Pang_RandAR_Decoder-only_Autoregressive_Visual_Generation_in_Random_Orders@CVPR2025@CVF

Total: 1

#1 RandAR: Decoder-only Autoregressive Visual Generation in Random Orders [PDF13] [Copy] [Kimi11] [REL]

Authors: Ziqi Pang, Tianyuan Zhang, Fujun Luan, Yunze Man, Hao Tan, Kai Zhang, William T. Freeman, Yu-Xiong Wang

We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generatng images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a predefined generation order, RandAR removes this inductive bias, unlocking new capabilities in decoder-only generation. Our essential design enabling random order is to insert a "position instruction token" before each image token to be predicted, representing the spatial location of the next image token. Trained on randomly permuted token sequences -- a more challenging task than fixed-order generation, RandAR achieves comparable performance to conventional raster-order counterpart. More importantly, decoder-only transformers trained from random orders acquire new capabilities. For the efficiency bottleneck of AR models, RandAR adopts parallel decoding with KV-Cache at inference time, enjoying 2.5x acceleration without sacrificing generation quality. Additionally, RandAR supports in-painting, outpainting and resolution extrapolation in a zero-shot manner.We hope RandAR inspires new directions for decoder-only visual generation models and broadens their applications across diverse scenarios.

Subject: CVPR.2025 - Oral