Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models
Paper • 2609.28682 • Published • 1
Zehao Liu
zml5418
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning authored a paper 1 day ago
Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning ModelsOrganizations
None yet
upvoted a paper 1 day ago
authored 3
papers 1 day ago
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
Paper • 2605.27765 • Published
Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models
Paper • 2609.28682 • Published • 1
Skin-R1: Toward Trustworthy Clinical Reasoning for Dermatological Diagnosis
Paper • 2511.14900 • Published
commented a
paper 11 months ago
updated a
model 11 months ago
published a
model 11 months ago