Ask to Distill: Learning to Synthesize Data for On-Policy Distillation
Paper • 2610.27450 • Published • 11
Jimeng Shi
jimeng008
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation upvoted a paper 20 days ago
Learning from Teacher Continuations at Student States upvoted a paper 20 days ago
Selecting Diverse SFT Traces Improves Post-RL GeneralizationOrganizations
None yet
upvoted a paper about 20 hours ago
upvoted 2
papers 20 days ago
upvoted 3
papers 5 months ago
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
Paper • 2605.26029 • Published • 14
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Paper • 2606.02373 • Published • 59
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
Paper • 2605.12975 • Published • 9