Lune

Profiles2020-2024

Caiwen Ding

University of Connecticut

13Papers
12Last author
45Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers13

  1. MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks TrainingAuthor 9 of 9ASPLOS 2024 · 32 citations
  2. LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted InferenceAuthor 11 of 11NeurIPS 2023 · 57 citations
  3. AutoReP: Automatic ReLU Replacement for Fast Private Network InferenceAuthor 14 of 14ICCV 2023 · 44 citations
  4. Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-offAuthor 7 of 7DAC 2023 · 7 citations
  5. Neurogenesis Dynamics-inspired Spiking Neural Network Training AccelerationAuthor 10 of 10DAC 2023 · 6 citations
  6. PASNet: Polynomial Architecture Search Framework for Two-party Computation-based Secure Neural Network DeploymentAuthor 11 of 11DAC 2023 · 5 citations
  7. Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and FilteringAuthor 5 of 5S&P 2023
  8. You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language ModelAuthor 6 of 9CVPR 2023
  9. A length adaptive algorithm-hardware co-design of transformer on FPGA through sparse attention and dynamic pipeliningAuthor 11 of 11DAC 2022 · 49 citations
  10. Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune ParadigmAuthor 11 of 11ACL 2022
  11. FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN AcceleratorAuthor 11 of 11ISCA 2021 · 73 citations
  12. TAG: Gradient Attack on Transformer-based Language ModelsAuthor 8 of 8EMNLP Findings 2021 · 59 citations
  13. Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured PruningAuthor 7 of 7EMNLP Findings 2020 · 39 citations
Dusk over the sea between two cliffs drawn in fine vertical lines