Yuxuan YAO
yyuxuan
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
11 days ago
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with
Adaptive Exploration
upvoted
a
paper
22 days ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
Organizations
None yet