廖思宇
一、 个人简介
廖思宇，博士，硕士生导师，获罗格斯大学博士学术成就奖，主要研究高性能神经网络模型及相关的应用，研究成果已经发表在许多一流国际会议和期刊，如MICRO、ISCA、ICML、AAAI和CIKM等。拥有丰富的工业界经验，获国际商业机器实习优秀奖，易趣编程马拉松周一等奖，高通创新奖学金决赛入围，拥有美国专利1项。担任IEEE ASAP 2021 TPC成员，为TACO、TCAS-I、TCAS-II、TSP、NeurIPS、ACL、ICCV、AAAI等期刊和会议的审稿人。
欢迎计算机、电子等相关专业的本科生、研究生加入本团队。
二、 研究领域
随着大数据与并行计算的发展，现代人工智能已经影响到很多领域的发展，同时对底层的软硬件也提出了更高的要求。主要研究方向包括但不限于：高性能的深度学习模型训练与推理算法，如结构化/量化/分解/蒸馏/早停等；特定算法的并行计算设计实现，CUDA/SSE等；生成式人工智能在通讯、医疗、艺术等方面的应用，如扩散模型编解码，电子地图生成等；嵌入式深度学习模型部署。
三、 教育背景
2010.9-2014.6，合肥工业大学，信息安全，本科
2014.9-2018.6，纽约市立大学研究生中心，计算机，硕士
2018.9-2020.10，罗格斯大学，计算机，博士
四、 工作经历
2017.9-2017.12，纽约大学访学
2019.9-2019.12，普林斯顿大学访学
2020.11-2024.5，亚马逊，应用科学家
2024.06-至今 中山大学，集成电路学院，预聘助理教授（副教授职务）。
五、 部分代表性成果
[NeurIPS 2025] X. Feng and S. Liao, "CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices", in Advances in Neural Information Processing Systems (NeurIPS), 2025
[NeurIPS 2025] X. Ding, B. Liu, S. Liao* and Z. Wang*, "Memory-Efficient Training with In-Place FFT Implementation", in Advances in Neural Information Processing Systems (NeurIPS), 2025
[IJCAI 2025] X. Ding, M. Wang, S. Liao* and Z. Wang*, "Block Circulant Adapter for Large Language Models", in Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025
[IJCAI 2025] X. Ding, L. Chen, S. Liao* and Z. Wang*, "Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors", in Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI), 2025
[CIKM 2023] S. Liao, R. Zhang, B. Poblete and V. Murdock, "Bias Invariant Approaches for Improving Word Embedding Fairness", in Proceedings of the 32nd ACM International Conference on Information & Knowledge Management (CIKM), 2023
[AAAI 2021] S. Liao, C. Deng, M. Yin and B. Yuan, "Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding", in Association for the Advancement of Artificial Intelligence (AAAI), 2021
[AAAI 2020] S. Liao, J. Chen, Y. Wang, Q. Qiu and B. Yuan, "Embedding Compression with Isotropic Iterative Quantization", in Association for the Advancement of Artificial Intelligence (AAAI), 2020
[AAAI 2019] S. Liao and B. Yuan, "CircConv: A Structured Convolution with Low Complexity", in Association for the Advancement of Artificial Intelligence (AAAI), 2019
[MICRO 2018] C. Deng#, S. Liao#, Y. Xie, K. Parhi, X. Qian and B. Yuan, "PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices", in IEEE/ACM International Symposium on Microarchitecture (MICRO), 2018
[ICML 2017] L. Zhao#, S. Liao#, Y. Wang, Z. Li, J. Tang and B. Yuan, "Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank", in Proceedings of International Conference on Machine Learning (ICML),2017