This is the personal webpage of Tuan ([tʰwɑ̃n], fullname: Tuan Q. Dinh). I am currently a postdoc fellow working on foundation models and their development for scientific discovery, especially for proteins and human genetics. I am jointly supervised by Prof. Vasilis Ntranos at UCSF and the Data Sciences group at Maze Therapeutics.
Research interests: AI/ML and AI4Science, with the current focus being modular deep learning for computational biology.
When time rushes by, I read/translate poems, seeking the ones that speak to me, e.g.,
I chase the mist where whispers lie, The wise take wing beneath the sky.
Education: Tuan obtained Ph.D. in Computer Sciences (minor in Statistics) with Prof. Kangwook Lee, studying modular neural networks built on pre-trained models. Previously, Tuan completed the M.S. with Prof. Vikas Singh and the B.E. with Prof. Tru Cao, working on AI systems for disease forecast and healthcare.
ICML'25 (Spotlight) | LLM | TabFlex: Scaling Tabular Learning to Millions with Linear Attention | summary | code |
NeurIPS'23 | LLM | Large Language Models of Code Fail at Completing Code with Potential Bugs | summary | code |
EMNLP'22 (Findings) | Multimodal | Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment | summary | code |
NeurIPS'22 | LLM | LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks | summary | code |
ICMLW'22 | GAN, PEFT | Improved Input Reprogramming for GAN Conditioning | summary | code |
ICML'21 (Oral) | MLSys, GAN | Coded-InvNet for Resilient Prediction Serving Systems | summary | code |
TPAMI'20 | GAN, Medical Imaging | Performing Group Difference Testing on Graph Structured Data from GANs: Analysis and Applications in Neuroimaging | code | |
AAAI'20 (Oral) | Optimization, GAN | The Promise of Conditional Gradient Methods for Training Deep Models | code |
MobiCom'22 | Healthcare | PROS: an Efficient Pattern-Driven Compressive Sensing Framework for Low-Power Biopotentialbased Wearables with On-chip Intelligence | summary | code |
MobiSys'21 | Healthcare | WAKE: A Behind-the-ear Wearable System for Microsleep Detection | summary | code |
IEEE TMC'21 | Healthcare | Detection of Microsleep Events with a Behind-the-ear Wearable System | ||
Oxford Journal'18 | Epidemiology | Forecasting Dengue Incidences: Statistical and Dynamic Models | ||
CtaD'17 | Medical Imaging | Graph Imputation techniques for estimating amyloid positivity from longitudinal cognitive and MRI measurements for efficient secondary prevention trials | ||
ACIIDS'16 (Oral) | Epidemiology | Forecasting the Magnitude of Dengue in Southern Vietnam |
US 11087525 | AI Framework, Inverse Graphics | Unsupervised learning of three dimensional visual alphabet |
US 16186121 | Algorithm, Training Framework | Training System for Artificial Neural Networks Having a Global Weight Constrainer |