舒瑶 研究员

基础智能研究团队负责人

教育经历：

2017-08 至 2022-09，新加坡国立大学，计算机科学，博士

2013-09 至 2017-06，华中科技大学，计算机科学与技术，学士

工作经历：

2024-01 至 今，光明实验室，研究员（天才新星）

2023-08 至 2023-12，腾讯，高级研究员（技术大咖）

2022-06 至 2023-06，新加坡国立大学，博士后

2021-12 至 2022-06，新加坡国立大学，研究助理

邮箱：shuyao@gml.ac.cn

研究领域：学习、优化理论，生成式大模型，自动化机器学习

荣誉头衔：

2023，新加坡国立大学计算机学院博士毕业致辞

2023，IMDA卓越计算奖（最佳博士毕业论文）

2022，新加坡国立大学院长研究卓越奖

发表论文论著：

部分论文如下，完整列表请查看：https://scholar.google.com/citations?hl=en&user=qb9STggAAAAJ

1. Zhenfeng He, Yao Shu, Zhongxiang Dai, Bryan Kian Hsiang Low, Robustifying and Boosting Training-Free Neural Architecture Search, In The Twelfth International Conference on Learning Representations (ICLR), 2023.

2. Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, and Kian Hsiang Low. Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers. In Workshop on Instruction Tuning and Instruction Following (NeurIPS), 2023.

3. Zhongxiang Dai, Gregory Kang Ruey Lau, Arun Verma, Yao Shu, Bryan Kian Hsiang Low, and Patrick Jaillet. Quantum Bayesian Optimization. In The Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.

4. Arun Verma, Zhongxiang Dai, Yao Shu, and Bryan Kian Hsiang Low. Exploiting Correlated Auxiliary Feedback in Parameterized Bandits. In The Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.

5. Yao Shu, Zhongxiang Dai, Weicong Sng, Arun Verma, Patrick Jaillet, and Bryan Kian Hsiang Low. Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation. In The Eleventh International Conference on Learning Representations (ICLR), 2023.

6. Zhongxiang Dai, Yao Shu, Arun Verma, Flint Xiaofeng Fan, Bryan Kian Hsiang Low, and Patrick Jaillet. Federated Neural Bandit. In The Eleventh International Conference on Learning Representations (ICLR), 2023.

7. Yao Shu, Zhongxiang Dai, Zhaoxuan Wu, and Bryan Kian Hsiang Low. Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search. In The Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022.

8. Zhongxiang Dai, Yao Shu, Bryan Kian Hsiang Low, and Patrick Jaillet. Sample-Then-Optimize Batch Neural Thompson Sampling. In The Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022.

9. Yao Shu, Yizhou Chen, Zhongxiang Dai, and Bryan Kian Hsiang Low. Neural Ensemble Search via Bayesian Sampling. In The Thirty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI), 2022.

10. Zhaoxuan Wu, Yao Shu, and Bryan Kian Hsiang Low. DAVINZ: Data Valuation using Deep Neural Networks at Initialization. In The Thirty-Ninth International Conference on Machine Learning (ICML), 2022.

11. Yao Shu, Shaofeng Cai, Zhongxiang Dai, Beng Chin Ooi, and Bryan Kian Hsiang Low. NASI: Label- and Data-agnostic Neural Architecture Search at Initialization. In The Tenth International Conference on Learning Representations (ICLR), 2022.

12. Shaofeng Cai, Yao Shu, and Wei Wang. Dynamic Routing Networks. In IEEE Winter Conference on Applications of Computer Vision (WACV), pages 3587–3596, 2021.

13. Yao Shu, Wei Wang, and Shaofeng Cai. Understanding Architectures Learnt by Cell-based Neural Architecture Search. In The Eighth International Conference on Learning Representations (ICLR), 2020.