Related papers: Hierarchical Autoregressive Image Models with Auxi…

Autoregressive models have demonstrated great performance in natural language processing (NLP) with impressive scalability, adaptability and generalizability. Inspired by their notable success in NLP field, autoregressive models have been…

Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…

Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most advanced accelerators. While speculative decoding has been explored to mitigate this…

Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain,…

A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with serial conditioning. Some recent works have addressed this by conditioning between…

As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect…

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural…

The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…

Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet. However, such models require many thousands of gradient-based weight updates and unique…

Image AutoRegressive (IAR) models have achieved state-of-the-art performance in speed and quality of generated images. However, they also raise concerns about memorization of their training data and its implications for privacy. This work…

While autoregressive models excel at image compression, their sample quality is often lacking. Although not realistic, generated images often have high likelihood according to the model, resembling the case of adversarial examples. Inspired…

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…

Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of…

Autoregressive (AR) models have garnered significant attention in image generation for their ability to effectively capture both local and global structures within visual data. However, prevalent AR models predominantly rely on the…

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, they incorporate image context in a linear 1D order by…

Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

Autoregressive neural network models have been used successfully for sequence generation, feature extraction, and hypothesis scoring. This paper presents yet another use for these models: allocating more computation to more difficult…

Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture aspects of the syntax and semantics of language. But what…