• Multi-modal Understanding and Generation 

      Wang, Zhaoqing
      Published 2026
      The convergence of computer vision and natural language processing has been accelerated by large-scale pre-training, enabling machines to align visual concepts with semantic meaning. However, a gap remains between the ...
      Open Access
      Thesis
    • Robust and Efficient Training of Deep Neural Networks via Principled Stopping Strategies 

      Yuan, Suqin
      Published 2026
      In many modern regimes, deep neural networks can overfit the training data while still generalizing well, which has enabled large-scale training and motivated neural scaling law. Nevertheless, benign overfitting is not ...
      Open Access
      Thesis
    • Opioid Deprescribing at Transitions of Care in Australia 

      Wang, Jeffery
      Published 2026
      Opioid analgesics are widely used for acute, chronic, and perioperative pain, but long-term use has contributed to increased misuse, dependence, and opioid-related harm. Transitions of care, particularly from hospital to ...
      Open Access
      Thesis
    • Towards High Efficient Federated Learning Systems 

      Pei, Jiaming
      Published 2026
      Federated learning (FL) has shown strong potential in domains such as Intelligent Transportation Systems (ITS), Internet of Things (IoT), and industrial cyber–physical systems (ICPS). However, FL faces three fundamental ...
      Open Access
      Thesis
    • Optimizing the Use of Heterogeneous Memory 

      Wu, Xiaoxiang
      Published 2026
      Chapter 2 studies persistent key-value stores and isolate the impact of individual design techniques within a unified code base. Unlike prior works that evaluate complete systems, our methodology enables an apples-to-apples ...
      Open Access
      Thesis