arxiv:2503.18892
WeihaoZeng
AndrewZeng
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
11 days ago
SWE-Perf: Can Language Models Optimize Code Performance on Real-World
Repositories?
upvoted
a
paper
about 2 months ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
upvoted
a
paper
2 months ago
Pitfalls of Rule- and Model-based Verifiers -- A Case Study on
Mathematical Reasoning
Organizations
datasets
63
AndrewZeng/hacking_deepscalaer
Viewer
•
Updated
•
6.12k
•
7
AndrewZeng/SimpleRL-SFT
Viewer
•
Updated
•
7.62k
•
6
AndrewZeng/math_level1to5_qwen_prompt
Viewer
•
Updated
•
12k
•
13
•
1
AndrewZeng/math-bstar-sample
Viewer
•
Updated
•
11.5k
•
6
AndrewZeng/bstar-math-dev
Viewer
•
Updated
•
604
•
9
AndrewZeng/prm-reward-data
Viewer
•
Updated
•
240k
•
9
AndrewZeng/math-trn-format
Viewer
•
Updated
•
11.5k
•
10
AndrewZeng/math_scaling
Viewer
•
Updated
•
100
•
6
AndrewZeng/random_syn
Viewer
•
Updated
•
108k
•
17
AndrewZeng/medium_syn_mistral_20w_mistral_infer_part_4
Viewer
•
Updated
•
38.9k
•
9