Showing 2026 · cs.LGShow all
3 papers · 2 filters
cs.LG2026
Provable Zeroth-Order Safe Exploration for Reinforcement Learning from Human Feedback
Weiqin Chen, Xinmeng Huang, Dongsheng Ding +1
Safe reinforcement learning from human feedback (Safe-RLHF) seeks to improve helpfulness while satisfying harmlessness constraints. Existing primal-dual approaches can converge to…
cs.LG2026
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
Shervin Khalafi, Alejandro Ribeiro, Dongsheng Ding
Unlearning in diffusion models aims to remove undesirable data or concepts while preserving the utility of pretrained models -- two fundamentally conflicting objectives. We propose…
cs.LG2026
Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
Tao Wang, Shuo Li, Yan Sun +2
Reinforcement learning with verifiable rewards (RLVR) has emerged as a central paradigm for improving the reasoning capabilities of large language models. Group-based policy optimi…