3 papers
cs.CV2026
Not All Tokens Need 40 Steps: Heterogeneous Step Allocation in Diffusion Transformers for Efficient Video Generation
Ernie Chu, Vishal M. Patel
Diffusion Transformers (DiTs) have achieved state-of-the-art video generation quality, but they incur immense computational cost because standard inference applies the same number…
cs.CV2026
NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation
Yu Zeng, Charles Ochoa, Mingyuan Zhou +3
Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image genera…
cs.CV2024
JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
Yu Zeng, Vishal M. Patel, Haochen Wang +4
Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains. To a…