相关论文: Distilling Specialized Orders for Visual Generatio…

Conventional wisdom suggests that autoregressive models are used to process discrete data. When applied to continuous modalities such as visual data, Visual AutoRegressive modeling (VAR) typically resorts to quantization-based approaches to…

Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (''slots'') from images, unconditional…

This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…

Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements…

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard…

Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR…

AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those of diffusion models. However, their token-by-token image generation mechanism remains computationally intensive…

Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first…

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B…

Directly generating 3D meshes, the default representation for 3D shapes in the graphics industry, using auto-regressive (AR) models has become popular these days, thanks to their sharpness, compactness in the generated results, and ability…

State-of-the-art vision pretraining methods rely on image-level self-distillation from object-centric datasets such as ImageNet, implicitly assuming each image contains a single object. This assumption does not always hold: many ImageNet…

Autoregressive (AR) Large Language Models (LLMs) have demonstrated significant success across numerous tasks. However, the AR modeling paradigm presents certain limitations; for instance, contemporary autoregressive LLMs are trained to…

Autoregressive models excel in efficiency and plug directly into the transformer ecosystem, delivering robust generalization, predictable scalability, and seamless workflows such as fine-tuning and parallelized training. However, they…

Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training…

Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing the fast one-step models remains challenging, as existing methods consistently fail to…

Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…

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…

Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap,…