News
-
September 26, 2024
Two papers will be presented at NeurIPS 2024. Congrats to Yiran Zhao, Yuxi Xie and other collaborators!
Accelerating greedy coordinate gradient via probe sampling
Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning (Workshop) -
September 20, 2024
Two papers will be presented at EMNLP 2024. Congrats to Esther Gan, Yiran Zhao, Hongfu Liu, Yuxi Xie and other collaborators!
Reasoning Robustness of LLMs to Adversarial Typographical Errors
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models -
May 15, 2024
Two papers will be presented at ACL 2024. Congrats to Kaixin Li, Qisheng Hu, Xuan Long Do, Yiran Zhao, Hannah Brown and other collaborators!
Prompt Optimization via Adversarial In-Context Learning (Oral)
Instructcoder: Instruction tuning large language models for code editing (Workshop)
Featured Research
Beam Search for Reasoning
A framework of stepwise self-evaluation LLM reasoning. A concurrent work with Tree of Thoughts.
Noisy Student
The first method that uses extra unlabeled data to achieve state-of-the-art on ImageNet. Also employed in AlphaFold 2 (Nobel Prize 2024), Google Search and other state-of-the-art AI systems.
Mission
Feel the AGI. Use 10k GPUs like rich kids in the industry. Get 100k citations. Get Nobel prizes and Turing awards.
Just kidding haha. We work on democratizing AI in aspects including but not limited to resource-efficient AI, vision language models and more exploratory topics.
People
Faculty
Michael Qizhe Shieh
Assistant Professor
Jinjie Ni
Postdoc
PhD Students
Hannah Brown
Co-advised with Kenji Kawaguchi
Esther Gan
Co-advised with Min-Yen Kan
Yiran Zhao
Affiliated Member
Masters Students
Fengtao He
National University of Singapore
Leon Lin
National University of Singapore
Undergraduate Students
Qilong Feng
National University of Singapore
Zhennan Shen
Shanghai Jiao Tong University
Yang Zhang
Peking University
Publications
*: equal contribution, †: equal advising
