Cheng Han

Assistant Professor
chk9k (at) umsystem.edu
University of Missouri -- Kansas City, USA

Biography

I am a Tenure-track Assistant Professor at the School of Science and Engineering, University of Missouri -- Kansas City, USA. My research interests include adaptable and sustainable intelligence, where I design, implement, deploy, and evaluate AI systems that empower the communities. I am continuously interested in recuriting Ph.D. students with strong background in AI agents and systemic efficiency.

News (03/14/2025): Website updated for new papers published in EMNLP and ICLR. Congrats to Taowen and Yiyang!

Table of Content

Selected Publications

  1. Visual Recognition with Deep Nearest Centriods [pdf(arxiv)][code]. W. Wang*†, C. Han*, T. Zhou*, D. Liu†, International Conference on Learning Representations (ICLR), 2023 (Spotlight). *Equal Contribution

  2. Prompt Learns Prompt: Exploring Knowledge-Aware Generative Prompt Collaboration For Video Captioning [pdf(IJCAI)]. L. Yan*, C. Han*, Z. Xu, D. Liu†, Q. Wang, International Joint Conferences on Artificial Intelligence (IJCAI), 2023. *Equal Contribution

  3. E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [pdf(arxiv)][code]. C. Han*, Q. Wang, Y. Cui, Z. Cao, W. Wang, S. Qi, D. Liu†. International Conference on Computer Vision (ICCV), 2023.

  4. Unified 3D Segmenter As Prototypical Classifiers [pdf(Openreview)][code]. Z. Qin*, C. Han*, X. Lu, Q. Wang, X, Nie, Y, Yin†. Conference on Neural Information Processing Systems (NeurIPS), 2023. *Equal Contribution

  5. CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation [pdf(arxiv)]. Y. Cui, C. Han, D. Liu†. ACM Journal on Autonomous Transportation Systems (JATS), 2023.

  6. Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning? C. Han*, Q. Wang, Y. Cui, W. Wang, L. Huang, S. Qi, D. Liu†. International Conference on Learning Representations (ICLR), 2024 [pdf(Openreview)][code].

  7. Image Translation as Diffusion Visual Programmers. C. Han, J. C. Liang, Q. Wang, M. Rabbani, S. Dianat, R. Rao, Y. N. Wu, D. Liu†. International Conference on Learning Representations (ICLR), 2024. [pdf(Openreview)][Website].

  8. ProMotion: Prototypes As Motion Learners. Y. Lu, D. Liu, Q., C. Han, Y. Cui, Z. Cao, X. Zhang, Y. V. Chen, H. Fan†. IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024. [pdf]

  9. SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving. Y. Cui, C. Han, D. Liu†. [pdf]

  10. Prototypical Transformer as Unified Motion Learners. C. Han*, Y. Lu*, G. Sun, J. C. Liang, Z. Cao, Q. Wang, Q. Guan, S. A. Dianat, R. M. Rao, T. Geng, Z. Tao†, D. Liu†. International Conference on Machine Learning (ICML), 2024. [pdf]

  11. Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks. Z. Cheng, C. Han, J. C. Liang, Q. Wang, X. Zhang, D. Liu†. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024. [pdf]

  12. Optical Flow as Spatial-Temporal Attention Learners. Y. Lu*, C. Han*, Q. Wang, H. Fan, Z. Kong, D. Liu, Y. Chen. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024.

  13. AMD: Automatic Multi-step Distillation of Large-scale Vision Models. C. Han, Q. Wang, S. A Dianat, M. Rabbani, R. M Rao, Y. Fang, Q. Guan, L. Huang, D. Liu†. The European Conference on Computer Vision (ECCV), 2024. [pdf]

  14. M^2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning. T. Wang, Y. Liu, J. C. Liang, J. Zhao, Y. Cui, Y. Mao, S. Nie, J. Liu, F. Feng, Z. Xu, C. Han, L. Huang, Q. Wang, D. Liu. The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. [pdf]

  15. Visual Fourier Prompt Tuning. R. Zeng*, C. Han*, Q Wang, C. Wu, T. Geng, L. Rao, L. Huang, Y. N. Wu, D. Liu. The Conference on Neural Information Processing Systems (NeurIPS), 2024. [pdf]

  16. Re-Imagining Multimodal Instruction Tuning: A Representation View. Y. Liu, J. C. Liang, R. Tang, Y. Lee, M. Rabbani, S. Dianat, R. Rao, L. Huang, D. Liu, Q. Wang, C. Han†. The International Conference on Learning Representations (ICLR), 2025. [pdf]

Services

  1. Faculty Search Committee at the University of Missouri – Kansas City, 2024

  3. Graduate Committee at the University of Missouri – Kansas City, 2024

  5. Program Committee, The Association for the Advancement of Artificial Intelligence (AAAI), 2023 -- Now.

  7. Program Committee, SIAM International Conference on Data Mining (SDM), 2024.

  9. Reviewer, The Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.

  11. Reviewer, The International Conference on Learning Representations (ICLR), 2024.

  13. Reviewer, The Conference on Computer Vision and Pattern Recognition (CVPR), 2022 -- Now.

  15. Reviewer, IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022 -- Now.

  17. Reviewer, Association for Computational Linguistics Rolling Review (ARR), 2023 -- Now.

  18. Reviewer, The International World Wide Web Conference (WWW), 2024.

  19. Reviewer, The Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

  20. Reviewer, The International Conference on Learning Representations (ICLR), 2023 – now

  21. Reviewer, The International Conference on Machine Learning (ICML), 2023 – now

  22. Reviewer, International Journal of Computer Vision (IJCV), 2024

  23. Reviewer, Transactions on Machine Learning Research (TMLR), 2024

  24. Reviewer, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024.

  25. Reviewer, IEEE Transactions on Artificial Intelligence (IEEE TAI), 2025.

  26. Reviewer, Neurocomputing, 2024.

Talks and Presentation

  1. ICLR 2023 Spotlight Presentation, Visual Recognition with Deep Nearest Centriods [YouTube].

  3. ICCV 2023 Presentation, E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [YouTube].

  5. NeurIPS 2023 Presentation, Unified 3D Segmenter as Prototypical Classifiers. New Orleans, USA.

  7. ICLR 2024 Presentation, Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?

  9. ICLR 2024 Presentation, Image Translation as Diffusion Visual Programmers.

Teaching

  1. UMKC COMP-SCI 5567-0001: Deep Learning Spring, 2025.