I am currently a Postdoctoral Researcher in the Embedded Systems Laboratory (ESL) at EPFL, working under the supervision of Prof. David Atienza. I received my Ph.D. in Computer Science and Engineering from UC San Diego (UCSD), where I was advised by Prof. Tajana Rosing. My research interests include a) emerging near-memory processing (NMP) architecture, b) RISC-V, c) hyperdimensional computing.
Before joining UCSD, I received B.E. and M.E. degrees from Southeast University, under supervision of Prof. Chuan Zhang and Prof. Yair Be’ery. I finished a four-month research intern in Intel Labs China where I developed the Flexible MIMO Processor for networks beyond 5G.
🔥 News
- 2025.07: 🎉 SLIM was accepted by TECS.
- 2025.06: 🎉 HyperMetric was accepted by TCAD.
- 2025.06: 🎉 Chip Clo-HDnn was accepted by VLSI Symposium.
- 2025.05: 🎉 HPVM-HDC was accepted by ISCA.
- 2024.12: 🎉 I will be joining EPFL as a postdoctoral researcher.
- 2024.09: 🎉 I have successfully completed my Ph.D. at UCSD! Check my thesis here
- 2024.07: 🎉 HyperGen work was accepted!
- 2024.07: 🎉 TriHD work was accepted!
📖 Educations
- 2020 - 2024, Ph.D. in Computer Science and Engineering, University of California, San Diego, La Jolla, USA.
- 2017 - 2020, M.E. in Information and Communication Engineering, Southeast University, Nanjing, China.
- 2013 - 2017, B.E. in Information Engineering, Southeast University, Nanjing, China.
Highlighted Projects
💫 Near-memory Acceleration for Emerging Workloads
SLIM: A Heterogeneous Accelerator for Edge Inference of Sparse Large Language Model via Adaptive Thresholding
Weihong Xu, Haein Choi, Po-Kai Hsu, Shimeng Yu, and Tajana Rosing
ACM Transactions on Embedded Computing Systems (TECS), 2025
- [TC 2024] RelHDx: Hyperdimensional Computing for Learning on Graphs With FeFET Acceleration
Jaeyoung Kang, Minxuan Zhou, Weihong Xu, and Tajana Rosing
IEEE Transactions on Computers (TC), 2025 - [TCAD 2024] DRAM-based acceleration of open modification search in hyperdimensional space
Jaeyoung Kang, Weihong Xu, Wout Bittremieux, Niema Moshiri, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024 - [TACO 2024] Abakus: Accelerating k-mer Counting With Storage Technology
Lingxi Wu, Minxuan Zhou, Weihong Xu, Ashish Venkat, Tajana Rosing, and Kevin Skadron
ACM Transactions on Architecture and Code Optimization (TACO), 2024 - [TCAD 2023] RAPIDx: High-performance ReRAM Processing in-Memory Accelerator for DNA Alignment
Weihong Xu, Saransh Gupta, Niema Moshiri, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023 - [HPCA 2022] TransPIM: A Memory-based Acceleration via Software-Hardware Co-Design for Transformers
Minxuan Zhou∗, Weihong Xu∗, Jaeyoung Kang, and Tajana Rosing
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2022 * Equal contribution -
[DAC 2022] A Near-Storage Framework for Boosted Data Preprocessing of Mass Spectrum Clustering
Weihong Xu, Jaeyoung Kang, and Tajana Rosing
IEEE/ACM Design Automation Conference (DAC), 2022 - [Under Review] Proxima: Near-storage Acceleration for Graph-based Approximate Nearest Neighbor Search in 3D NAND
Weihong Xu, Junwei Chen, Po-Kai Hsu, Jaeyoung Kang, Minxuan Zhou, Sumukh Pinge, Shimeng Yu, and Tajana Rosing
Under review of IEEE Transactions on Computers, 2024
🤖 Edge AI Chips
Clo-HDnn: A 4.66 TLOPS/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, and Mingu Kang
Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits), 2025 * Equal contribution
FSL-HDnn: A 5.7 TOPS/W End-to-end Few-shot Learning Classifier Accelerator with Feature Extraction and Hyperdimensional Computing
Haichao Yang, Chang Eun Song, Weihong Xu, Behnam Khaleghi, Uday Mallappa, Monil Shah, Keming Fan, Mingu Kang, and Tajana Rosing
European Solid-State Electronics Research Conference (ESSERC), 2024
📊 Hyperdimensional Computing
- [TCAD 2025] HyperMetric: Efficient Hyperdimensional Computing With Metric Learning for Robust Edge Intelligence
Weihong Xu, Sean Fuhrman, Keming Fan, Sumukh Pinge, Wei-Chen Chen, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024 - [ISCA 2025] Hpvm-hdc: A heterogeneous programming system for accelerating hyperdimensional computing
Russel Arbore, Xavier Routh, Abdul Rafae Noor, Akash Kothari, Haichao Yang, Weihong Xu, Sumukh Pinge, Minxuan Zhou, Tajana Rosing, and Vikram Adve
International Symposium on Computer Architecture (ISCA), 2025 - [TCAD 2024] Tri-HD: Train, Re-train, and Infer with Hyperdimensional Computing in Memory
Weihong Xu, Saransh Gupta, Justin Morris, Xincheng Shen, Mohsen Imani, Baris Aksanli, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024 - [DATE 2024] AttBind: Memory-Efficient Acceleration for Long-Range Attention Using Vector-Derived Symbolic Binding
Weihong Xu, Jaeyoung Kang, and Tajana Rosing
Design, Automation and Test in Europe Conference (DATE), 2024 - [ICCD 2023] HyperMetric: Robust Hyperdimensional Computing on Error-prone Memories using Metric Learning
Weihong Xu, Viji Swaminathan, Sumukh Pinge, Sean Fuhrman, and Tajana Rosing
IEEE International Conference on Computer Design (ICCD), 2023 - [DATE 2023] FSL-HD: Accelerating Few-Shot Learning on ReRAM using Hyperdimensional Computing
Weihong Xu, Jaeyoung Kang, and Tajana Rosing
Design, Automation and Test in Europe Conference (DATE), 2023
🧬 Bioinformatics: Genome and Mass Spectrometry Analysis
HyperGen: Compact and Efficient Genome Sketching using Hyperdimensional Vectors
Weihong Xu, Po-kai Hsu, Niema Moshiri, Shimeng Yu, and Tajana Rosing
Bioinformatics, 2024
- HyperGen is a memory-efficient tool for genomic sketching
HyperSpec: Fast Mass Spectra Clustering in Hyperdimensional Space
Weihong Xu, Jaeyoung Kang, Wout Bittremieux, Niema Moshiri, and Tajana Rosing
Journal of Proteome Research, 2023
- HyperSpec is one of the fastest clustering tool for mass spectrometry data
📝 Full Publication List
Published Journals
- [TECS 2025] SLIM: A Heterogeneous Accelerator for Edge Inference of Sparse Large Language Model via Adaptive Thresholding
Weihong Xu, Haein Choi, Po-Kai Hsu, Shimeng Yu, and Tajana Rosing
ACM Transactions on Embedded Computing Systems (TECS), 2025 - [TCAD 2025] HyperMetric: Efficient Hyperdimensional Computing With Metric Learning for Robust Edge Intelligence
Weihong Xu, Sean Fuhrman, Keming Fan, Sumukh Pinge, Wei-Chen Chen, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024 - [TETC 2025] Fhemem: A processing in-memory accelerator for fully homomorphic encryption
Minxuan Zhou, Yujin Nam, Pranav Gangwar, Weihong Xu, Arpan Dutta, Chris Wilkerson, Rosario Cammarota, Saransh Gupta, and Tajana Rosing IEEE Transactions on Emerging Topics in Computing (TETC), 2025 - [TCAD 2024] Tri-HD: Train, Re-train, and Infer with Hyperdimensional Computing in Memory
Weihong Xu, Saransh Gupta, Justin Morris, Xincheng Shen, Mohsen Imani, Baris Aksanli, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024 - [Bioinformatics 2024] HyperGen: Compact and Efficient Genome Sketching using Hyperdimensional Vectors
Weihong Xu, Po-kai Hsu, Niema Moshiri, Shimeng Yu, and Tajana Rosing
Bioinformatics, 2024
- [TACO 2024] Abakus: Accelerating k-mer Counting With Storage Technology
Lingxi Wu, Minxuan Zhou, Weihong Xu, Ashish Venkat, Tajana Rosing, and Kevin Skadron
ACM Transactions on Architecture and Code Optimization (TACO), 2024 - [TCAD 2023] RAPIDx: High-performance ReRAM Processing in-Memory Accelerator for DNA Alignment
Weihong Xu, Saransh Gupta, Niema Moshiri, and Tajana Rosing
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023 - [JPR 2023] HyperSpec: Fast Mass Spectra Clustering in Hyperdimensional Space
Weihong Xu, Jaeyoung Kang, Wout Bittremieux, Niema Moshiri, and Tajana Rosing
Journal of Proteome Research, 2023
- [TCAD 2020] Reconfigurable and Low-complexity Accelerator for Convolutional and Generative Networks over Finite Fields
Weihong Xu, Zaichen Zhang, Xiaohu You, and Chuan Zhang
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2020 - [JETCAS 2020] Deep Learning-aided Belief Propagation Decoder for Polar Codes
Weihong Xu, Xiaosi Tan, Yair Be’ery, Zaichen Zhang, Xiaohu You, and Chuan Zhang
IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), 2020
Published Conferences
- [VLSI 2025] Clo-HDnn: A 4.66 TLOPS/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, and Mingu Kang
Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits), 2025 * Equal contribution -
[ISCA 2025] Hpvm-hdc: A heterogeneous programming system for accelerating hyperdimensional computing
Russel Arbore, Xavier Routh, Abdul Rafae Noor, Akash Kothari, Haichao Yang, Weihong Xu, Sumukh Pinge, Minxuan Zhou, Tajana Rosing, and Vikram Adve
International Symposium on Computer Architecture (ISCA), 2025 - [IEDM 2024] Filament-Free Bulk RRAM with High Endurance and Long Retention for Neuromorphic Few-Shot Learning On-Chip
Ashwani Kumar, Yucheng Zhou, Sai Praneeth Potladurthy, Jeong-Hoon Kim, Weihong Xu, Flavio Ponzina, Seonghyun Kim, Ertugrul Cubukcu, Tajana Rosing, Gert Cauwenberghs, and Duygu Kuzum
IEEE International Electron Devices Meeting (IEDM), 2024 - [DATE 2024] AttBind: Memory-Efficient Acceleration for Long-Range Attention Using Vector-Derived Symbolic Binding
Weihong Xu, Jaeyoung Kang, and Tajana Rosing
Design, Automation and Test in Europe Conference (DATE), 2024 - [ESSERC 2024] FSL-HDnn: A 5.7 TOPS/W End-to-end Few-shot Learning Classifier Accelerator with Feature Extraction and Hyperdimensional Computing
Haichao Yang, Chang Eun Song, Weihong Xu, Behnam Khaleghi, Uday Mallappa, Monil Shah, Keming Fan, Mingu Kang, and Tajana Rosing
European Solid-State Electronics Research Conference (ESSERC), 2024 - [DAC 2024] Rl-ptq: Rl-based mixed precision quantization for hybrid vision transformers
Eunji Kwon, Minxuan Zhou, Weihong Xu, Tajana Rosing. and Seokhyeong Kang
ACM/IEEE Design Automation Conference (DAC), 2024 - [ICCD 2023] HyperMetric: Robust Hyperdimensional Computing on Error-prone Memories using Metric Learning
Weihong Xu, Viji Swaminathan, Sumukh Pinge, Sean Fuhrman, and Tajana Rosing
IEEE International Conference on Computer Design (ICCD), 2023 - [DATE 2023] FSL-HD: Accelerating Few-Shot Learning on ReRAM using Hyperdimensional Computing
Weihong Xu, Jaeyoung Kang, and Tajana Rosing
Design, Automation and Test in Europe Conference (DATE), 2023 - [HPCA 2022] TransPIM: A Memory-based Acceleration via Software-Hardware Co-Design for Transformers
Minxuan Zhou∗, Weihong Xu∗, Jaeyoung Kang, and Tajana Rosing
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2022 * Equal contribution - [DAC 2022] A Near-Storage Framework for Boosted Data Preprocessing of Mass Spectrum Clustering
Weihong Xu, Jaeyoung Kang, and Tajana Rosing
IEEE/ACM Design Automation Conference (DAC), 2022
Under Review
- [Under Review] Proxima: Near-storage Acceleration for Graph-based Approximate Nearest Neighbor Search in 3D NAND
Weihong Xu, Junwei Chen, Po-Kai Hsu, Jaeyoung Kang, Minxuan Zhou, Sumukh Pinge, Shimeng Yu, and Tajana Rosing
Under review of IEEE Transactions on Computers, 2024