Reinforcement Learning agent and a configurator that can modify some environmental parameters to improve the agent's performance.

We show that any (possibly non-private) learning rule can be effectively transformed to a private learning rule with only a polynomial overhead in the mistake bound.

Currently, two mainstream GNN-based methods have been developed for constructing force fields: group theory-based methods and direction-based methods.

Lack of samples per minute or per hour (metrics 1 and 2) are helping to understand 4G networking issues.

We present an alternative approach to decompose non-negative tensors, called many-body approximation .

Part of this work was done during Kang Xu's internship at Shanghai Artificial Intelligence Laboratory.

What is your research area? My research topic, at a high level, hasn't changed much since my dissertation. It has always been the problem of physical scene understanding - building machines that see, reason about, and interact with the physical world. Besides learning algorithms, what are the levels of abstraction needed by Al systems in their representations, and where do they come from? I aim to answer these fundamental questions, drawing inspiration from nature, i.e., the physical world itself, and from human cognition.