Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Paper • 2604.02288 • Published • 33
Weikai Xu PRO
xwk123
AI & ML interests
VLM-based Mobile Agents & Tool learning Agents & Agentic RL
Recent Activity
updated a collection 18 days ago
MobileWorldModel updated a collection 18 days ago
MobileWorldModel upvoted a paper 19 days ago
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample RoutingOrganizations
None yet
upvoted a paper 19 days ago