Zhiwen Fan

Educational Background

Ph.D., Electrical and Computer Engineering, The University of Texas at Austin – 2025

- Multi-modal learning
- Generative artificial intelligence (AI)
- Robotics
- Spatial computing

Fan, Z., et al. “Large Spatial Model: End-to-End Unposed Images to Semantic 3D,” Advances in Neural Information Processing Systems (NeurIPS), vol. 37, pp. 40212–40229, 2024.
Cong, W., et al. “Can Test-Time Scaling Improve World Foundation Model?,” Second Conference on Language Modeling (COLM), 2025.
Li, L., Fan, Z., Cong, W., Liu, X., Yin, Y., Foutter, M., ... & Wei, Y. “Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions,” Advances in Neural Information Processing Systems (NeurIPS), 2025.
Hu, H., et al. “Expressive Gaussian Human Avatars from Monocular RGB Video,” Advances in Neural Information Processing Systems (NeurIPS), vol. 37, pp. 5646–5660, 2024.
Yu, W., et al. “X²-Gaussian: 4D Radiative Gaussian Splatting for Continuous-Time Tomographic Reconstruction,” IEEE/CVF International Conference on Computer Vision (ICCV), 2025.