Zhijiang
Zeee
ยท
AI & ML interests
Natural Language Processing, Machine Learning
Recent Activity
upvoted
a
paper
about 19 hours ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
upvoted
a
paper
5 days ago
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference
Optimization
upvoted
a
paper
3 months ago
Through the Valley: Path to Effective Long CoT Training for Small
Language Models
Organizations
