arxiv:2609.14708
Yecheng Wu
gbcfchc
AI & ML interests
None yet
Recent Activity
published a model 3 days ago
gbcfchc/Ouro-1.4B-Thinking-DOPD updated a model 3 days ago
gbcfchc/Ouro-1.4B-Thinking-DOPD submitted a paper 9 days ago
Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models