Ryuki Ri's picture

5 1

Ryuki Ri

RyukiRi

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 20 hours ago

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

upvoted a paper about 20 hours ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

upvoted a paper 9 days ago

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

View all activity

Organizations

None yet

upvoted 2 papers about 20 hours ago

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

Paper • 2603.25562 • Published 20 days ago • 13

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 2 days ago • 60

upvoted a paper 9 days ago

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

Paper • 2604.02288 • Published 14 days ago • 30

upvoted an article 9 months ago

Article

Seeing Isn’t Understanding: The Spatial Reasoning Gap in Vision-Language Models

Jul 13, 2025

•

11

upvoted a paper about 2 years ago

Neural Network Diffusion

Paper • 2402.13144 • Published Feb 20, 2024 • 100