Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
pb09204048  authored a paper about 24 hours ago
TIP: Token Importance in On-Policy Distillation
pb09204048  submitted a paper about 1 month ago
On-Policy Self-Distillation for Reasoning Compression
pb09204048  authored a paper about 1 month ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
View all activity

Papers

Support Tokens, Stability Margins, and a New Foundation for Robust LLMs

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning

View all Papers

Articles
pb09204048 
authored a paper about 24 hours ago
pb09204048 
submitted a paper to Daily Papers about 1 month ago
pb09204048 
authored a paper about 1 month ago
pb09204048 
submitted a paper to Daily Papers about 2 months ago
JasonZhu13 
published an article 3 months ago
view article
Article

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

•
71
pb09204048 
authored a paper 3 months ago
rohjain 
authored a paper 6 months ago
akjindal53244 
authored a paper about 2 years ago
JasonZhu13 
authored a paper about 2 years ago