arxiv:2609.35954
zhangzhiwei
zhangzhiwei666
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision authored a paper 3 days ago
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision authored a paper 3 days ago
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy DistillationOrganizations
models 0
None public yet
datasets 0
None public yet