Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Project
Low Carbon Transformation Pathway
In order to reduce the risks and impacts of climate change, global efforts to keep the average temperature rise within 1.5 degrees Celsius are of great significance to all mankind. In this context, many countries…
Project
Fast Neural PDE Solver
Understanding many sustainability issues relates fundamentally to PDEs, from macroscope to microscope, such as navier stokes equation and Schrödinger equations. Solving these PDEs enables us to understand and forecast the world and is a critical…
Project
Learning to Decode the Immune System to Diagnose Disease
Adaptive published the original proof-of-concept for this project (Emerson, et al. Nat Genet. 2017), demonstrating that shared TCRs can be used as a basis for diagnosing viral infection. Since then, we have further demonstrated the…
Project
Learn the Dynamics
The laws of nature are described as dynamical systems. Learning dynamics, as a new AI technique, faces the following challenges: (1) the existing pure deep learning models are not that reliable in the scientific field,…
Project
Language-speech Pretraining
We are working on pre-trained language model, including new pre-training method, pre-trained model compression, pre-training for other tasks such as speech and music. Mingliang Zeng, Xu Tan, Rui Wang, Zeqian Ju, Tao Qin, Tie-Yan Liu,…
Project
Graphormer
Graphormer is a deep learning package that allows researchers and developers to train custom models for molecule modeling tasks. It aims to accelerate the research and application in AI for molecule science, such as material…
Project
Generalization in Deep Learning
Understanding the generalization of deep learning is an important but challenging problem. We establish generalization error bounds for SGD by characterizing the algorithmic stability in terms of the population risk at initialization and from information…
Project
Game Testing
As modern games keep growing both in size and complexity, it has become more challenging to ensure that all the game content is well tested. To this end, we explore to develop new and efficient…
Project
Fast Pretraining
Unsupervised language pre-training has been widely adopted by many machine learning applications. However, as the pre-training task requires no human labeling effort, a massive scale of training corpus from the Web can be used to…
Project
Drug Discovery
Drug discovery is an important area with big business and social impact. From designing a new drug until it is finally approved, it takes tens of years and billions of dollars. We would like to…