| Understanding architectures learnt by cell-based neural architecture search Y Shu, W Wang, S Cai Proc. ICLR, 2020 | 120 | 2020 |
| Effective and efficient dropout for deep convolutional neural networks S Cai, Y Shu, G Chen, BC Ooi, W Wang, M Zhang arXiv preprint arXiv:1904.03392, 2019 | 102 | 2019 |
| DAVINZ: Data Valuation using Deep Neural Networks at Initialization Z Wu, Y Shu, BKH Low Proc. ICML, 2022 | 67 | 2022 |
| Dynamic routing networks S Cai, Y Shu, W Wang Proc. WACV, 2021 | 60 | 2021 |
| Efficient memory management for gpu-based deep learning systems J Zhang, SH Yeung, Y Shu, B He, W Wang arXiv preprint arXiv:1903.06631, 2019 | 57 | 2019 |
| NASI: Label- and Data-agnostic Neural Architecture Search at Initialization Y Shu, S Cai, Z Dai, BC Ooi, BKH Low Proc. ICLR, 2022 | 52 | 2022 |
| Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transformers X Lin, Z Wu, Z Dai, W Hu, Y Shu, SK Ng, P Jaillet, BKH Low Proc. ICML, 2024 | 38* | 2024 |
| Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search Y Shu, Z Dai, Z Wu, BKH Low Proc. NeurIPS, 2022 | 36 | 2022 |
| Federated Neural Bandit Z Dai, Y Shu, A Verma, FX Fan, BKH Low, P Jaillet Proc. ICLR, 2023 | 28 | 2023 |
| Sample-Then-Optimize Batch Neural Thompson Sampling Z Dai, Y Shu, BKH Low, P Jaillet Proc. NeurIPS, 2022 | 22 | 2022 |
| Quantum Bayesian Optimization Z Dai, GKR Lau, A Verma, Y Shu, BKH Low, P Jaillet Proc. NeurIPS, 2023 | 16 | 2023 |
| Zeroth-order optimization with trajectory-informed derivative estimation Y Shu, Z Dai, W Sng, A Verma, P Jaillet, BKH Low Proc. ICLR, 2023 | 15 | 2023 |
| Localized zeroth-order prompt optimization W Hu, Y Shu, Z Yu, Z Wu, X Lin, Z Dai, SK Ng, BKH Low Proc. NeurIPS (Spotlight), 2024 | 14 | 2024 |
| Neural Ensemble Search via Bayesian Sampling Y Shu, Y CHEN, Z Dai, BKH Low Proc. UAI, 2022 | 13* | 2022 |
| Heterogeneous Federated Zeroth-Order Optimization using Gradient Surrogates Y Shu, X Lin, Z Dai, BKH Low Workshop on Differentiable Almost Everything @ ICML, 2024 | 11* | 2024 |
| Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars Z Wu, X Lin, Z Dai, W Hu, Y Shu, SK Ng, P Jaillet, BKH Low Proc. NeurIPS, 2024 | 8 | 2024 |
| Randomness in Deconvolutional Networks for Visual Representation K He, J Wang, H Li, Y Shu, M Zhang, M Zhu, L Wang, JE Hopcroft arXiv preprint arXiv:1704.00330, 2017 | 7* | 2017 |
| Flexora: Flexible Low Rank Adaptation for Large Language Models C Wei, Y Shu, YT He, FR Yu Workshop on Fine-Tuning in Modern Machine Learning @ NeurIPS, 2024 | 2 | 2024 |
| Data-Centric AI in the Age of Large Language Models X Xu, Z Wu, R Qiao, A Verma, Y Shu, J Wang, X Niu, Z He, J Chen, Z Zhou, ... Proc. EMNLP, 2024 | 2* | 2024 |
| Data valuation in federated learning Z Wu, X Xu, RHL Sim, Y Shu, X Lin, L Agussurja, Z Dai, SK Ng, CS Foo, ... Federated Learning, 281-296, 2024 | 2 | 2024 |
Bryan Kian Hsiang LowAssociate Professor (with tenure), Department of Computer Science, National University of SingaporeVerified email at comp.nus.edu.sg