The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation Paper โข 2503.10636 โข Published 1 day ago โข 3 โข 1
Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis Paper โข 2412.15322 โข Published Dec 19, 2024 โข 18 โข 2
Tracking Anything with Decoupled Video Segmentation Paper โข 2309.03903 โข Published Sep 7, 2023 โข 28 โข 2