collaborators

7 papers

cs.CV2025

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers

Dogyun Park, Moayed Haji-Ali, Yanyu Li +5

Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively exp…

cs.CV2025

Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds

Yushu Wu, Yanyu Li, Anil Kag +9

Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like…

cs.CV2025

CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion

Yanyu Li, Pencheng Wan, Liang Han +3

Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost an…

cs.CV2025

H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models

Yushu Wu, Yanyu Li, Ivan Skorokhodov +6

Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power…

cs.CV2025

Improving the Diffusability of Autoencoders

Ivan Skorokhodov, Sharath Girish, Benran Hu +5

Latent diffusion models have emerged as the leading approach for generating high-quality images and videos, utilizing compressed latent representations to reduce the computational…

cs.CV2024

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

Dongting Hu, Jierun Chen, Xijie Huang +16

Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…