Di Chang

7

Papers

88

Total Citations

Papers (7)

DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis

DIM: Dyadic Interaction Modeling for Social Behavior Generation

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

X-Dyna: Expressive Dynamic Human Image Animation

X-Dancer: Expressive Music to Human Dance Video Generation

DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion