Related papers: Fast T2T: Optimization Consistency Speeds Up Diffu…

Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse…

Stable Diffusion has achieved remarkable success in the field of text-to-image generation, with its powerful generative capabilities and diverse generation results making a lasting impact. However, its iterative denoising introduces high…

Machine learning methods, such as diffusion models, are widely explored as a promising way to accelerate high-fidelity fluid dynamics computation via a super-resolution process from faster-to-compute low-fidelity input. However, existing…

Modern deep learning methods typically treat image sequences as large tensors of sequentially stacked frames. However, is this straightforward representation ideal given the current state-of-the-art (SoTA)? In this work, we address this…

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…

Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the…

Many robotic systems, such as mobile manipulators or quadrotors, cannot be equipped with high-end GPUs due to space, weight, and power constraints. These constraints prevent these systems from leveraging recent developments in visuomotor…

Diffusion models enable high-quality virtual try-on (VTO) with their established image synthesis abilities. Despite the extensive end-to-end training of large pre-trained models involved in current VTO methods, real-world applications often…

Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, latent space smoothness within diffusion models remains…

Diffusion models (DMs) create samples from a data distribution by starting from random noise and iteratively solving a reverse-time ordinary differential equation (ODE). Because each step in the iterative solution requires an expensive…

The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…

Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their…

To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-guided generation have been recently proposed due to their…

We introduce the Approximated Optimal Transport (AOT) technique, a novel training scheme for diffusion-based generative models. Our approach aims to approximate and integrate optimal transport into the training process, significantly…

Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images…

Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two challenges: the sensitivity of DPO to preference pairs and…

Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and…

Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prompt. Previous work has attempted to address this issue by steering the model using guidance…

Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing advances face significant efficiency challenges due to the…

The diffusion model has demonstrated promising results in image generation, recently becoming mainstream and representing a notable advancement for many generative modeling tasks. Prior applications of the diffusion model for both fast…