RewardHacking

AI & ML interests

None defined yet.

Recent Activity

xinpeng  submitted a paper 1 day ago

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation

tongliuphysics  authored a paper 12 months ago

Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?

tongliuphysics  authored a paper 12 months ago

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings

View all activity

Team members 2