Related papers: Autoregressive Image Generation with Randomized Pa…

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

We introduce Purrception, a variational flow matching approach for vector-quantized image generation that provides explicit categorical supervision while maintaining continuous transport dynamics. Our method adapts Variational Flow Matching…

AutoRegressive (AR) models have made notable progress in image generation, with Masked AutoRegressive (MAR) models gaining attention for their efficient parallel decoding. However, MAR models have traditionally underperformed when compared…

Diffusion models enable high-quality and diverse visual content synthesis. However, they struggle to generate rare or unseen concepts. To address this challenge, we explore the usage of Retrieval-Augmented Generation (RAG) with image…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. Current numerical reasoning methods…

Existing autoregressive (AR) image generative models use a token-by-token generation schema. That is, they predict a per-token probability distribution and sample the next token from that distribution. The main challenge is how to model the…

Sequence-to-sequence vision-language models are showing promise, but their applicability is limited by their inference latency due to their autoregressive way of generating predictions. We propose a parallel decoding sequence-to-sequence…

Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this paper, we explore the…

We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial…

Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, especially those describing complex sound events. We uncover a…

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…

Deep learning has been successfully demonstrated in MRI reconstruction of accelerated acquisitions. However, its dependence on representative training data limits the application across different contrasts, anatomies, or image sizes. To…

Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing methods typically rely on dedicated models for achieving…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…

Autoregressive (AR) models have demonstrated significant success in the realm of text-to-image generation. However, they usually face two major challenges. Firstly, the generated images may not always meet the quality standards expected by…

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

We introduce a cluster-based generative image segmentation framework to encode higher-level representations of visual concepts based on one-shot learning inspired by the Omniglot Challenge. The inferred parameters of each component of a…

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…