Daochang Liu

I am a Lecturer (Assistant Professor) at the School of Physics, Mathematics and Computing, The University of Western Australia. I was a postdoctoral researcher at the School of Computer Science, The University of Sydney, and obtained my PhD from Peking University.

My research interests lie in computer vision, generative learning, video understanding and generation, and healthcare applications.

I am actively looking for PhD/MPhil students and research interns. If you are interested, please contact me.

News

May 2026 Two papers accepted to ICML 2026.
May 2026 One paper accepted to MICCAI 2026.
April 2026 One paper accepted to TPAMI.

Selected Publications

Full list on Google Scholar

Progressive chicken generation and information-grounding attention maps

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh, Daochang Liu, Weidong Cai, Xiuying Wang, Chang Xu

International Conference on Machine Learning (ICML), 2026

paper code

Contrastive Flow Map Matching

Junyu Zhang, Daochang Liu, Younghyun Kim, Jong Hwan Ko, Shichao Zhang, Chang Xu, Eunbyung Park

International Conference on Machine Learning (ICML), 2026

paper

Overview of generative physical AI research

Generative Physical AI in Vision: A Survey

Daochang Liu, Junyu Zhang, Anh-Dung Dinh, Eunbyung Park, Shichao Zhang, Ajmal Mian, Mubarak Shah, Chang Xu

arXiv, 2025

paper summary

Privacy-utility trade-offs in diffusion models

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models

Chen Chen, Daochang Liu, Mubarak Shah, Chang Xu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

paper code

Representative Guidance: Diffusion Model Sampling with Coherence

Anh-Dung Dinh, Daochang Liu, Chang Xu

International Conference on Learning Representations (ICLR), 2025

paper code

Anti-Exposure Bias in Diffusion Models

Junyu Zhang, Daochang Liu, Eunbyung Park, Shichao Zhang, Chang Xu

International Conference on Learning Representations (ICLR), 2025

paper code

DiffAct++: Diffusion Action Segmentation

Daochang Liu, Qiyue Li, Anh-Dung Dinh, Tingting Jiang, Mubarak Shah, Chang Xu

IEEE Transactions on Pattern Analysis & Machine Intelligence (TPAMI), 2025

paper

Memorization-free diffusion model framework

Towards Memorization-Free Diffusion Models

Chen Chen, Daochang Liu, Chang Xu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

paper project code video

Adversarial noise-based transfer learning framework

Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning

Xiyu Wang, Baijiong Lin, Daochang Liu, Ying-Cong Chen, Chang Xu

International Conference on Machine Learning (ICML), 2024

paper

Diffusion Action Segmentation

Daochang Liu, Qiyue Li, Anh-Dung Dinh, Tingting Jiang, Mubarak Shah, Chang Xu

International Conference on Computer Vision (ICCV), 2023

paper project code video

Progressive guidance for diffusion sampling

Rethinking Conditional Diffusion Sampling with Progressive Guidance

Anh-Dung Dinh, Daochang Liu, Chang Xu

Conference on Neural Information Processing Systems (NeurIPS), 2023

paper code

Unified surgical skill assessment framework

Towards Unified Surgical Skill Assessment

Daochang Liu, Qiyue Li, Tingting Jiang, Yizhou Wang, Rulin Miao, Fei Shan, Ziyu Li

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

paper project code video

Weakly supervised temporal action localization framework

Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization

Daochang Liu, Tingting Jiang, Yizhou Wang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019

paper code

Selected Services

2026 Program Chair, Digital Image Computing: Techniques and Applications (DICTA)
2025–2026 Area Chair, Conference on Neural Information Processing Systems (NeurIPS)
2025–2026 Area Chair, International Conference on Learning Representations (ICLR)
2024–2026 Area Chair, International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)

Selected Awards

2026 NVIDIA Academic Grant Award
2026 UWA Data Institute Early Career Researcher Award
2025 APRS Early Career Researcher Award Honorable Mention
2024 NCI National AI Flagship Scheme Grant
2024 Digital Sciences Initiative Ignite Award
2022 ICDM Best Student Paper Award