2 papers
cs.LG2025
Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization
Kezhao Liu, Jason Klein Liu, Mingtao Chen +1
Reinforcement Learning from Human Feedback (RLHF) leverages a Kullback-Leibler (KL) divergence loss to stabilize training and prevent overfitting. However, in methods such as GRPO,…
cs.CV2025
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Yiming Liu, Kezhao Liu, Yao Xiao +4
Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks. The success of DBP is often attributed to the forward diffusion proces…