Zhenghao Xu's picture

2 31

Zhenghao Xu

zhenghaoxu

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 13 hours ago

Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training

upvoted a paper 3 days ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

liked a model about 2 months ago

inclusionAI/LLaDA2.0-flash

View all activity

Organizations

models 0

None public yet

datasets 11

zhenghaoxu/think-rm-rmr1-helpsteer3

Viewer • Updated Oct 21, 2025 • 111k • 6 • 1

zhenghaoxu/R2E-Gym-Lite-Truncate-Heuristic

Viewer • Updated Sep 26, 2025 • 7.49k • 128

zhenghaoxu/R2E-Gym-Lite-Truncate-Heuristic-100

Viewer • Updated Sep 26, 2025 • 100 • 4

zhenghaoxu/R2E-Gym-Lite-Truncate-7B

Viewer • Updated Sep 26, 2025 • 6.64k • 17

zhenghaoxu/R2E-Gym-Lite-Truncate-7B-Fixed

Viewer • Updated Sep 25, 2025 • 6.89k • 22

zhenghaoxu/R2E-Gym-Lite-RFT

Viewer • Updated Sep 23, 2025 • 67k • 14

zhenghaoxu/R2E-Gym-Lite-with-Difficulty

Viewer • Updated Sep 19, 2025 • 6.24k • 32 • 4

zhenghaoxu/R2E-Gym-Lite-RFT-no-think

Viewer • Updated Sep 19, 2025 • 135k • 4 • 1

zhenghaoxu/R2E-Gym-Trajs

Viewer • Updated Sep 13, 2025 • 4.04k • 23 • 1

zhenghaoxu/helpsteer2-preference_comparison

Viewer • Updated Mar 10, 2025 • 14.2k • 2

View 11 datasets