Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
3
4
7
Hejian Sang
pb09204048
Follow
Jibbscript's profile picture
webxos's profile picture
QEntanglement's profile picture
8 followers
ยท
6 following
AI & ML interests
None yet
Recent Activity
authored
a paper
1 day ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
upvoted
a
paper
5 days ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
submitted
a paper
5 days ago
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
View all activity
Organizations
Articles
1
Article
62
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
Papers
2
arxiv:
2602.21420
arxiv:
2510.00237
models
0
None public yet
datasets
0
None public yet