Papers

2

Total Citations

26

H-Index

2

About

Tianyun Ma is a leading researcher at the intersection of edge AI and robotics, with key contributions spanning efficient large language model (LLM) deployment and multi-robot perception. His most cited work, "Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM" (2024, 17 citations), addresses the critical challenge of running billion-parameter models on resource-constrained edge devices. By proposing a chiplet-based hybrid architecture, Ma enables privacy-preserving, low-latency inference for smartphones and robotics—a breakthrough for single-batch computing scenarios where traditional cloud-dependent approaches fall short. This work has quickly gained traction, reflecting the urgent industry need for on-device AI. Earlier, Ma's foundational research on "Multi-robot collaborative SLAM and scene reconstruction based on RGB-D camera" (2020, 9 citations) tackled the slow mapping speeds of single-robot systems. He developed a centralized, multi-client framework where robots collaboratively collect RGB-D data for real-time scene reconstruction, significantly accelerating SLAM in dynamic environments. Together, these contributions establish Ma as a pioneer in bridging large-scale AI models with practical, decentralized robotic systems—a vision that continues to shape the future of intelligent edge computing.

Research Focus

Key Achievements

2
H-Index
2
Papers
26
Total Citations
13
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: 16
🏛 Institutions: University of Science and Technology Beijing, Tsinghua University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago