Author

Ju-Ho Lee

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows

This work forms a KL-regularized objective whose optimum induces a Gibbs policy over final actions under a Gaussian-smoothed behavior prior, and introduces Proposal-Conditioned Refinement Flows (PReFlow), a policy extraction method combining critic-based proposal selection with a conditional refinement flow.

Junhyun Ha, Ju-Ho Lee, Byoungwoo Park · 0 citations