DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation Paper • 2506.03123 • Published 3 days ago • 14
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly Paper • 2505.10610 • Published 22 days ago • 53
FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors Paper • 2501.08225 • Published Jan 14 • 19
Improving Image Restoration through Removing Degradations in Textual Representations Paper • 2312.17334 • Published Dec 28, 2023 • 2