logo
today local_bar
Direct Alignment Algorithm

1 paper across 1 session

Poster Session 2

1 paper
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
KL Penalty Control via Perturbation for Direct Preference Optimization
#404 · Sangkyu Lee, Janghoon Han, Hosung Song, Stanley Jungkyu Choi, Honglak Lee, Youngjae Yu

Instance-level adaptive KL penalty control method for Direct Preference Optimization