Hao Sun
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper presents EAGG, an embodiment-aligned grasp generator that generalizes across objects and end effectors.
The paper introduces Kops, an extension interface for eBPF that allows userspace compilers and kernel modules to introduce new operations without modifying the kernel core, improving performance and reducing the trusted computing base.
Muon improves agentic RL performance in sparse-reward tasks under GiGPO, particularly with specific advantage estimators and learning rates.
Papers
When Does Muon Help Agentic Reinforcement Learning?
Kai Ruan, Jinghao Lin, Zihe Huang, Ziqi Zhou +3 more
Muon improves agentic RL performance in sparse-reward tasks under GiGPO, particularly with specific advantage estimators and learning rates.