🚀 Training an image generation model and picking sides between autoregressive (AR) and diffusion? Why not both? Check out MADFormer with half of the model layers for AR and half for diffusion. AR gives a fast guess for the next patch prediction while diffusion helps refine the
First-year PhD student @HKUniversity @XLangNLP. B.Eng. @Tsinghua_Uni; previously interned at @tsvetshop. Interested in VLA, multimodal learning, and RL.

