logo
today local_bar
overfitting

2 papers across 2 sessions

Poster Session 3

1 paper
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
#903 · Marlon Becker, Frederick Altrock, Benjamin Risse

Poster Session 6

1 paper
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 Raventós, Nan Cheng, Surya Ganguli, Shaul Druckmann

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