Keyang Xuan's picture

2

Keyang Xuan PRO

keyangx3

·

keyangds

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

upvoted a paper 6 months ago

Sotopia-RL: Reward Design for Social Intelligence

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published 3 days ago • 31

upvoted a paper 6 months ago

Sotopia-RL: Reward Design for Social Intelligence

Paper • 2508.03905 • Published Aug 5, 2025 • 23