Tian Han (than6)

Tian Han

Assistant Professor

Charles V. Schaefer, Jr. School of Engineering and Science

Department of Computer Science

Gateway Center S248
(201) 216-5484
Website

Education

  • PhD (2019) University of California, Los Angeles (Statistics)
  • Other (2013) The Hong Kong University of Science and Technology (Computer Science)

Research

Unsupervised/Semi-supervised Learning, Probabilistic Generative Modeling, Explainable AI, Computer Vision.

General Information

I received my PhD degree from the Statistics Department at the University of California, Los Angeles (UCLA). I'm in the area of artificial intelligence (AI) and machine learning, focusing on developing statistical learning methods for probabilistic models, and on building explainable and controllable AI systems for various applications. I have published papers and served as an Area Chair or Senior Program Committee member at leading conferences in computer vision, machine learning, and AI, including CVPR, NeurIPS, ECCV, ICCV and AAAI.

Experience

Graduate Research Assistant - UCLA (2018-2019)

Institutional Service

  • Transfer Credit Coordinator Member

Appointments

2019, Tenure-track Assistant Professor

Honors and Awards

CISE-RI: NSF CAREER Award (2024)

Selected Publications

Conference Proceeding

  1. Li, H.; Han, T. (2024). Enforcing Sparsity on Latent Space for Robust and Explainable Representations (pp. 5282-5291). Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024).
    https://openaccess.thecvf.com/content/WACV2024/papers/Li_Enforcing_Sparsity_on_Latent_Space_for_Robust_and_Explainable_Representations_WACV_2024_paper.pdf.
  2. Cui, J.; Wu, Y.; Han, T. (2023). Learning Hierarchical Features with Joint Latent Space Energy-Based Prior (pp. 2218--2227). Proceedings of IEEE International Conference on Computer Vision (ICCV 2023).
    https://openaccess.thecvf.com/content/ICCV2023/papers/Cui_Learning_Hierarchical_Features_with_Joint_Latent_Space_Energy-Based_Prior_ICCV_2023_paper.pdf.
  3. Cui, J.; Han, T. (2023). Learning Energy-based Model via Dual-MCMC Teaching (vol. 36, pp. 28861-28872). Advances in Neural Information Processing Systems (NeurIPS 2023).
    https://proceedings.neurips.cc/paper_files/paper/2023/file/5bed8703db85ab27dc32f6a42f8fbdb6-Paper-Conference.pdf.
  4. Kong, D.; Pang, B.; Han, T.; Wu, Y. (2023). Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting. Uncertainty in Artificial Intelligence (UAI 2023) (pp. 1109-1120). PMLR.
    https://proceedings.mlr.press/v216/kong23a/kong23a.pdf.
  5. Cui, J.; Wu, Y.; Han, T.. Learning Joint Latent Space EBM Prior Model for Multi-layer Generator (pp. 3603-3612). Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023).
    https://doi.org/10.1109/CVPR52729.2023.00351.
  6. Xiao, Z.; Han, T. (2022). Adaptive multi-stage density ratio estimation for learning latent space energy-based model (vol. 35, pp. 21590-21601). Advances in Neural Information Processing Systems (NeurIPS 2022).
    https://proceedings.neurips.cc/paper_files/paper/2022/file/874a4d89f2d04b4bcf9a2c19545cf040-Paper-Conference.pdf.
  7. Lu, C.; Han, T.; Ning, Y. (2022). Context-aware health event prediction via transition functions on dynamic disease graphs. Proceedings of the AAAI Conference on Artificial Intelligence (4 ed., vol. 36, pp. 4567-4574). AAAI.
    https://www.aaai.org/AAAI22Papers/AAAI-6800.LuC.pdf.
  8. Zhao, Y.; Qiu, L.; Lu, P.; Shi, F.; Han, T.; Zhu, S. (2022). Learning from the Tangram to Solve Mini Visual Tasks (3 ed., vol. 36, pp. 3490--3498). The Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022.
    https://www.aaai.org/AAAI22Papers/AAAI-10312.ZhaoY.pdf.
  9. Pang, B.; Han, T.; Nijkamp, E.; Zhu, S.; Wu, Y. (2020). Learning Latent Space Energy-Based Prior Model. Advances in Neural Information Processing Systems (NeurIPS 2020).
  10. Nijkamp, E.; Pang, B.; Han, T.; Zhou, L.; Zhu, S.; Wu, Y. (2020). Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference. 16th European Conference on Computer Vision, ECCV 2020.
  11. Han, T.; Nijkamp, E.; Zhou, L.; Pang, B.; Zhu, S.; Wu, Y. (2020). Joint Training of Variational Auto-Encoder and Latent Energy-Based Model (pp. 7978--7987). Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020.
  12. Nijkamp, E.; Hill, M.; Han, T.; Zhu, S.; Wu, Y. (2020). On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models (pp. 5272--5280). The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020.
  13. Han, T.; Nijkamp, E.; Fang, X.; Hill, M.; Zhu, S.; Wu, Y. (2019). Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inferential Model. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019.
  14. Han, T.; Lu, Y.; Zhu, S.; Wu, Y. (2017). Alternating Back-Propagation for Generator Network. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17).

Conference Workshop Contribution

  1. Han, T.; Zhang, J.; Wu, Y. (2020). From em-projection to Variational Auto-Encoder. NeurIPS 2020 Workshop on Deep Learning through Information Geometry.

Journal Article

  1. Xing, X.; Gao, R.; Han, T.; Zhu, S.; Wu, Y. (2020). Deformable Generator Networks: Unsupervised Disentanglement of Appearance and Geometry. Transactions on Pattern Analysis and Machine Intelligence (PAMI). IEEE.

Courses

[CS559-B]: Machine Learning: fundamentals and applications --Fall 19, Spring 20, Fall 20, Fall 21, Fall 22, Fall 23, Fall 24
[CS515-A]: Fundamental of Computing --Spring 21
[CS583-A, B]: Deep Learning --Spring 22, Spring 23, Spring 24, Spring 25.