| Graph neural networks inspired by classical iterative algorithms Y Yang, T Liu, Y Wang, J Zhou, Q Gan, Z Wei, Z Zhang, Z Huang, D Wipf International Conference on Machine Learning, 11773-11783, 2021 | 113 | 2021 |
| Transformers from an Optimization Perspective Y Yang, Z Huang, D Wipf arXiv preprint arXiv:2205.13891, 2022 | 43 | 2022 |
| Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks H Ahn, Y Yang, Q Gan, T Moon, DP Wipf Advances in Neural Information Processing Systems 35, 38436-38448, 2022 | 42 | 2022 |
| Going beyond linear mode connectivity: The layerwise linear feature connectivity Z Zhou, Y Yang, X Yang, J Yan, W Hu Advances in Neural Information Processing Systems 36, 60853-60877, 2023 | 41 | 2023 |
| ICLR: In-Context Learning of Representations CF Park, A Lee, ES Lubana, Y Yang, M Okawa, K Nishi, M Wattenberg, ... The Thirteenth International Conference on Learning Representations, 2025 | 34 | 2025 |
| Practical and asymptotically optimal quantization of high-dimensional vectors in euclidean space for approximate nearest neighbor search J Gao, Y Gou, Y Xu, Y Yang, C Long, RCW Wong Proceedings of the ACM on Management of Data 3 (3), 1-26, 2025 | 24 | 2025 |
| Implicit vs unfolded graph neural networks Y Yang, T Liu, Y Wang, Z Huang, D Wipf Journal of Machine Learning Research 26 (82), 1-46, 2025 | 19* | 2025 |
| Relation of the relations: A new paradigm of the relation extraction problem Z Jin, Y Yang, X Qiu, Z Zhang arXiv preprint arXiv:2006.03719, 2020 | 19 | 2020 |
| Are neurons actually collapsed? on the fine-grained structure in neural representations Y Yang, J Steinhardt, W Hu International Conference on Machine Learning, 39453-39487, 2023 | 15 | 2023 |
| Why Propagate Alone? Parallel Use of Labels and Features on Graphs Y Wang, J Jin, W Zhang, Y Yang, J Chen, Q Gan, Y Yu, Z Zhang, Z Huang, ... arXiv preprint arXiv:2110.07190, 2021 | 13 | 2021 |
| RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm Y Yang, J Gao, W Hu arXiv preprint arXiv:2504.03717, 2025 | 5 | 2025 |
| New Evidence of the Two-Phase Learning Dynamics of Neural Networks Z Zhou, Y Yang, M Sugiyama, J Yan arXiv preprint arXiv:2505.13900, 2025 | 1 | 2025 |
| Swing-by Dynamics in Concept Learning and Compositional Generalization Y Yang, CF Park, ES Lubana, M Okawa, W Hu, H Tanaka The Thirteenth International Conference on Learning Representations, 0 | 1* | |
| An Equivariance Toolbox for Learning Dynamics Y Yang, L Ziyin arXiv preprint arXiv:2512.21447, 2025 | | 2025 |
| Topological Invariance and Breakdown in Learning Y Yang, T Poggio, I Chuang, L Ziyin arXiv preprint arXiv:2510.02670, 2025 | | 2025 |
| Provable Low-Frequency Bias of In-Context Learning of Representations Y Yang, H Tanaka, W Hu arXiv preprint arXiv:2507.13540, 2025 | | 2025 |
| HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks Y Yang, J Yang, W Hu, M Dereziński arXiv preprint arXiv:2403.18142, 2024 | | 2024 |
David WipfPrincipal Research Scientist, Amazon Web ServicesVerified email at amazon.com
