The authors propose Coordinated Multi-Agent Diffusion Steering (CMDS), a modular post-training framework.
Learned control coordinates frozen diffusion models into multi-agent generators
CMDS casts coordination as stochastic optimal control, balancing assembly-level rewards against pretrained dynamics without retraining component generators.
Top University
Riccardo Barbano · Vincent Pauline · Runchang Li · George Webber · Alexander Denker · Željko Kereta · +3 more
UCL · TUM · MCML · CUHK · KCL
Research Digest··3 min read
The authors propose Coordinated Multi-Agent Diffusion Steering (CMDS), which treats independently trained diffusion models as fixed generative primitives and learns a control that steers their joint reverse processes toward high-reward assembled outputs.
Why this paper
From UCL and 8 others
In one line
Coordinated multi-agent diffusion steering (CMDS) learns an amortised control to coordinate frozen pretrained diffusion models using an assembly-level reward.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§