Wenxun Wang
Orcid: 0009-0007-1999-6441
According to our database1,
Wenxun Wang
authored at least 7 papers
between 2022 and 2024.
Collaborative distances:
Collaborative distances:
Timeline
2022
2023
2024
0
1
2
3
4
2
3
2
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2024
A Fully Quantized Training Accelerator for Diffusion Network With Tensor Type & Noise Strength Aware Precision Scheduling.
IEEE Trans. Circuits Syst. II Express Briefs, December, 2024
A Dynamic Execution Neural Network Processor for Fine-Grained Mixed-Precision Model Training Based on Online Quantization Sensitivity Analysis.
IEEE J. Solid State Circuits, September, 2024
2023
SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference.
Proceedings of the IEEE/ACM International Conference on Computer Aided Design, 2023
A 28nm 1.07TFLOPS/mm<sup>2</sup> Dynamic-Precision Training Processor with Online Dynamic Execution and Multi- Level-Aligned Block-FP Processing.
Proceedings of the IEEE Custom Integrated Circuits Conference, 2023
Block-Wise Dynamic-Precision Neural Network Training Acceleration via Online Quantization Sensitivity Analytics.
Proceedings of the 28th Asia and South Pacific Design Automation Conference, 2023
2022
Proceedings of the IEEE International Symposium on Circuits and Systems, 2022
Dynamic CNN Accelerator Supporting Efficient Filter Generator with Kernel Enhancement and Online Channel Pruning.
Proceedings of the 27th Asia and South Pacific Design Automation Conference, 2022