Hanrui (Ryan) Wang received his PhD degree from MIT advised by Song Han. His research focuses on efficient AI computing. His work has been recognized by ACM SRC 1st Place Award, Best Poster Award at NSF AI Institute, Best Paper Award at QCE, and Best Paper Award at ICML RL4RL. He is the recipient of Qualcomm Fellowship, Unitary Fund, Nvidia Fellowship Finalist, Rising Star in ML and Systems, and Rising Star in ISSCC. He is the creator of TorchQuantum library which has been adopted by IBM and PyTorch Ecosystems He received B. Eng. degree with honors from Fudan University.
Efficiency is critical for unlocking the full potential of AI. We innovate in key areas such as Transformer and LLMs (SpAtten, Hardware-Aware Transformer, Lightning-Transformer, SpAtten-Chip, SpArch), Vision (AMC, APQ), using techniques including pruning, quantization, neural architecture search, and hardware-architecture-algorithm co-design.
Quantum offers substantial speed and efficiency improvements for problems that are challenging for classical computers. We innovate in key areas of quantum compilers (Atomique, Q-Pilot), AI for Quantum Science (QuantumNAS, QuEst, QuantumNAT, QOC, SnCQA), quantum control (Pulse Learning, DISQ), and quantum error correction to accelerate the path towards practical quantum computing.
Email: hanrui@mit.edu
If you work on efficient AI Computing, Quantum Computing, GenAI and interested in working with me, please fill out the recruiting form.
