siyuanzhu

siyuan-zhu

·

AI & ML interests

reinforcement learning

Recent Activity

liked a dataset 11 days ago

XiaomiMiMo/MiMo-V2.6-RL-oss

liked a model 5 months ago

Musci-research/Musci-ASR-2.4B

upvoted a paper 5 months ago

GAGPO: Generalized Advantage Grouped Policy Optimization

View all activity

Organizations

Papers 2

arxiv:2605.13217

arxiv:2512.14465

models 0

None public yet

datasets 3

siyuan-zhu/gsm8k-python

Viewer • Updated May 28, 2025 • 1.2k • 30 • 1

siyuan-zhu/kk-difficulty

Viewer • Updated Mar 24, 2025 • 6.9k • 25 • 1

siyuan-zhu/gsm8k-doubao-lite-difficulties

Viewer • Updated Mar 24, 2025 • 8.79k • 31 • 1