在二元基准上性能媲美专用方法，并自然扩展至三人及以上交互场景。可生成紧密同步（如舞蹈、拳击）与松散结构（如社交互动）的动作序列。项目页面：https://von31.github.io/MAGNet/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。