Welcome, I’m Alvin!

I build AI for healthcare and biomedical discoveries. Before my assistant professorship, I was a postdoctoral fellow at MIT Traverso lab focusing on deep learning research to make nanomedicine more accessible, more precise and more effective. If you’re driven by research that makes a difference and are excited about the intersection of AI and medicine, we should talk!

I am seeking PhD students with a passion for applying deep learning in the field of medicine.

Interests
  • Generative Models
  • Computational Biology
  • Nanomedicine
Education
  • Postdoctoral Fellowship, 2024

    Massachusetts Institute of Technology & Brigham and Women's Hospital, Harvard Medical School, USA

  • PhD in Computer Science, 2021

    Nanyang Technological University, Singapore

  • BEng in Bioengineering, 2013

    Nanyang Technological University, Singapore

Research

Deep Learning for Precision Medicine
The convergence of medicine and deep learning promises many life-changing innovations that will advance healthcare. To contribute to this cause, my research aims to synthesize insights from various domains into a unified AI platform. Unlike existing AI models that typically focus on a single modality, I focus on developing deep learning technologies that combine knowledge and modalities from a myriad of medical domains such as multi-omics, nanomedicine, and nucleic acid/protein engineering. This will be key to enhancing our understanding of human health and medicine, leading to groundbreaking discoveries in personalized healthcare.
Deep Learning for Precision Medicine
Developing Intelligent Nanomedicine with AI and High-Throughput Science
My research focuses on the synergy between deep learning and high-throughput science in developing intelligent nanomedicine. Nanomedicine, a specialized field of medicine that utilizes nanotechnology, taps on nanoparticles for disease prevention, diagnosis, and treatment. The experimental screening of all possible nanomedicine formulations is immensely challenging due to the vast array of variables involved. With novel deep learning models trained on data generated from high-throughput techniques, we can find promising formulations in-silico more quickly and efficiently. By accelerating the development cycle of nanomedicine discovery with my research, we can make medicine more accessible, safer and more effective.
Developing Intelligent Nanomedicine with AI and High-Throughput Science

Recent Publications

(2021). Self-Instantiated Recurrent Units with Dynamic Soft Recursion. NeurIPS 2021 (Thirty-Fifth Conference on Neural Information Processing Systems).

PDF Cite

(2021). On Orthogonality Constraints for Transformers. ACL 2021 (Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Volume 2: Short Papers).

Cite

(2020). Deep learning for fabrication and maturation of 3D bioprinted tissues and organs. Virtual and Physical Prototyping, Volume 15, 2020 - Issue 3.

PDF Cite

(2019). Poison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networks. arXiv:1911.08040 [cs].

PDF Cite