Xiaofeng Hou
Papers
1
Total Citations
3
H-Index
1
About
Xiaofeng Hou is a rising researcher at the forefront of autonomous micromobility systems (AMS) and heterogeneous AI acceleration. His work addresses the critical challenge of managing multiple deep neural networks running in parallel on diverse AI accelerators within low-speed minicabs and robots. Hou’s most-cited paper, “A²: Towards Accelerator Level Parallelism for Autonomous Micromobility Systems” (2024, 3 citations), introduces the paradigm of Accelerator Level Parallelism (ALP), which advocates for holistic management of accelerators to improve efficiency and performance. This contribution is foundational for the next generation of autonomous systems, where real-time, low-latency processing is essential. Though early in his career, Hou’s focus on ALP positions him as a key innovator in optimizing edge AI hardware for safety-critical, resource-constrained environments. His work bridges the gap between theoretical parallelism and practical deployment, promising to shape how autonomous micromobility systems handle complex, concurrent AI workloads. With a clear trajectory toward scalable, efficient AI acceleration, Hou is a researcher to watch in the evolving landscape of autonomous systems and embedded AI.
Research Focus
Key Achievements
Top Papers
- 1