Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics

The paper introduces BRAID, a hierarchical latent-variable model that generates multi-person human motion by explicitly modeling both group-level interaction dynamics and individual behavior conditioned on evolving group context. It treats social motion generation as a meta-transfer learning problem, learning shared interaction priors across datasets and adapting them to arbitrary context sets of observed people and joints. BRAID supports coherent generation under full, sparse, or partial observations and produces compact social-state vectors useful for downstream embodied-agent systems, with evaluations on social forecasting, tracking, in-filling, and response generation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• diffusion
• robotics
• fine-tuning
• safety