L-YeZhu
Postdoc @ CS Princeton. Research in Generation Models, Computer Vision, and ML4Astrophysics, also interested in CogScience.
Princeton UniversityNJ, USA
Pinned Repositories
AI4Astronomy.github.io
Project website
Beats_Scores
A simple tool for calculating musical beats scores in terms of rhythm correspondence.
BoundaryDiffusion
[NeurIPS2023] BoundaryDiffusion: A learning-free method for semantic control with Diffusion Models
CDCD
[ICLR2023] Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation (CDCD).
D2M-GAN
[ECCV2022] D2M-GAN for music generation from dance videos
DiscoveryDiff
Discovery and Expansion of New Domains within Diffusion Models
L-YeZhu.github.io
Learning-Audio-Visual-Correlations
[ICCASP2021] Learning Audio-Visual Correlations from Variational Cross-Modal Generation.
SI-Dial
Supplementing Missing Visions via Dialog for Scene Graph Generations
Video-Description-via-Dialog-Agents-ECCV2020
[ECCV2020] Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
L-YeZhu's Repositories
L-YeZhu/CDCD
[ICLR2023] Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation (CDCD).
L-YeZhu/D2M-GAN
[ECCV2022] D2M-GAN for music generation from dance videos
L-YeZhu/BoundaryDiffusion
[NeurIPS2023] BoundaryDiffusion: A learning-free method for semantic control with Diffusion Models
L-YeZhu/Learning-Audio-Visual-Correlations
[ICCASP2021] Learning Audio-Visual Correlations from Variational Cross-Modal Generation.
L-YeZhu/Video-Description-via-Dialog-Agents-ECCV2020
[ECCV2020] Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents
L-YeZhu/DiscoveryDiff
Discovery and Expansion of New Domains within Diffusion Models
L-YeZhu/SI-Dial
Supplementing Missing Visions via Dialog for Scene Graph Generations
L-YeZhu/Beats_Scores
A simple tool for calculating musical beats scores in terms of rhythm correspondence.
L-YeZhu/AI4Astronomy.github.io
Project website
L-YeZhu/L-YeZhu.github.io