xwm/SciWorld-MPO
Reinforcement Learning • 8B • Updated • 7 • 2
xwm
xwm
AI & ML interests
None yet
Recent Activity
authored a paper about 12 hours ago
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding authored a paper about 12 hours ago
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining authored a paper about 12 hours ago
MiMo-Audio: Audio Language Models are Few-Shot LearnersOrganizations
None yet