Liangli Zhen

Senior Scientist at A*STAR

zhenll.png

Welcome to my homepage! I am a group manager and senior scientist at the Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore. I lead the Reliable AI research group to improve AI safety and robustness. Prior to joining IHPC, I received my PhD in Computer Science from Sichuan University in 2018, supervised by Professor Dezhong Peng. I was a joint PhD student at the University of Birmingham from Aug 2016 to Aug 2018, supervised by Professor Xin Yao.

My research is mainly on machine learning and optimisation. Related research topics include multimodal learning, adversarial robustness, domain generalisation, neural architecture search, foundation models, evolutionary multi-objective optimisation, and more.

News

  • [Apr 2024] We are currently offering open positions for visiting PhD students and internships in Reliable AI research.
  • [Apr 2024] Our paper on Neural Architecture Search with Progressive Evaluation and Sub-Population Preservation has been accepted by the IEEE Transactions on Evolutionary Computation.
  • [Mar 2024] Our paper on Generative Image Reconstruction from Gradients has been accepted by the IEEE Transactions on Neural Networks and Learning Systems.
  • [Jan 2024] Our paper on Geometric Correspondence-Based Multimodal Learning for Ophthalmic Image Analysis has been accepted by the IEEE Transactions on Medical Imaging.
  • [Jan 2024] Our paper on MedNAS: Multi-scale Training-free Neural Architecture Search for Medical Image Analysis has been accepted by the IEEE Transactions on Evolutionary Computation.
  • [Nov 2023] Our paper on Deep Supervised Multi-View Learning with Graph Priors has been accepted by the IEEE Transactions on Image Processing.
  • [Nov 2023] Our paper on Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing has been accepted by the IEEE Transactions on Evolutionary Computation.
  • [Jul 2023] Our project on Development of Stable, Robust and Secure Intelligent Systems for Autonomous Vehicles has been awarded the AI Singapore Robust AI Grand Challenge Funding.
  • [Jul 2023] Our paper on Generative Gradient Inversion via Over-parameterized Convolutional Networks in Federated Learning has been accepted by ICCV-2023.