RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating 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 enables random order by inserting 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 its 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 inpainting, 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. Our project page is at https://rand-ar.github.io/.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderInductive BiasSimilar Papers 제목 키워드 기반
DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation
Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of a…
multimodal generationImage GenerationDenoising Autoregressive Representation Learning
In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squ…
DecoderDenoisingImage GenerationRepresentation LearningAR-Omni: A Unified Autoregressive Model for Any-to-Any Generation
Real-world perception and interaction are inherently multimodal, encompassing not only language but also vision and speech, which motivates the development of "Omni" MLLMs that support both multimodal inputs and multimod…
multimodal generationImage GenerationV2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language m…
DecoderImage GenerationLanguage ModelingLanguage Modelling+1GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token predict…
DecoderImage GenerationImage ReconstructionRepresentation Learning