Related papers: IAR2: Improving Autoregressive Visual Generation w…
Segment Anything Model 2 (SAM2), a vision foundation model has significantly advanced in prompt-driven video object segmentation, yet their practical deployment remains limited by the high computational and memory cost of processing dense…
Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…
Autoregressive (AR) image generation models are capable of producing high-fidelity images but often suffer from slow inference due to their inherently sequential, token-by-token decoding process. Speculative decoding, which employs a…
Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \textbf{VideoMAR}, a concise and…
Autoregressive conditional image generation algorithms are capable of generating photorealistic images that are consistent with given textual or image conditions, and have great potential for a wide range of applications. Nevertheless, the…
This paper presents Diffusion via Autoregressive models (D-AR), a new paradigm recasting the image diffusion process as a vanilla autoregressive procedure in the standard next-token-prediction fashion. We start by designing the tokenizer…
Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a…
Autoregressive models have emerged as a powerful generative paradigm for visual generation. The current de-facto standard of next token prediction commonly operates over a single-scale sequence of dense image tokens, and is incapable of…
Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models…
Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with…
Autoregressive (AR) visual generation relies on tokenizers to map images to and from discrete sequences. However, tokenizers are trained to reconstruct clean images from ground-truth tokens, while AR generators are optimized only for token…
Generative recommendation (GR) typically encodes behavioral or semantic aspects of item information into discrete tokens, leveraging the standard autoregressive (AR) generation paradigm to make predictions. However, existing methods tend to…
Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR models while maintaining overall generation quality remains an…
Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images. Nevertheless, the potential of Visual Autoregressive (VAR)…
Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during…
Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with…
Recently, autoregressive (AR) language models have emerged as a dominant approach in speech synthesis, offering expressive generation and scalable training. However, conventional AR speech synthesis models relying on the next-token…
We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches…
Recent advances in text-to-image generative models have enabled numerous practical applications, including subject-driven generation, which fine-tunes pretrained models to capture subject semantics from only a few examples. While…
The success of Large Language Models (LLMs) has motivated a shift toward generative approaches to retrieval and ranking, aiming to supersede classical Dual Encoders (DEs) and Cross Encoders (CEs). A prominent paradigm is pointwise…