Ruibin Xiong
chrisxiong
AI & ML interests
LLM
Recent Activity
upvoted a paper 13 days ago
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy upvoted a paper 19 days ago
ClawGym: A Scalable Framework for Building Effective Claw Agents upvoted a paper 8 months ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable RewardOrganizations
None yet