Related papers: GPD: Guided Progressive Distillation for Fast and …

This paper presents our method for the generative track of The First Dataset Distillation Challenge at ECCV 2024. Since the diffusion model has become the mainstay of generative models because of its high-quality generative effects, we…

Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…

Spatio-temporal modeling is foundational for smart city applications, yet it is often hindered by data scarcity in many cities and regions. To bridge this gap, we propose a novel generative pre-training framework, GPD, for spatio-temporal…

Image generation using diffusion models have demonstrated outstanding learning capabilities, effectively capturing the full distribution of the training dataset. They are known to generate wide variations in sampled images, albeit with a…

Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…

Diffusion- and flow-based models have emerged as state-of-the-art generative modeling approaches, but they require many sampling steps. Consistency models can distill these models into efficient one-step generators; however, unlike flow-…

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free…

Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption…

Diffusion models are among the most effective methods for image generation. This is in particular because, unlike GANs, they can be easily conditioned during training to produce elements with desired class or properties. However, guiding a…

Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this potential in practice remains challenging: reducing the number of…

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…

Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning…

Diffusion models offer superior generation quality at the expense of extensive sampling steps. Distillation methods, with Distribution Matching Distillation (DMD) as a popular example, can mitigate this issue, but performance degradation…

Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…

This paper addresses the challenge of achieving high-quality and fast image generation that aligns with complex human preferences. While recent advancements in diffusion models and distillation have enabled rapid generation, the effective…

Recently, diffusion distillation methods have compressed thousand-step teacher diffusion models into one-step student generators while preserving sample quality. Most existing approaches train the student model using a diffusive divergence…

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…

Score-based distillation methods (e.g., variational score distillation) train one-step diffusion models by first pre-training a teacher score model and then distilling it into a one-step student model. However, the gradient estimator in the…

We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing…

We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained for 2D image synthesis have been turned into…