CV

Education

University of California, Los Angeles (UCLA) | 2021-Present
Ph.D. in Computer Science

• Advisor: Aditya Grover
• GPA: 3.89/4.00

Hanoi University of Science and Technology (HUST) | 2015-2020
Bachelor in Information Systems

• Thesis: Predictive Coding for Locally-Linear Control
• Thesis advisor: Khoat Than
• GPA: 3.65/4.00, graduated with Excellent Degree

Research experience

Student Researcher | 2024
Google Deepmind

• Mentor: Xingyou (Richard) Song
• Research Topic: Universal Regression-Guided Search via LLM Embeddings

Research Intern | 2022
Microsoft Research, Autonomous Systems and Robotics Group

• Mentor: Jayesh Gupta, Ashish Kapoor
• Research Topic: General-purpose Pretraining for Climate Modeling

AI Resident | 2019 - 2021
VinAI Research, Vietnam - website: www.vinai.io

• Supervisor: Hung Bui
• Research Topic: Representation Learning for Planning in Latent Space

Research Student | 2018 - 2019
Data Science Lab (DSLab), HUST - website: ds.soict.hust.edu.vn/

• Supervisor: Khoat Than
• Research Topic: Life-long Learning for Statistical Models

Publications

Probing the Decision Boundaries of In-context Learning in LLMs
Siyan Zhao, Tung Nguyen, Aditya Grover
Conference on Neural Information Processing Systems (NeurIPS 2024)

ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
Juan Nathaniel, Yongquan Qu, Tung Nguyen, Sungduk Yu, Julius Busecke, Aditya Grover, Pierre Gentine
Conference on Neural Information Processing Systems (NeurIPS 2024)

Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
Tung Nguyen, Rohan Shah, Hritik Bansal, Troy Arcomano, Sandeep Madireddy, Romit Maulik, Veerabhadra Kotamarthi, Ian Foster, Aditya Grover
Conference on Neural Information Processing Systems (NeurIPS 2024)
Best Paper Award, Tackling Climate Change with Machine Learning Workshop, ICLR 2024.

ExPT: Synthetic Pretraining for Few-Shot Experimental Design
Tung Nguyen, Sudhanshu Agrawal, Aditya Grover
Conference on Neural Information Processing Systems (NeurIPS 2023)

ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling
Tung Nguyen, Jason Kyle Jewik, Hritik Bansal, Prakhar Sharma, Aditya Grover
Conference on Neural Information Processing Systems (NeurIPS 2023)

ClimaX: A Foundation Model for Weather and Climate
Tung Nguyen, Johannes Brandstetter, Ashish Kapoor, Jayesh K. Gupta*, Aditya Grover*
International Conference on Machine Learning (ICML 2023) Best Paper at ICML Workshop on Synergy of Scientific and Machine Learning Modeling, Spotlight Oral at ICLR Workshop on AI and Climate Change.

Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
Tung Nguyen, Aditya Grover
International Conference on Machine Learning (ICML 2022)

Temporal Predictive Coding for Model-based Planning in Latent Space
Tung Nguyen*, Rui Shu*, Tuan Pham*, Hung H. Bui, Stefano Ermon
International Conference on Machine Learning (ICML 2021)

Predictive Coding for Locally-Linear Control
Rui Shu*, Tung Nguyen*, Yinlam Chow, Tuan Pham, Khoat Than, Mohammad Ghavamzadeh, Stefano Ermon, Hung H. Bui
International Conference on Machine Learning (ICML 2020)

Infinite Dropout for training Bayesian models from data streams
Son Nguyen, Tung Nguyen, Linh Ngo, Khoat Than
IEEE International Conference on Big Data (Big Data 2019)

Under Review

Predict from Strings: Language Model Embeddings for Bayesian Optimization | 2024
Tung Nguyen, Qiuyi Zhang, Bangding Yang, Chansoo Lee, Jorg Bornschein, Sagi Perel, Yutian Chen, Xingyou Song

LICO: Large Language Models for In-Context Molecular Optimization | 2024
Tung Nguyen, Aditya Grover

AtmosArena: Benchmarking Foundation Models for Atmospheric Sciences | 2024
Tung Nguyen, Prateik Sinha, Advit Deepak, Karen A. McKinnon, Aditya Grover

ClimDetect: A Benchmark Dataset for Climate Change Detection and Attribution | 2024
Sungduk Yu, Brian L. White, Anahita Bhiwandiwalla, Musashi Hinck, Matthew Lyle Olson, Tung Nguyen, Vasudev Lal

Projects

Representation Learning for Locally-Linear Control | 2020

• Get familiar with the literature of Learning Controllable Embedding – an approach to the problem of control from high-dimensional observations
• Replicate the results of Prediction, Consistency, Curvature (PCC) – the contemporary state-of-the-art method
• Open the source code: github.com/VinAIResearch/PCC-pytorch

Honors and Awards

Outstanding Graduate Student Research Award | 2024
Department of Computer Science, UCLA
4 graduate students from the Department of Computer Science are selected each year as winners of the Outstanding Graduate Student Research Award.

Amazon Student Doctoral Fellowship | 2022-2023
Department of Computer Science, UCLA
Each year 12 doctoral students who work in the field of AI are selected as Amazon fellows. Amazon fellows receive full funding for one academic year to pursue independent research projects.

Best Thesis Award | 2020
School of Information and Communication Technology, HUST
The best thesis was selected among over 400 graduation theses in the Fall Semester, 2020.

Academic Services

Reviewer
ICML (2021, 2022, 2023, 2024), Neurips (2021, 2022, 2024), ICLR (2022, 2024, 2025)

Technical Talk AGU Annual Meeting 2023 – website: https://www.agu.org/fall-meeting

• Present ClimaX at AGU23 - the largest gathering of Earth and space scientists with 25,000+ attendees from 100+ countries annually.

Teaching Assistant
CS261 Deep Generative Models – UCLA

• Hold discussion sections and office hours

Teaching Assistant
CS161 Fundamentals of Artificial Intelligence – UCLA

• Hold discussion sections and office hours