Overview
Background
Dr. Jiajun Liu is Principal Research Scientist and Science Leader for the Distributed Sensing Systems Group (DSSG) at the CSIRO, and leads the Distributed Intelligence team in the DSSG. He is also an Adjunct Associate Professor@UQ. He received his PhD/BEng from the University of Queensland, Australia, and Nanjing University, China, in 2013 and 2006, respectively.
His research interest covers a range of topics in Machine Learning and Data Science, including efficient neural nets, graph learning, and multimedia/multimodal analytics. At CSIRO he is looking into how to make sensing systems more intelligent and efficient, by developing knowledge distillation and efficient neural architectures to enable efficient AI models on edge devices and distributed sensing applications.
He also serves as a reviewer/TPC member/Area Chair for numerous international journals and conferences, such as IEEE Transactions on Knowledge and Data Engineering, The VLDB Journal, IEEE Transactions on Multimedia, IEEE Transactions on Big Data, Clustering Computing, Ad Hoc Networks, Neurocomputing, Multimedia Systems, ACM Multimedia Conference 14' 21', CIKM 21', PAKDD 17~20', APWeb 16', etc.
Availability
- Associate Professor Jiajun Liu is:
- Available for supervision
Works
Search Professor Jiajun Liu’s works on UQ eSpace
2026
Journal Article
On learning denoisable student logits
Chen, Diqi, Li, Yang, Liu, Jiajun, Kusy, Brano, Zhou, Jun and Gao, Yongsheng (2026). On learning denoisable student logits. Pattern Recognition, 179 113684, 113684-179. doi: 10.1016/j.patcog.2026.113684
2026
Journal Article
Video-Seer: a hierarchical scene selection and multi-view analysis approach for zero-shot video question answering
Huang, Chenglei, Zhu, Jia, Li, Zilong, Guo, Hanghui, Liu, Jiajun, De Meo, Pasquale and Shi, Weijie (2026). Video-Seer: a hierarchical scene selection and multi-view analysis approach for zero-shot video question answering. IEEE Transactions on Multimedia. doi: 10.1109/TMM.2026.3673555
2026
Journal Article
Seagrass species classification using random forest and U-Net models on multiple satellite images taken at various times and places
Thammasanya, Thunchanok, Chotikarn, Ponlachart, Liu, Jiajun, Kaewthongrach, Rungnapa, Moukomla, Sitthisak, Pongpiachan, Siwatt, Aobpaet, Anuphao, Vannametee, Ekkamol, Niammuad, Damrongrit, Charuchittipan, Doojdao, Choomkong, Apichat, Chidburee, Polpreecha, Chanket, Urawan, Bamroongrugsa, Noparat, Somboonsuke, Buncha and Sinutok, Sutinee (2026). Seagrass species classification using random forest and U-Net models on multiple satellite images taken at various times and places. International Journal of Remote Sensing, 1-20. doi: 10.1080/01431161.2026.2636792
2026
Journal Article
DFedDG2: Distribution Guided Gossip Based Generalizable and Communication Efficient Decentralized Federated Learning
Pal, Biprodip, Funiak, Stano, Liu, Jiajun, Moghadam, Peyman, Islam, Md. Saiful and Liew, Alan Wee-Chung (2026). DFedDG2: Distribution Guided Gossip Based Generalizable and Communication Efficient Decentralized Federated Learning. IEEE Internet of Things Journal, 1-1. doi: 10.1109/jiot.2026.3667408
2026
Journal Article
Understanding the Effects of Projectors in Knowledge Distillation
Chen, Yudong, Wang, Sen, Liu, Jiajun, Xu, Xuwei, Hoog, Frank de, Kusy, Brano and Huang, Zi (2026). Understanding the Effects of Projectors in Knowledge Distillation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-16. doi: 10.1109/tpami.2026.3677028
2025
Conference Publication
MARCO: a cooperative knowledge transfer framework for personalized cross-domain recommendations
Xie, Lili, Zhang, Yi, Qiu, Ruihong, Liu, Jiajun and Wang, Sen (2025). MARCO: a cooperative knowledge transfer framework for personalized cross-domain recommendations. 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, Xi'an, China, 7-10 December 2025. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3767695.3769481
2025
Conference Publication
OmniRestore: robust universal image restoration from combined and unspecified degradations
Karnavar, Anjusree, Li, Yang, Liu, Jiajun, Zhou, Jun and Wang, Junhu (2025). OmniRestore: robust universal image restoration from combined and unspecified degradations. 2025 IEEE International Conference on Multimedia and Expo (ICME), Nantes, France, 30 October 2025. New York, NY United States: IEEE Computer Society. doi: 10.1109/ICME59968.2025.11209899
2025
Conference Publication
Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning
Li, Xun, Santa Cruz, Rodrigo, Xi, Mingze, Zhang, Hu, Perera, Madhawa, Wang, Ziwei, Ravendran, Ahalya, Matthews, Brandon J., Xu, Feng, Adcock, Matt, Wang, Dadong and Liu, Jiajun (2025). Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning. New York, NY, USA: ACM. doi: 10.1145/3746027.3758177
2025
Conference Publication
RePaViT: scalable vision transformer acceleration via structural reparameterization on feedforward network layers
Xu, Xuwei, Li, Yang, Chen, Yudong, Liu, Jiajun and Wang, Sen (2025). RePaViT: scalable vision transformer acceleration via structural reparameterization on feedforward network layers. International Conference on Machine Learning, Vancouver, Canada, 13-19 July 2025. San Diego, CA, United States: ICML.
2025
Journal Article
SATE: efficient knowledge distillation with implicit student-aware teacher ensembles
Chen, Diqi, Li, Yang, Liu, Jiajun, Zhou, Jun and Gao, Yongsheng (2025). SATE: efficient knowledge distillation with implicit student-aware teacher ensembles. Pattern Recognition, 172 112355, 112355. doi: 10.1016/j.patcog.2025.112355
2025
Conference Publication
DARLR: Dual-agent offline reinforcement learning for recommender systems with dynamic reward
Zhang, Yi, Qiu, Ruihong, Xu, Xuwei, Liu, Jiajun and Wang, Sen (2025). DARLR: Dual-agent offline reinforcement learning for recommender systems with dynamic reward. 48th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (ACM SIGIR 2025), Padua, Italy, 13-18 July 2025. New York, NY, United States: Association for Computing Machinery. doi: 10.1145/3726302.3729942
2025
Conference Publication
Building efficient segmentation models from large open-vocabulary foundation models without any labels
Li, Yang, Chen, Diqi, Wang, Sen, Kusy, Brano and Liu, Jiajun (2025). Building efficient segmentation models from large open-vocabulary foundation models without any labels. 2025 International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 30 June-5 July 2025. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/ijcnn64981.2025.11228002
2025
Conference Publication
On-the-fly object-aware representative point selection in point cloud
Zhang, Xiaoyu, Wang, Ziwei, Dong, Hai, Bao, Zhifeng and Liu, Jiajun (2025). On-the-fly object-aware representative point selection in point cloud. 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, United States, 26 February-6 March 2025. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/wacv61041.2025.00174
2025
Conference Publication
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
Zhang, Bingqing, Cao, Zhuo, Du, Heming, Yu, Xin, Li, Xue, Liu, Jiajun and Wang, Sen (2025). TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm. 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ United States, 26 February - 6 March 2025. Piscataway, NJ United States: IEEE. doi: 10.1109/wacv61041.2025.00485
2025
Conference Publication
Beyond static LLM policies: imitation-enhanced reinforcement learning for recommendation
Zhang, Yi, Xie, Lili, Qiu, Ruihong, Liu, Jiajun and Wang, Sen (2025). Beyond static LLM policies: imitation-enhanced reinforcement learning for recommendation. 2025 IEEE International Conference on Data Mining (ICDM), Washington, DC, United States, 12-15 November 2025. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/ICDM65498.2025.00098
2025
Conference Publication
Effective tuning strategies for generalist robot manipulation policies
Zhang, Wenbo, Li, Yang, Qiao, Yanyuan, Huang, Siyuan, Liu, Jiajun, Dayoub, Feras, Ma, Xiao and Liu, Lingqiao (2025). Effective tuning strategies for generalist robot manipulation policies. 2025 International Conference on Robotics and Automation (ICRA), Atlanta, GA, United States, 19 - 23 May 2025. Washington, DC, United States: I E E E Computer Society. doi: 10.1109/ICRA55743.2025.11127492
2025
Conference Publication
LLM as copilot for coarse-grained vision-and-language navigation
Qiao, Yanyuan, Liu, Qianyi, Liu, Jiajun, Liu, Jing and Wu, Qi (2025). LLM as copilot for coarse-grained vision-and-language navigation. Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part V, Milan, Italy, 29 September – 4 October 2024. Heidelberg, Germany: Springer. doi: 10.1007/978-3-031-72652-1_27
2024
Journal Article
Optimized Edge Node Allocation Considering User Delay Tolerance for Cost Reduction
Zhang, Xiaoyu, Huang, Shixun, Dong, Hai, Bao, Zhifeng, Liu, Jiajun and Yi, Xun (2024). Optimized Edge Node Allocation Considering User Delay Tolerance for Cost Reduction. IEEE Transactions on Services Computing, 17 (6), 4055-4068. doi: 10.1109/tsc.2024.3486174
2024
Conference Publication
BuildingSage: a safe and secure AI copilot for smart buildings
Dedeoglu, Volkan, Zhang, Qianggong, Li, Yang, Liu, Jiajun and Sethuvenkatraman, Subbu (2024). BuildingSage: a safe and secure AI copilot for smart buildings. BuildSys '24: The 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, Hangzhou, China, 7-8 November 2024. New York, United States: BuildSys 2024 - Proceedings of the 2024 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. doi: 10.1145/3671127.3699677
2024
Conference Publication
Navigating beyond instructions: vision-and-language navigation in obstructed environments
Hong, Haodong, Wang, Sen, Huang, Zi, Wu, Qi and Liu, Jiajun (2024). Navigating beyond instructions: vision-and-language navigation in obstructed environments. MM '24: The 32nd ACM International Conference on Multimedia, Melbourne, VIC, Australia, 28 October-1 November 2024. New York, United States: Association for Computing Machinery. doi: 10.1145/3664647.3681640
Supervision
Availability
- Associate Professor Jiajun Liu is:
- Available for supervision
Looking for a supervisor? Read our advice on how to choose a supervisor.
Supervision history
Current supervision
-
Doctor Philosophy
Short Sequence Representation Learning with Limited Supervision
Associate Advisor
Other advisors: Professor Xue Li, Associate Professor Sen Wang
-
Doctor Philosophy
Towards Intelligent and Generalisable Agents for Vision-and-Language Navigation
Associate Advisor
Other advisors: Associate Professor Sen Wang
Completed supervision
-
2026
Doctor Philosophy
Adaptive Reinforcement Learning for Practical Decision Making
Associate Advisor
Other advisors: Dr Ruihong Qiu, Associate Professor Sen Wang
-
2025
Doctor Philosophy
Information-Preserving Efficient Vision Transformers
Associate Advisor
Other advisors: Associate Professor Sen Wang
-
2025
Doctor Philosophy
Simplifying Representations, Models, and Datasets for Efficient Visual Learning
Associate Advisor
Other advisors: Associate Professor Sen Wang
Media
Enquiries
For media enquiries about Associate Professor Jiajun Liu's areas of expertise, story ideas and help finding experts, contact our Media team: