Related papers: DRiffusion: Draft-and-Refine Process Parallelizes …

Masked Diffusion Models (MDMs) offer a promising alternative to autoregressive language models by enabling parallel token generation and bidirectional context modeling. However, their inference speed is significantly limited by the…

Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a promising acceleration technique by reducing the resolution…

Recent advances in diffusion models have driven remarkable progress in image generation. However, the generation process remains computationally intensive, and users often need to iteratively refine prompts to achieve the desired results,…

Video generation models have been used as a robot policy to predict the future states of executing a task conditioned on task description and observation. Previous works ignore their high computational cost and long inference time. To…

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding reverse process progressively "denoises"…

Diffusion models have become a leading method for generative modeling of both image and scientific data. As these models are costly to train and \emph{evaluate}, reducing the inference cost for diffusion models remains a major goal.…

Discrete diffusion models have emerged as a promising direction for vision-language tasks, offering bidirectional context modeling and theoretical parallelization. However, their practical application is severely hindered by a…

Diffusion planning has been recognized as an effective decision-making paradigm in various domains. The capability of generating high-quality long-horizon trajectories makes it a promising research direction. However, existing diffusion…

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in…

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later…

Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs,…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast…

Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…

Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…

Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be…

Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too…