Diffusion Steering via RL
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
This paper introduces Diffusion Steering via Reinforcement Learning (DSRL), a method for adapting pretrained diffusion policies by learning in their latent-noise space instead of finetuning model weights. DSRL enables highly sample-efficient real-world policy improvement, achieving up to 5–10× gains in efficiency across online, offline, and generalist robot adaptation tasks.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack