Related papers: Causal Forcing++: Scalable Few-Step Autoregressive…

Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce…

Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by…

Modeling physical systems in a generative manner offers several advantages, including the ability to handle partial observations, generate diverse solutions, and address both forward and inverse problems. Recently, diffusion models have…

Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a single-step…

Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrates significant potential due to its strong theoretical…

The increased demand for 3D data in AR/VR, robotics and gaming applications, gave rise to powerful generative pipelines capable of synthesizing high-quality 3D objects. Most of these models rely on the Score Distillation Sampling (SDS)…

With the advance of diffusion models, today's video generation has achieved impressive quality. But generating temporal consistent long videos is still challenging. A majority of video diffusion models (VDMs) generate long videos in an…

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism…

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…

While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend…

Diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance.To achieve efficient Real-ISR, many works employ Variational Score Distillation (VSD) to distill pre-trained stable-diffusion (SD)…

Diffusion models generate high-quality images but require dozens of forward passes. We introduce Distribution Matching Distillation (DMD), a procedure to transform a diffusion model into a one-step image generator with minimal impact on…

The inference latency of diffusion models remains a critical barrier to their real-time application. While trajectory-based and distribution-based step distillation methods offer solutions, they present a fundamental trade-off.…

With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic…

Diffusion Probability Models (DPMs) have made impressive advancements in various machine learning domains. However, achieving high-quality synthetic samples typically involves performing a large number of sampling steps, which impedes the…

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and…

Existing video tokenizers typically use the traditional Variational Autoencoder (VAE) architecture for video compression and reconstruction. However, to achieve good performance, its training process often relies on complex multi-stage…

Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teacher gradients these pipelines consume are Monte Carlo (MC) expectations over noise…

We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existing next-token…