2 papers
cs.RO2026
Motus2: A Self-Evolving General World Model for Dexterous Manipulation
Hongzhe Bi, Zihao Zhou, Yihang Tang +16
General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing mo…
cs.AI2025
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
Junzhe Li, Yutao Cui, Tao Huang +8
Although GRPO substantially enhances flow matching models in human preference alignment of image generation, methods such as FlowGRPO and DanceGRPO still exhibit inefficiency due t…