Thang Luong
Thang Luong is currently a Senior Staff Research Scientist at Google DeepMind, ex Google Brain. He obtained his PhD in Computer Science from Stanford University in 2016, during which he pioneered the field of deep learning for machine translation. At Google DeepMind, Dr. Luong built state-of-the-art models in both language (QANet, ELECTRA) and vision (UDA, NoisyStudent). He is a co-founder the Meena project, which debuted the world’s best chatbot in 2020 (later became Google LaMDA, Bard, now Gemini) and an inventor of LuongAttention. Dr. Luong has been co-leading the development of Bard Multimodality since 2022 and is the lead of the AlphaGeometry project that solves Olympiad geometry problems at the IMO level (Nature, 2024).
Academically, Dr. Luong has served as area chairs at ACL & NeuRIPS conferences. He has published over 50 articles at top-tiered conferences, with over 30000 citations and 20 patents. All of his publications can be found at Google Scholar. Blogposts: AlphaGeometry, self-training & Google search, conversational chatbot, semi-supervised learning, language pretraining, and neural machine translation.
Academically, Dr. Luong has served as area chairs at ACL & NeuRIPS conferences. He has published over 50 articles at top-tiered conferences, with over 30000 citations and 20 patents. All of his publications can be found at Google Scholar. Blogposts: AlphaGeometry, self-training & Google search, conversational chatbot, semi-supervised learning, language pretraining, and neural machine translation.
Authored Publications
Sort By
Google
Meta Pseudo Labels
Hieu Pham
Zihang Dai
Qizhe Xie
IEEE Conference on Computer Vision and Pattern Recognition (2021)
STraTA: Self-Training with Task Augmentation for Better Few-shot Learning
Tu Vu
Grady Simon
Mohit Iyyer
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference
Dmitry (Dima) Lepikhin
Maxim Krikun
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference (2021)
Just Pick a Sign: Reducing Gradient Conflict in Deep Networks with Gradient Sign Dropout
Drago Anguelov
Henrik Kretzschmar
Jiquan Ngiam
Yuning Chai
Zhao Chen
NeurIPS 2020 Submission (2020) (to appear)
