Qihao Zhao

fistyyyy

·

https://scholar.google.com/citations?user=sECb19EAAAAJ&hl=zh-CN&oi=ao

fistyee

AI & ML interests

Research co-author: https://github.com/microsoft/ResearchStudio AI Music: https://dawnote.app/

Recent Activity

commentedon a paper 9 days ago

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

commentedon a paper 9 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

upvoted a collection 9 days ago

View all activity

Organizations

None yet

commented 2 papers 9 days ago

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

Paper • 2607.04439 • Published 13 days ago • 58 •

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published 20 days ago • 166 •

New activity in microsoft/MMLU-CF over 1 year ago

Upload parquet

#22 opened over 1 year ago by

Upload parquet

#23 opened over 1 year ago by

Upload MMLU-CF validation set

#2 opened over 1 year ago by

Create README.md

#1 opened over 1 year ago by