Qiguang Chen
LightChen2333
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
13 days ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
upvoted
a
paper
17 days ago
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference
Optimization
updated
a dataset
about 2 months ago
LightChen2333/M3CoT
Organizations
Re-purpose dataset card for "Deep Learning for Geometry Problem Solving" survey reading list
#2 opened about 2 months ago
by
nielsr
The result for Llama 2 13B's GSM-8K (8-shot, CoT) is 77.4, which seems incorrect.
🤝
1
2
#19 opened over 1 year ago
by
Hi-archer
Upload 3 files
#1 opened over 2 years ago
by
LightChen2333