Caiwen Ding is an assistant professor in the Department of Computer Science & Engineering at the University of Connecticut. He received his Ph.D. degree from Northeastern University (NEU), Boston in 2019, supervised by Prof. Yanzhi Wang. His interests include machine Learning systems; computer architecture and heterogeneous computing (FPGAs/GPUs); computer vision, natural language processing; non-von Neumann computing and neuromorphic computing; privacy-preserving machine learning.
His work has been frequently published in high-impact conferences (e.g., ASPLOS, ISCA, MICRO, HPCA, SC, AAAI, ACL, EMNLP, IJCAI, FPGA, DAC, DATE, ISLPED). His work on Block-Circulant Matrix-based Smartphone Acceleration received the Best Paper Award Nomination at DATE 2018; his work on ReRAM-based In-Memory Computing for DNN Acceleration received the Best Paper Award Nomination at DATE 2021.
- Laboratory of Intelligent & Efficient Systems
- Laboratory of Machine Learning in Drug Discovery & Development
To prospective students:
I am always looking for highly-motivated Ph.D. students who have strong interests in FPGAs/GPUs programming (preferred), or machine learning/deep learning, with full financial support. You are welcome to drop me an email with your materials such as CV and transcripts and mention my name in your application.
4/2022 Our DAC 22 paper “A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining” has been recognized as a Publicity Paper.
4/2022 Caiwen gave an invited seminar at UConn CEE 5030 Transportation Graduate Seminar.
4/2022 Invited to serve on the External Review Committee (ERC) for the 2023 HPCA.
4/2022 Nathan Choi has been admitted to the graduate program of UC Berkeley. Congrats Nathan!
2/2022 One paper “Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm” is accepted by the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022) main conference. Congrats to Shaoyi!
2/2022 Received two more (three in total) Alveo U280 Data Center Accelerator ($7,145 each) from the Xilinx University Program. Thanks to Xilinx!
2/2022 One paper is accepted by DAC 2022; Congrats to Hongwu and Shaoyi!
2/2022 We are excited to join the UIUC Xilinx Center of Excellence as an external collaborator.
1/2022 One paper “QuClassi: A Hybrid Deep Neural Network Architecture based on Quantum State Fidelity” is accepted by MLSys 2022.
1/2022 I am honored to receive a Research Grant from USDA-NIFA Agriculture and Food Research Initiative (Award No.: 2022-67023-36399) as Co-PI! Link
11/2021 One paper “Enabling Super-Fast Deep Learning on Tiny Energy-Harvesting IoT Devices” is accepted by DATE 2022. Congrats to Jieren and Shanglin!
10/2021 Received $30,000 worth of GCP Credits from Google.
10/2021 Received the 2021 UCONN IMS IMMP grant.
09/2021 Received a research grant from the Eversource Energy Center at UConn.
08/2021 Received a research grant from Travelers.
08/2021 Jieren’s two first-authored papers “TAG: Gradient Attack on Transformer-based Language Models” and “A Secure and Efficient Federated Learning Framework for NLP” are accepted by EMNLP 2021. Congrats!
08/2021 Caiwen is invited to serve as a member of the novel Program Committee Board (PCB) of IJCAI.
07/2021 Our special session proposal with Prof. Weiwen Jiang (GMU) on AI for drug discovery has been accepted by ICCAD 2021.
07/2021 One paper is accepted by ICCAD 2021. Congrats to Hongwu, Shaoyi, and Bingbing!
07/2021 Caiwen gave an invited talk on Model Compression on DNNs at UTSA’s REU Seminar Series.
07/2021 Caiwen gave an invited talk on Binary Neural Networks on FPGA at ASAP’2021.
06/2021 Jieren received an internship offer from ORNL. Congratulations to Jieren!
06/2021 Two papers “E.T.: Re-Thinking Self-Attention for Transformer Models on GPUs” and “Dr.Top-k: Delegate-Centric Top-k Computation on GPUs” are accepted in SC 2021.
06/2021 Received 2021 UConn Research Excellence Program (REP) Award.
05/2021 Received an Alveo U280 Data Center Accelerator ($6,495) from the Xilinx University Program. Thanks to Xilinx!
05/2021 Caiwen will serve as a TPC member of ICESS 2021.
05/2021 One paper is accepted in the Transportation Consortium of South-Central States (TranSET) 2021.
04/2021 Two papers “Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation” and “Against Membership Inference Attack: Pruning is All You Need” are accepted in IJCAI 2021.
04/2021 Two papers are accepted in GLSVLSI 2021.
04/2021 Caiwen will serve as a reviewer of DAC’2021 Late-Breaking Results.
04/2021 Caiwen will serve as a TPC member of GLSVLSI 2021.
04/2021 Caiwen will serve as a TPC member of ISVLSI 2021.
03/2021 One paper “FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator” is accepted in IEEE/ACM International Symposium on Computer Architecture (ISCA 2021).
02/2021 Received “Excellent in teaching” award from Provost.
02/2021 One paper “Design, Sensing, and Control of a Novel UAV Platform for Aerial Drilling and Screwing” is accepted in IEEE Robotics and Automation Letters (IEEE RA-L). We will present it at the 2021 IEEE International Conference on Robotics and Automation (ICRA 2021).
02/2021 One paper is accepted in IEEE Transactions on Parallel and Distributed Systems (TPDS).
02/2021 Two papers “Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices” and “A unified DNN weight pruning framework using reweighted optimization methods” are accepted in the ACM/EDAC/IEEE Design Automation Conference (DAC) 2021.
02/2021 Three papers are accepted in ISQED 2021.
01/2021 Paper “TinyADC: Peripheral Circuit-aware Weight Pruning Framework for Mixed-signal DNN Accelerators” receives Best Paper Award Nomination at DATE 2021.
12/2020 Received Google’s exploreCSR award. Welcome to the Tri-State ExploreCSR Workshop.
11/2020 One paper about Efficient Federated Learning is accepted in SpicyFL workshop at NeurIPS 2020.
11/2020 One paper is accepted in The Design, Automation, and Test in Europe Conference (DATE) 2021.
09/2020 One paper is accepted in the findings of Empirical Methods in Natural Language Processing (EMNLP) 2020.