Yifan Hao

Institute of Computing Technology

Papers

1

Total Citations

17

H-Index

1

About

Yifan Hao is a leading researcher in efficient AI hardware and on-device machine learning, with a focus on bridging the gap between massive language models and resource-constrained edge devices. His most notable contribution is the Cambricon-LLM architecture, a chiplet-based hybrid design that enables the deployment of 70-billion-parameter large language models on devices like smartphones and robots. This work addresses the critical challenge of single-batch inference with extremely low arithmetic intensity, achieving practical on-device intelligence without sacrificing user privacy or network resilience. Hao’s research has already garnered significant attention, with his flagship 2024 paper accumulating 17 citations shortly after publication, reflecting its immediate impact on the field. By pioneering hardware-software co-design for LLM inference, Hao is shaping the future of distributed AI, where powerful models operate locally rather than relying on cloud servers. His work stands at the intersection of computer architecture, chiplet integration, and edge computing, offering a scalable path toward private, low-latency AI applications.

Research Focus

Key Achievements

1
H-Index
1
Papers
17
Total Citations
17
Avg Citations/Paper
🏆 Most Cited Paper
Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM
17 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 14
🏛 Institutions: Institute of Computing Technology

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago