Liang Pan

EgoTwin: Dreaming Body and View in First Person

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

HSImul3R: Reconstructing Simulation-Ready Human-Scene-Interaction from Sparse Views

PhysX-3D: Physical-Grounded 3D Asset Generation

ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model

DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

VideoLucy: Deep Memory Backtracking for Long Video Understanding

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation

GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

MVPaint: 3D Texture Generation with Multi-View Consistency