zhangzef

Starrrrrry

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

Can Text-to-Image Models Draw from the Right Frame of Reference?

liked a model about 1 month ago

upvoted a paper 2 months ago

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

View all activity

Organizations

None yet

Collections 1

Papers 6

arxiv:2604.04780

arxiv:2512.04563

arxiv:2508.19697

arxiv:2504.10368

models 3

Starrrrrry/COOPER

15B • Updated Dec 7, 2025 • 1

Starrrrrry/COOPER-AMG

Updated Dec 7, 2025 • 1

Starrrrrry/RLAIF-V-Bias-7B

7B • Updated Dec 4, 2025 • 3

datasets 4

Starrrrrry/gyh_arxiv

Updated Dec 10, 2025 • 18

Starrrrrry/COOPER_Train_Set

Updated Dec 7, 2025 • 370 • 1

Starrrrrry/RLAIF-V-Bias-Dataset

Viewer • Updated Mar 28, 2025 • 68.1k • 175 • 2

Starrrrrry/arxiv_insect

Viewer • Updated Feb 4, 2025 • 60k • 13 • 1