no code implementations • 4 Apr 2024 • Hanxian Huang, Jishen Zhao
WasmRev is pre-trained using self-supervised learning on a large-scale multi-modal corpus encompassing source code, code documentation and the compiled WebAssembly, without requiring labeled data.
1 code implementation • 3 Apr 2024 • Zhongming Yu, Genghan Zhang, Hanxian Huang, Xin Chen, Jishen Zhao
Yet, efficient tensor-centric frameworks for GNNs remain scarce due to unique challenges and limitations encountered when implementing segment reduction in GNN contexts.
no code implementations • 5 Mar 2024 • Xin Chen, Hanxian Huang, Yanjun Gao, Yi Wang, Jishen Zhao, Ke Ding
Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment.
no code implementations • 8 Jan 2024 • Hanxian Huang, Tarique Siddiqui, Rana Alotaibi, Carlo Curino, Jyoti Leeka, Alekh Jindal, Jishen Zhao, Jesus Camacho-Rodriguez, Yuanyuan Tian
Drawing insights from real-workloads, we propose template-based featurization techniques and develop a stacked-LSTM with an encoder-decoder architecture for accurate forecasting of query workloads.
no code implementations • ICCV 2023 • Cheng Fu, Hanxian Huang, Zixuan Jiang, Yun Ni, Lifeng Nai, Gang Wu, Liqun Cheng, Yanqi Zhou, Sheng Li, Andrew Li, Jishen Zhao
One promising way to accelerate transformer training is to reuse small pretrained models to initialize the transformer, as their existing representation power facilitates faster model convergence.