ComPO

AI & ML interests

None defined yet.

Recent Activity

PeterLauLukCh  authored a paper 18 days ago

Reward-free Alignment for Conflicting Objectives

PeterLauLukCh  submitted a paper 20 days ago

Reward-free Alignment for Conflicting Objectives

PeterLauLukCh  authored a paper 2 months ago

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

View all activity

Team members 2