Papers
1
Total Citations
38
H-Index
1
About
Yupeng Su is a researcher at the forefront of efficient artificial intelligence, with a primary focus on deploying large language models (LLMs) on resource-constrained edge devices. His work addresses a critical challenge in modern AI: enabling powerful models to run on hardware-limited platforms such as robots and mobile systems without sacrificing performance. Su’s most-cited paper, "EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models" (2025), has already garnered 38 citations, reflecting its timely impact on the field. This work introduces a novel heterogeneous computing architecture that leverages both CPU and FPGA resources to dramatically reduce the computational and energy demands of LLM inference at the edge. By tackling the intensive computational requirements of LLMs, Su’s contributions pave the way for practical, real-world applications of advanced AI in autonomous systems and IoT devices. His research stands out for its focus on hardware-software co-design, bridging the gap between cutting-edge AI capabilities and the physical constraints of edge computing. For students and researchers interested in the intersection of AI, hardware acceleration, and edge deployment, Su’s work offers a compelling blueprint for the future of efficient, on-device intelligence.
Research Focus
Key Achievements
Top Papers
- 1