today local_bar

Nan Cheng

PhD student, University of Michigan - Ann Arbor

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning

#3719 · Feng Chen, Allan Raventos, Nan Cheng, Surya Ganguli, Shaul Druckmann

We show that limiting a model's confidence during training can improve test-time scaling in mathematical reasoning.