MAPO: Mixed Advantage Policy Optimization
Paper • 2509.18849 • Published • 27 •
2
Wenke Huang
WilliamHuang91
AI & ML interests
Federated Learning, Multimodal Large Language Model
Recent Activity
liked a dataset 21 days ago
XuankunRong/SafeTag-VL-3K upvoted a paper 4 months ago
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data liked a Space 9 months ago
gangweix/Pixel-Perfect-DepthOrganizations
commented a
paper 10 months ago