Shijie Geng

makitanikaze

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation

upvoted a paper 2 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

updated a collection about 2 months ago

View all activity

Organizations

None yet

makitanikaze 's papers 11

arxiv:2605.02178

arxiv:2511.12997

arxiv:2405.05945

arxiv:2404.07940

arxiv:2402.05935

arxiv:2309.15940

arxiv:2304.15010

arxiv:2303.14865

arxiv:2203.13366

arxiv:2110.04544

arxiv:1907.06794