Senior Lecturer&ARC DECRA Fellow@CSE; working on Self-Improving AI, LLMs, MLLMs, Diffusion Models.

Homepage - https://donggong1.github.io/;

Google Scholar - https://scholar.google.com.au/citations?user=e2u6hRoAAAAJ.

Dr. Dong Gong is a Senior Lecturer and ARC DECRA Fellow (2023-2026) at the School of Computer Science and Engineering (CSE), The University of New South Wales (UNSW). He is also holding an adjunct position at the Australian Institute for Machine Learning (AIML) at The University of Adelaide. After obtaining a PhD degree in Dec 2018, Dong worked as a Research Fellow at the AIML until Jan 2022. He is running a research group at UNSW. His research aims to develop reliable, efficient, and practical Self-Improving AI for open-ended scenarios. He has been actively serving the research community as Area Chair or reviewers for conferences such as CVPR, NeurIPS, ICML, ICCV, ACM MM, WACV, etc, and was awarded as outstanding reviewers for NeurIPS’18 and outstanding AC for ACM MM’24.
 

His research aims to develop reliable, useful, and efficient self-improving AI across open-ended, continuously changing environments. My current major research topics are about:

• continual learning
  - forgetting mitigation in training-time learning (regularization, replay, architecture)
  - agentic & online learning with controlled/minimised forgetting
  - continual learning for LLMs and MLLMs.

• foundation model adaptation, post-training, test-time learning

• generative models
  - image and video generation

• deep learning model design, e.g.,
  - memory model & mechanism
  - (dynamic) mixture-of-experts

• high-level visual perception & low-level vision problems, e.g.,
  - semantic and depth prediction
  - image restoration and enhancement

I am continually seeking highly self-motivated PhD, MPhil, Postdoc with passion and strong background for machine learning and computer vision. Please check the details and email me your CV and transcripts if you are interested.