Wenxuan Luo
MateoAdams2
AI & ML interests
Research on LLM agents and evaluation. Mostly focused on experiments.
Recent Activity
upvoted a paper about 2 hours ago
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning liked a dataset 1 day ago
qingwuuu/ngld-grape-leaf-vlm-w-img-without-diff-ref-v4 upvoted a paper 1 day ago
UniMixer: A Unified Architecture for Scaling Laws in Recommendation SystemsOrganizations
None yet