Songchen MA

Songchen MA

Ph.D. in Instrumentation Science and Technology, Tsinghua University

Songchen MA (马松辰)

Research Assistant Professor

The Hong Kong University of Science and Technology (HKUST)

Dr. Songchen Ma is currently a Research Assistant Professor in the Department of Electronic and Computer Engineering at The Hong Kong University of Science and Technology (HKUST). He received his B.E. degree from Jilin University in 2019 and his Ph.D. degree in Instrument Science and Technology from Tsinghua University in 2024, under the supervision of Prof. Luping Shi and Prof. Rong Zhao. He was a Postdoctoral Fellow at the AI Chip Center for Emerging Smart Systems (ACCESS) under InnoHK from 2024 to 2026, working with Prof. Kwang-Ting Cheng. Dr. Ma’s research focuses on scalable brain-inspired computing architecture, AI chip design, and embodied AI systems. He developed the world’s first brain-inspired computing chip for multi-task robots, TianjicX, which was awarded the Chip10 Science Award in 2022 and the “NSK Sino-Japan Friendship Outstanding Paper Prize”. His Ph.D. dissertation was recognized by the Tsinghua Excellent Dissertation Award in 2024. His work has also been highlighted by AAAS News and selected as a Research Highlight in Nature Electronics. His research has been published in top-tier journals and conferences, including two papers in Science Robotics (one as cover feature and the other highlighted by AAAS News), as well as publications in Nature Electronics, Nature Communications, IEEE Transactions on Computers, ISCA, ISSCC, CICC, ICML and ICCAD.

Research Interests

Intelligent robotics systems, Brain-inspired and neuromorphic computing chip, Scalable AI chip architecture.

Professional Experience

  • Research Assistant Professor, Department of Electronic and Computer Engineering @ HKUST, 2026.09–present
    • Research focus: scalable AI chip/system architecture and computing hardware for intelligent robotics.
  • Post-doctoral Fellow, ACCESS @ HKUST, 2024.09–2026.09
    • Sponsored by Hong Kong RTH‑I.T.F
    • Collaborating Advisor: Prof. Kwang-Ting (Tim) Cheng

Education Experience

  • Ph.D., Instrument Science & Technology, Tsinghua University, 2019.09–2024.06
    • Center for Brain Inspired Computing Research;
    • Research on intelligent chip architecture and computing hardware for robotics.
  • B.Eng., Pilot Program in Engineering, Jilin University, 2015.08–2019.07
    • College of Instrumentation & Electrical Engineering.

Selected Publications

  • Ma, S., et al. (2022). Neuromorphic Computing Chip with Spatiotemporal Elasticity for Multi-intelligent-tasking Robots. Science Robotics, 7(67), eabk2948. (Science Highlighted Feature AAAS News, Chip10 Science in 2022, Impacting Factor:25.0).
  • Yu, F., Wu, Y., Ma, S. (co-first), et al. (2023). Brain-inspired Multimodal Hybrid Neural Network for Robot Place Recognition. Science Robotics, 8(78), eabm6996. (Cover feature article, Impacting Factor:25.0).
  • Zhang, W., Ma, S. (co-first), et al. (2024). The Development of General-Purpose Brain-Inspired Computing. Nature Electronics, 7:954-965. (Impacting Factor:34.5).
  • Ma, S., et al. (2025). CoXplorer: Multi-Staged Co-Exploration Framework for AI Model Compression and Accelerator Design. In ACM/IEEE Int. Conf. on Computer-Aided Design (ICCAD) (Top-tier conference in EDA).
  • Li, H., Ma, S.# (co-corresponding), … & Zhao, R.# (2026). Bridging Efficiency and Scalability in LLM System via 3D Hybrid PIM with 2D In-Transit Computation. International Symposium on Computer Architecture (ISCA), Raleigh, 2026 (Accepted, top-tier conference in computer architecture, CCF-A).
  • Tan, Y., Ma, S. (co-first), et al. (2026). A 5nm 91.43 TOPS/W 4-Chiplet Generalizable Rendering Processor with UCIe-Enabled Cross-Die Cache and Balance-Aware Progressive Multi-Level Sparsity. IEEE Custom Integrated Circuits Conference (CICC), Seattle, 2026 (Top-tier conference in IC).
  • Li, H., Ma, S.#(co-first, co-corresponding), Wang, T., … & Zhao, R.# (2024). HASP: Hierarchical Asynchronous Parallelism for Multi-NN Tasks. IEEE Transactions on Computers, 73(2):366-379.
  • Lin, J., Qu H., Ma, S. (co-first), et al. (2023). SongC: A Compiler for Hybrid Near-Memory and In-Memory Many-Core Architecture. IEEE Transactions on Computers, 73(10):2420-2433.

Honors & Awards

  • Gold Medal at the 50th International Exhibition of Inventions Geneva (2025, group award)
  • Tsinghua University Outstanding PhD graduate (2024)
  • Tsinghua University Excellent Dissertation Award (2024)
  • National Scholarship for Ph.D. Students (THU 2022, 0.2%)
  • Chip10 Science in 2022 中国芯片科学十大进展
  • Best Poster Award in ICAC 2023
  • NSK Sino-Japan Friendship Outstanding Paper Prize
  • Nomination Award for 2022 Top-10 Research Advances in China Semiconductors
  • President Scholarship for Outstanding Undergraduates (JLU, 2019)
  • The Baogang Scholarship in 2018 (placed First in JLU)
  • National Scholarship for Undergraduate Students (JLU 2016, 2017, 0.2%)
  • Excellent Student Leader Scholarship (JLU 2016, 2017, 2018)

Contact

  • Address: Units 801-807 & 816, 8/F, Building 17W, Hong Kong Science Park, New Territories, Hong Kong
  • Email: songchenma@ust.hk