3 papers
cs.CV2025
HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation
Hongye Cheng, Tianyu Wang, Guangsi Shi +2
Co-speech gestures are crucial non-verbal cues that enhance speech clarity and expressiveness in human communication, which have attracted increasing attention in multimodal resear…
cs.LG2025
The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation
Ho Kei Cheng, Alexander Schwing
Minibatch optimal transport coupling straightens paths in unconditional flow matching. This leads to computationally less demanding inference as fewer integration steps and less co…
cs.CV2024
MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Ho Kei Cheng, Masato Ishii, Akio Hayakawa +3
We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework MMAudio. In contrast to si…