New paper steers frozen pretrained diffusion models to work together via stochastic optimal control
jmhernandez233 · x · 2026-10-09
The paper "One for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal Control" shows how to coordinate multiple frozen pretrained diffusion models without any fine-tuning.
- Method: stochastic optimal control is used to steer several pretrained diffusion models so they act as a coordinated system, with all weights kept frozen
- Demonstrated on coordinating robot arms, human motion, navigation, and image components
- Co-led by @vincentpaulinef and @BarbanoRiccardo; the authors say more work is coming
More from Research
- Test-Time Structure-Space Search lifts antibody design success from 16% to 78% — anshulkundaje · 2026-10-09
- aimotive driving dataset: train labels come from a tracker that sees the future — RexDouglass · 2026-10-09
- Yale-led study finds symbolic structure inside LLM representations — tallinzen · 2026-10-09
- Discrete Diffusion Meetup at COLM: Oct 8, Grand Ballroom — yuntiandeng · 2026-10-09
- Astra 机器人控制实测:Johns Hopkins 深度评测其运动与控制理解 — jmin__cho · 2026-10-09
- Tavily's 93% live-retrieval agent study challenged: prompts were domain-anchored — edwin · 2026-10-09