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
Top Papers
- 1
- 2