Qiguang Chen
LightChen2333
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 days ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
upvoted
a
paper
7 days ago
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference
Optimization
updated
a dataset
about 1 month ago
LightChen2333/M3CoT