Diffusion Forcing for Multi-Agent Interaction Sequence Modeling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Maluleke, Vongani H., Horiuchi, Kie, Wilken, Lea, Ng, Evonne, Malik, Jitendra, Kanazawa, Angjoo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908915355090944
author Maluleke, Vongani H.
Horiuchi, Kie
Wilken, Lea
Ng, Evonne
Malik, Jitendra
Kanazawa, Angjoo
author_facet Maluleke, Vongani H.
Horiuchi, Kie
Wilken, Lea
Ng, Evonne
Malik, Jitendra
Kanazawa, Angjoo
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2512_17900
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
Maluleke, Vongani H.
Horiuchi, Kie
Wilken, Lea
Ng, Evonne
Malik, Jitendra
Kanazawa, Angjoo
Computer Vision and Pattern Recognition
Robotics
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/
title Diffusion Forcing for Multi-Agent Interaction Sequence Modeling
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2512.17900