Frank Chen's picture

1 7

Frank Chen

quantumfr

·

AI & ML interests

alignment and Interpretability

Recent Activity

commented on a paper 2 days ago

Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models

upvoted a paper 2 days ago

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

upvoted a paper 3 days ago

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

View all activity

Organizations

None yet

Papers 2

arxiv:2509.23962

arxiv:2502.05242

models 1

quantumfr/Qwen-2.5-7B-Simple-RL

Text Generation • 8B • Updated Mar 19

datasets 0

None public yet