When people share a space, their movements become intertwined. Embodied agents need to understand these social dynamics to interact effectively.

Introducing MAGNet 🧲, a unified autoregressive diffusion forcing model for multi-agent motion generation that captures these… pic.twitter.com/Doc6fDLKJ9

— Vongani Maluleke (@vonekels) 27 mars 2026

When people share a space, their movements become intertwined. Embodied agents need to understand these social dynamics to interact effectively. Introducing MAGNet 🧲, a unified autoregressive diffusion forcing model for multi-agent motion generation that captures these interactions. MAGNet is flexible: predict the future, fill in missing motion, or have people react to each other, all while naturally scaling to N>2 people and generating ultra-long motion sequences.

→ View original post on X — @berkeley_ai, 2026-03-27 02:07 UTC