Xinkai Wang
Papers
1
Total Citations
3
H-Index
1
About
Xinkai Wang is a rising researcher at the forefront of autonomous micromobility systems (AMS), specializing in the efficient deployment of deep neural networks on heterogeneous AI accelerators. His most notable contribution is the introduction of Accelerator Level Parallelism (ALP), a paradigm that treats multiple accelerators as a unified resource pool rather than isolated components. In his seminal 2024 paper, Wang demonstrates how ALP can dramatically improve throughput and latency for low-speed autonomous vehicles like minicabs and delivery robots, addressing a critical bottleneck in real-world edge-AI deployment. Though early in his career, his work has already garnered attention (3 citations) for its practical implications in making autonomous systems more responsive and energy-efficient. By shifting focus from individual accelerator optimization to holistic resource management, Wang is helping pave the way for scalable, cost-effective autonomous micromobility—a key enabler for smart cities and last-mile logistics. His research sits at the intersection of systems architecture, real-time AI, and embedded computing, promising to shape how future autonomous fleets operate.
Research Focus
Key Achievements
Top Papers
- 1