collaborators

6 papers

cs.CV2025

Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning

Fu-Yun Wang, Keqiang Sun, Yao Teng +4

Diffusion models have demonstrated remarkable success in various visual generation tasks, including image, video, and 3D content generation. Preference optimization (PO) is a promi…

cs.CV2025

HPSv3: Towards Wide-Spectrum Human Preference Score

Yuhang Ma, Yunhao Shui, Xiaoshi Wu +2

Evaluating text-to-image generation models requires alignment with human perception, yet existing human-centric metrics are constrained by limited data coverage, suboptimal feature…

cs.CV2025

Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models

Fu-Yun Wang, Yunhao Shui, Jingtan Piao +2

Diffusion models have made substantial advances in image generation, yet models trained on large, unfiltered datasets often yield outputs misaligned with human preferences. Numerou…

cs.CV2025

BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

Yijin Li, Yichen Shen, Zhaoyang Huang +9

Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynami…

cs.LG2024

Phased Consistency Models

Fu-Yun Wang, Zhaoyang Huang, Alexander William Bergman +9

Consistency Models (CMs) have made significant progress in accelerating the generation of diffusion models. However, their application to high-resolution, text-conditioned image ge…

cs.CV2024

AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data

Fu-Yun Wang, Zhaoyang Huang, Weikang Bian +5

This paper introduces an effective method for computation-efficient personalized style video generation without requiring access to any personalized video data. It reduces the nece…