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.
Fan, Z., et al. “VLM-3R: Vision-language models augmented with instruction-aligned 3D reconstruction,” arXiv preprint arXiv:2505.20279, 2025.
Cong, W., et al. “Can test-time scaling improve world foundation model?,” Second Conference on Language Modeling (COLM), 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.
Fan, Z., et al. “LightGaussian: Unbounded 3D Gaussian compression with 15× reduction and 200+ FPS,” Advances in Neural Information Processing Systems (NeurIPS), vol. 37, pp. 140138–140158, 2024.
Fan, Z., et al. “M³ViT: Mixture-of-experts vision transformer for efficient multi-task learning with model-accelerator co-design,” Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 28441–28457, 2022.