Max Robotics — Global Service Robot Directory + US Certification

About

Zidong Du is a leading researcher in computer architecture and hardware acceleration, with a core focus on neuromorphic computing, efficient AI inference, and edge intelligence. His seminal 2015 work on neuromorphic accelerators (84 citations) laid foundational insights into specialized hardware for processing real-world data—from industrial robotics to autonomous vehicles—establishing him as a key voice in the resurgence of neural network accelerators. More recently, Du has tackled the monumental challenge of deploying large language models on resource-constrained devices. His 2024 paper on Cambricon-LLM (17 citations) introduces a chiplet-based hybrid architecture that enables on-device inference of 70-billion-parameter LLMs, addressing the critical need for privacy-preserving, low-latency AI on smartphones and robotics. This work demonstrates his ability to bridge cutting-edge AI demands with practical hardware solutions. Du’s research also extends to hardware acceleration for SLAM in mobile systems (2023), showcasing his versatility in real-time spatial computing. With a career defined by pioneering contributions to efficient, deployable AI hardware, Zidong Du continues to shape the future of intelligent edge systems.