Vision-Language Models Are Joint Denoisers in Robotic Action Generation
JADE is introduced, a Joint Action DEnoiser that enables the VLM and action expert to jointly refine actions and enables JADE to generate actions with fewer sampling steps, helping offset the additional cost of VLM participation.
Xi-Cheng Gong, Wen-Xuan Song, Cheng-Ze Liu et al.
· 0 citations