How to Create a Mind
Our research aims to develop general-purpose artificial agent that can solve the difficult problems of humanity, similar to human intelligence. We aim to achieve this by creating learning algorithms that are fundamental to perception, cognition, and action. We hope that this computational approach will also provide insights into the inner workings of the human mind.
We are particularly interested in learning world models, representations, high-level cognition mechanisms, and policies that can be self-supervised, structured, and systematically generalized. This endeavor may involve exploring causality, compositionality, as well as temporal and hierarchical structures. Some examples of currently active projects are:
Unsupervised Structured Representation for High-Level Cognition
Visual Reasoning & Abstraction & Systematic Generalization
World Models for Model-Based Reinforcement Learning
LLM-Augmented MBRL Agent and General Goal-Achieving LLM Agent
We tackle this problem using the tools of deep learning, reinforcement learning, and probabilistic learning.
To create AI that can be brain-inspired, we also strive to understand the learning algorithms of the brain, drawing insights from cognitive science and neuroscience.
We are interested in applying these algorithms to Agent Learning applications such as
Robot Learning Agents
LLM Agents
Game AI Agents
as well as making them aligned with human values.
Please feel free to contact us if you’re enthusiastic about joining us on this exciting journey.