Rufus-Air: An Open LLM Post-Training Recipe
Paper • 2609.29421 • Published • 44
Xiaoliang Shi
xiaoliang-shi
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Rufus-Air: An Open LLM Post-Training Recipe upvoted a paper 10 days ago
Does Learning Protein Folding Generalize to Broader Reasoning? upvoted a paper 29 days ago
Rethinking Critic Learning in PPO: Understanding and Mitigating Value FlatteningOrganizations
