InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting.
CoRR, 2024
T-BUS: Taming Bipartite Unstructured Sparsity for Energy-Efficient DNN Acceleration.
Proceedings of the 42nd IEEE International Conference on Computer Design, 2024
HOLES: Boosting Large Language Models Efficiency with Hardware-Friendly Lossless Encoding.
Proceedings of the 42nd IEEE International Conference on Computer Design, 2024
INSPIRE: Accelerating Deep Neural Networks via Hardware-friendly Index-Pair Encoding.
Proceedings of the 61st ACM/IEEE Design Automation Conference, 2024
MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting.
CoRR, 2023