Scholar

Zhangjie Wu

Google Scholar ID: WVp4yjoAAAAJ

National University of Singapore

Computer VisionGenerative AIVideo Generation

Citations & Impact

All-time

Citations

2,707

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

1 items

arXiv.org · 2024

Cited

Resume (English only)

Academic Achievements

Publications:
- ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
- Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models (Best Paper Award Candidate at CVPR 2025)
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
- Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
- Cosmos World Foundation Model Platform for Physical AI (Core contributor at NVIDIA)
- InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video
- SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
- EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
- MotionDirector: Motion Customization of Text-to-Video Diffusion Models
- Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks
- VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence
- DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing
Awards:
- Difix3D+ recognized as the Best Paper Award Candidate at CVPR 2025
- Cosmos World Foundation Model Platform awarded Best AI + Best Overall of CES 2025

Research Experience

Education

Ph.D. student at National University of Singapore, advised by Prof. Mike Zheng Shou and Prof. Wynne Hsu; B.Eng. in Computer Science from Shen Yuan Honors College of Beihang University.

Background