3 papers
cs.LG2025
KL-Regularized Reinforcement Learning is Designed to Mode Collapse
Anthony GX-Chen, Jatin Prakash, Jeff Guo +2
It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred…
cs.LG2025
Three Forms of Stochastic Injection for Improved Distribution-to-Distribution Generative Modeling
Shiye Su, Yuhui Zhang, Linqi Zhou +2
Modeling transformations between arbitrary data distributions is a fundamental scientific challenge, arising in applications like drug discovery and evolutionary simulation. While…
cs.LG2025
A General Framework for Inference-time Scaling and Steering of Diffusion Models
Raghav Singhal, Zachary Horvitz, Ryan Teehan +4
Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remai…