Our lab investigates the interface of theoretical physics, quantum information, and machine learning through analytical, numerical, and data-driven approaches. We develop effective theories of learning dynamics in neural networks using tools from statistical mechanics, perturbation theory, and symmetry analysis, and study complexity measures connecting information geometry and physics. In quantum field theory and string theory, we explore holography, spacetime–entanglement dualities, topological phases, and quantum chaos. On the quantum technology side, we design quantum algorithms for simulation, chemistry, and optimization, leveraging tensor networks, graph states, and photonic architectures. Our overarching goal is to formulate unified principles of complexity and information spanning deep learning, quantum matter, and spacetime.