arxiv:2512.06547
Bruce Li
XiaocanBruceLi
ยท
AI & ML interests
None yet
Recent Activity
authored
a paper
7 days ago
A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation
liked
a model
9 months ago
siuze/FOC-yngping
Organizations
None yet