Optimizing diffusion noise can serve as universal motion priors

K Karunratanakul, K Preechakul… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract We propose Diffusion Noise Optimization (DNO) a new method that effectively
leverages existing motion diffusion models as motion priors for a wide range of motion …

Imagine flash: Accelerating emu diffusion models with backward distillation

J Kohler, A Pumarola, E Schönfeld… - arXiv preprint arXiv …, 2024 - arxiv.org
Diffusion models are a powerful generative framework, but come with expensive inference.
Existing acceleration methods often compromise image quality or fail under complex …

Schrodinger bridges beat diffusion models on text-to-speech synthesis

Z Chen, G He, K Zheng, X Tan, J Zhu - arXiv preprint arXiv:2312.03491, 2023 - arxiv.org
In text-to-speech (TTS) synthesis, diffusion models have achieved promising generation
quality. However, because of the pre-defined data-to-noise diffusion process, their prior …

Stochastic runge-kutta methods: Provable acceleration of diffusion models

Y Wu, Y Chen, Y Wei - arXiv preprint arXiv:2410.04760, 2024 - arxiv.org
Diffusion models play a pivotal role in contemporary generative modeling, claiming state-of-
the-art performance across various domains. Despite their superior sample quality …

Deep compression autoencoder for efficient high-resolution diffusion models

J Chen, H Cai, J Chen, E Xie, S Yang, H Tang… - arXiv preprint arXiv …, 2024 - arxiv.org
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models
for accelerating high-resolution diffusion models. Existing autoencoder models have …

Cosign: Few-step guidance of consistency model to solve general inverse problems

J Zhao, B Song, L Shen - European Conference on Computer Vision, 2025 - Springer
Diffusion models have been demonstrated as strong priors for solving general inverse
problems. Most existing Diffusion model-based Inverse Problem Solvers (DIS) employ a …

DiffAIL: Diffusion Adversarial Imitation Learning

B Wang, G Wu, T Pang, Y Zhang, Y Yin - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Imitation learning aims to solve the problem of defining reward functions in real-world
decision-making tasks. The current popular approach is the Adversarial Imitation Learning …

One step diffusion-based super-resolution with time-aware distillation

X He, H Tang, Z Tu, J Zhang, K Cheng, H Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Diffusion-based image super-resolution (SR) methods have shown promise in
reconstructing high-resolution images with fine details from low-resolution counterparts …

On the scalability of diffusion-based text-to-image generation

H Li, Y Zou, Y Wang, O Majumder… - Proceedings of the …, 2024 - openaccess.thecvf.com
Scaling up model and data size has been quite successful for the evolution of LLMs.
However the scaling law for the diffusion based text-to-image (T2I) models is not fully …

DroneDiffusion: Robust Quadrotor Dynamics Learning with Diffusion Models

A Das, RD Yadav, S Sun, M Sun, S Kaski… - arXiv preprint arXiv …, 2024 - arxiv.org
An inherent fragility of quadrotor systems stems from model inaccuracies and external
disturbances. These factors hinder performance and compromise the stability of the system …