Penghui Qi's picture

Penghui Qi

QPHutu

·

QPHutu

AI & ML interests

None yet

Recent Activity

authored a paper 16 days ago

Rethinking the Divergence Regularization in LLM RL

upvoted a paper 17 days ago

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

upvoted a paper 17 days ago

Rethinking the Divergence Regularization in LLM RL

View all activity

Organizations

liked 3 datasets 7 months ago

LLM360/guru-RL-92k

Viewer • Updated Aug 20, 2025 • 91.9k • 1.15k • 47

zwhe99/DeepMath-103K

Viewer • Updated May 29, 2025 • 103k • 6.97k • 367

sail/Sanity-Test-R1D-1.5B

Viewer • Updated Nov 15, 2025 • 1.52k • 109 • 7

liked a model 8 months ago

zz1358m/SofT-GRPO-master

Updated Nov 13, 2025 • 8

liked a dataset 9 months ago

SynthLabsAI/Big-Math-RL-Verified

Viewer • Updated Mar 25, 2025 • 251k • 5.21k • 235

liked a Space almost 2 years ago

Pipeline Parallellism with Controllable Memory

Calculate and visualize pipeline schedules

liked 2 Spaces over 2 years ago

EditAnything

Zero Bubble Pipeline Parallellism

Calculate and visualize pipeline schedules