Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
Paper • 2606.10968 • Published • 42
ray lin
linsoft
·
AI & ML interests
RL, NLP, LLM
Recent Activity
upvoted a paper 30 days ago
Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning updated a model over 1 year ago
Tinytron/MLC-Tinytron liked a model almost 2 years ago
facebook/encodec_24khzOrganizations
upvoted a paper 30 days ago