garyzhang
xiaoniqiu
ยท
AI & ML interests
LLM, Agents
Recent Activity
upvoted
a
paper
about 2 months ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
liked
a dataset
8 months ago
nebius/SWE-agent-trajectories
Organizations
None yet