h zhao's picture

5

h zhao

n1cck

huaiyizhao

AI & ML interests

None yet

Recent Activity

new activity 7 days ago

HuggingFaceM4/FineVision:Which training framework can directly load this data without preprocessing?

new activity 2 months ago

WeiboAI/VibeThinker-1.5B:hello? 虽然是一个推理模型，但有的方面也太离谱了吧

commented on a paper 5 months ago

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

View all activity

Organizations

None yet

New activity in HuggingFaceM4/FineVision 7 days ago

Which training framework can directly load this data without preprocessing?

#32 opened 7 days ago by

New activity in WeiboAI/VibeThinker-1.5B 2 months ago

hello? 虽然是一个推理模型，但有的方面也太离谱了吧

#8 opened 2 months ago by

commented 3 papers 5 months ago

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Paper • 2509.08721 • Published Sep 10, 2025 • 662 •

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 118 •

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 118 •

New activity in Time-MQA/TSQA 7 months ago

Open sourcing evaluation scripts?

#1 opened 7 months ago by