Keming Fan (PhD Candidate at UC San Diego)

I am a Ph.D. Candidate in the Electrical and Computer Engineering Department at UC San Diego.

I am co-advised by Professor Tajana Rosing and Professor Mingu Kang .

My research spans AI hardware, integrated circuit design, and computer architecture.

SK hynix America Summer 2025 Intern, San Jose, CA Architecture modeling for memory-constrained on-device LLM inference.

Rivos Inc. (acquired by Meta) Summer 2024 Intern, Santa Clara, CA Silicon interposer design flow development and exploration.

See Google Scholar for the complete publication list.

1. DirectMCP: Accelerating On-Device LLMs via In-Package Direct Swap
   Seongju Lee*, Keming Fan* (* equal contribution), Sehyuck Yoo, Lauren Kim, Mingu Kang , Tajana Rosing , Sunjoo Kim
   IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2027. Accepted.
   




2. ReCIM-HD: A 40 nm On-Device Learning Accelerator with Hyperdimensional Computing via Importance-Based Hybrid Digital-ReRAM CIM
   Keming Fan*, Chang Eun Song*, Soumil Jain, Weihong Xu, Gopabandhu Hota, Haichao Yang, Leo Liu, Meng-Fan Chang , Carlos H. Diaz, Gert Cauwenberghs , Tajana Rosing , Mingu Kang
   IEEE European Solid-State Electronics Research Conference (ESSERC), 2026. Accepted.
   




3. Clo-HDnn: A 4.66 TFLOPS/W and 3.78 TOPS/W Continual On-Device Learning Accelerator with Energy-Efficient Hyperdimensional Computing via Progressive Search
   Chang Eun Song*, Weihong Xu*, Keming Fan, Soumil Jain, Gopabandhu Hota, Haichao Yang, Leo Liu, Kerem Akarvardar, Meng-Fan Chang , Carlos H. Diaz, Gert Cauwenberghs , Tajana Rosing , Mingu Kang
   IEEE Symposium on VLSI Technology and Circuits (VLSI), 2025.
   




4. Efficient Open Modification Spectral Library Searching in High-Dimensional Space with Multi-Level-Cell Memory
   Keming Fan, Wei-Chen Chen, Sumukh Pinge, H.-S. Philip Wong , Tajana Rosing
   ACM/IEEE Design Automation Conference (DAC), 2024.
   

Selected silicon prototypes.

40nm AI accelerator (ESSERC'26)

FPGA-based measurement (ESSERC'26)

65nm design (Under review)

• Ph.D. Candidate, University of California, San Diego, 2022 - 2027 (Expected)
  Electrical and Computer Engineering
  
  

• Visiting Student, University of California, Berkeley, 2021 - 2022
  Electrical Engineering & Computer Science
  
  

• Bachelor, ShanghaiTech University, 2018 - 2022
  Electronic Information Engineering
  Undergraduate Thesis: Design of Ultra-Low-Power Wake-Up Receiver for Neurostimulators