Thanh-Tung Le

PhD, until 2026, now Senior Deep Learning Engineer at NVIDIA

Advised by Xiaohui Xie

Personal homepage

Publications

Towards Efficient Deep Learning for 3D Geometric Understanding and Generation

Thanh-Tung Le

PhD Thesis, University of California, Irvine, 2026.

Abstract PDF
GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation

Tuan Pham, Thanh-Tung Le, Xiaohui Xie, Stephan Mandt

ICCVW, 6357-6367, 2025.

Abstract PDF arXiv DOI
UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis

Thanh-Tung Le, Tuan Pham, Tung Nguyen, Deying Kong, Xiaohui Xie, Stephan Mandt

NeurIPS, 2025.

Abstract PDF
AFTer-SAM: Adapting SAM with Axial Fusion Transformer for Medical Imaging Segmentation

Xiangyi Yan, Shanlin Sun, Kun Han, Thanh-Tung Le, Haoyu Ma, Chenyu You, Xiaohui Xie

WACV, 7960-7969, 2024.

Abstract WACV DOI
Hybrid Neural Diffeomorphic Flow for Shape Representation and Generation via Triplane

Kun Han, Shanlin Sun, Thanh-Tung Le, Xiangyi Yan, Haoyu Ma, Chenyu You, Xiaohui Xie

WACV, 7692-7702, 2024.

Abstract PDF WACV arXiv DOI
Hybrid-CSR: Coupling Explicit and Implicit Reconstruction of Cortical Surface

Shanlin Sun, Tung Le, Pooya Khosravi, Chenyu You, Kun Han, Haoyu Ma, Deying Kong, Xiangyi Yan, Xiaohui Xie

BMVC, 2024.

Abstract BMVC
Integrating Efficient Optimal Transport and Functional Maps for Unsupervised Shape Correspondence Learning

Tung Le, Khai Nguyen, Shanlin Sun, Nhat Ho, Xiaohui Xie

CVPR, 23188-23198, 2024.

Abstract CVPR DOI