個人檔案
研究專長
AI運算平台設計、近似計算於AI之應用、安全與硬體特洛伊、SoC設計自動化
經歷
1.Software Engineer, Design Technology Solutions, Intel Corporation, 08/2011 – 07/2013
2.Research Assistant, Energy Aware Computing (EnyAC) Group, Carnegie Mellon University, 08/2006 – 07/2011
教育/學術資格
PhD, 資訊工程, Carnegie Mellon University
外部位置
指紋
- 1 類似的個人檔案
過去五年中的合作和熱門研究領域
專案
- 13 已完成
-
Transformer 類神經網路之軟硬體整合加速方案-總計畫暨子計畫一：考量硬體特性與模型量化之 Transformer 類神經網路架構搜尋技術
Wu, K.-C. (PI)
1/08/24 → 31/07/25
研究計畫: Other Government Ministry Institute
-
Transformer 類神經網路之軟硬體整合加速方案-總計畫暨子計畫一：考量硬體特性與模型量化之 Transformer 類神經網路架構搜尋技術
Wu, K.-C. (PI)
1/08/23 → 31/07/24
研究計畫: Other Government Ministry Institute
-
Transformer 類神經網路之軟硬體整合加速方案-總計畫暨子計畫一：考量硬體特性與模型量化之 Transformer 類神經網路架構搜尋技術
Wu, K.-C. (PI)
1/08/22 → 31/07/23
研究計畫: Other Government Ministry Institute
-
智慧終端系統晶片研發與新創事業計畫-子計畫二：以終端系統為考量之視覺深度神經網路模組設計(2/2)
Wu, K.-C. (PI)
1/05/21 → 31/07/22
研究計畫: Other Government Ministry Institute
-
智慧終端系統晶片研發與新創事業計畫-子計畫二：以終端系統為考量之視覺深度神經網路模組設計(1/2)
Wu, K.-C. (PI)
1/05/20 → 30/04/21
研究計畫: Other Government Ministry Institute
-
Integrating Neural Architecture Search and Rematerialization for Efficient On-Device Learning
Chen, C. L., Wu, K. C. & Huang, N. C., 13 7月 2025, GECCO 2025 - Proceedings of the 2025 Genetic and Evolutionary Computation Conference. Ochoa, G. (編輯). Association for Computing Machinery, Inc, p. 1226-1234 9 p. (GECCO 2025 - Proceedings of the 2025 Genetic and Evolutionary Computation Conference).研究成果: Conference contribution › 同行評審
-
PALU: KV-CACHE COMPRESSION WITH LOW-RANK PROJECTION
Chang, C. C., Lin, W. C., Lin, C. Y., Chen, C. Y., Hu, Y. F., Wang, P. S., Huang, N. C., Ceze, L., Abdelfattah, M. S. & Wu, K. C., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 56482-56509 28 p. (13th International Conference on Learning Representations, ICLR 2025).研究成果 › 同行評審
3 引文 斯高帕斯（Scopus） -
QUAMBA: A POST-TRAINING QUANTIZATION RECIPE FOR SELECTIVE STATE SPACE MODELS
Chiang, H. Y., Chang, C. C., Frumkin, N., Wu, K. C. & Marculescu, D., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 58791-58817 27 p. (13th International Conference on Learning Representations, ICLR 2025).研究成果: Conference contribution › 同行評審
5 引文 斯高帕斯（Scopus） -
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
Chiang, H. Y., Chang, C. C., Frumkin, N., Wu, K. C., Abdelfattah, M. S. & Marculescu, D., 2025, 於: Proceedings of Machine Learning Research. 267, p. 10411-10427 17 p.研究成果: Conference article › 同行評審
-
Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration
Taka, E., Huang, N. C., Chang, C. C., Wu, K. C., Arora, A. & Marculescu, D., 27 2月 2025, FPGA 2025 - Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays. Association for Computing Machinery, Inc, p. 159-171 13 p. (FPGA 2025 - Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays).研究成果: Conference contribution › 同行評審
開啟存取7 引文 斯高帕斯（Scopus）