Thái Hoàng Lê
Computer Science · Indiana University
Publications
165
Citations
1,210
Est. group size
—
Recurring co-author estimate
Active years
35
Publishing since 1992
Thái Hoàng Lê works across two connected areas: machine learning applications (including natural language processing, medical image analysis, and privacy-focused techniques such as machine unlearning and facial recognition) and pure mathematics related to number theory. The applied work spans large language model question-answering systems, lung nodule segmentation in CT scans, and explainable AI, while the mathematical work explores topics like equidistribution of sequences and additive bases.
Publication activity has grown steadily over the last decade, rising from a handful of papers per year to around 13-16 in recent years.
Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026
- Topological Data Analysis Applications in Natural Language Processing: A Survey
ACM SIGKDD Explorations Newsletter · 2026
- Natural Language Processing Methods for the Study of Protein–Ligand Interactions
Journal of Chemical Information and Modeling · 2025
- CAAF-ResUNet: Adaptive Attention Fusion with Boundary-Aware Loss for Lung Nodule Segmentation
Medicina · 2025
- ResUNet Model Enhanced with Multiple Attention Mechanisms for Effective Pulmonary Nodule Segmentation in CT Images
VNU Journal of Science Computer Science and Communication Engineering · 2025
- Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI
arXiv (Cornell University) · 2025
- PIU-FR: Personal Identity Unlearning for Facial Recognition
Communications in computer and information science · 2025
- Equidistribution of polynomial sequences in function fields, with applications
Advances in Mathematics · 2025
- AcaQAS: An Academic Question Answering System Based on Finetuning Large Language Models
SN Computer Science · 2025
- On the order of additive bases in finite abelian groups
Involve a Journal of Mathematics · 2025
- Improving Lung Nodule Segmentation in CT Scans with a Learnable PDE-Based Diffusion Block
Frontiers in artificial intelligence and applications · 2025
- Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification
arXiv (Cornell University) · 2025
- Well-distribution modulo one and the primes
Proceedings of the American Mathematical Society · 2025
- WSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification
Lecture notes in computer science · 2025
- Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models
2025
- Evaluating the SISA Framework for Efficient Machine Unlearning in Face Recognition Models
Communications in computer and information science · 2025
- arXiv (Cornell University)×17
- Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering×9
- Communications in computer and information science×4
- Indian Journal of Science and Technology×3
- EAI Endorsed Transactions on Context-aware Systems and Applications×2
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 11, 2026.
Claim or correct this profile