Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective
Paper • 2610.03185 • Published • 32
yilin wang
icarus131480
·
AI & ML interests
nlp
Recent Activity
upvoted a paper 5 days ago
Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective upvoted a paper about 1 month ago
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning liked a model about 1 year ago
meta-llama/Meta-Llama-3-8BOrganizations
None yet