activity
20242026
collaborators

5 papers

cs.CV2026

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm

Yaofang Liu, Kangning Cui, Meng Chu +7

Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to seria…

cs.CV2026

Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation

Yaofang Liu, Yumeng Ren, Aitor Artola +9

The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchronization of frame evolution imposed…

cs.CV2025

Improving Diffusion Generative Models via Truncated Karhunen--Loève Expansion

Yumeng Ren, Yaofang Liu, Aitor Artola +3

Pretrained diffusion models exhibit a well-known training-sampling mismatch, often attributed to exposure bias and related distribution-shift effects. We provide a quantitative int…

cs.CV2024

Super-resolving Real-world Image Illumination Enhancement: A New Dataset and A Conditional Diffusion Model

Yang Liu, Yaofang Liu, Jinshan Pan +4

Most existing super-resolution methods and datasets have been developed to improve the image quality in well-lighted conditions. However, these methods do not work well in real-wor…

cs.CV2024

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach

Yaofang Liu, Yumeng Ren, Xiaodong Cun +5

Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar ti…