Gengsheng Li

RyukiRi

·

AI & ML interests

None yet

Recent Activity

authored a paper 3 days ago

Rubric-based On-policy Distillation

authored a paper 3 days ago

Visual-Advantage On-Policy Distillation for Vision-Language Models

authored a paper 3 days ago

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

View all activity

Organizations

None yet

Papers 3

arxiv:2605.21924

arxiv:2605.07396

arxiv:2604.02288

models 2

RyukiRi/R-Diverse

RyukiRi/Classifiers-Enhanced-by-Pre-training

Updated Apr 16, 2024

datasets 0

None public yet