| A theoretical analysis on feature learning in neural networks: Emergence from inputs and advantage over fixed features Z Shi, J Wei, Y Liang arXiv preprint arXiv:2206.01717, 2022 | 52 | 2022 |
| Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning Z Xu, Z Shi, J Wei, F Mu, Y Li, Y Liang arXiv preprint arXiv:2402.15017, 2024 | 13 | 2024 |
| Provable Guarantees for Neural Networks via Gradient Feature Learning Z Shi, J Wei, Y Liang arXiv preprint arXiv:2310.12408, 2023 | 9 | 2023 |
| Improving Foundation Models for Few-Shot Learning via Multitask Finetuning Z Xu, Z Shi, J Wei, Y Li, Y Liang ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation …, 0 | 7* | |
| Interfacing Foundation Models' Embeddings X Zou, L Li, J Wang, J Yang, M Ding, J Wei, Z Yang, F Li, H Zhang, S Liu, ... arXiv preprint arXiv:2312.07532, 2023 | 1 | 2023 |
| Why Larger Language Models Do In-context Learning Differently? Z Shi, J Wei, Y Xu, Zhuoyan, Liang ICML 2024: International Conference on Machine Learning, 2024 | | 2024 |
| How market structure drives commodity prices B Li, KYM Wong, AHM Chan, TY So, H Heimonen, J Wei, D Saad Journal of Statistical Mechanics: Theory and Experiment 2017 (11), 113405, 2017 | | 2017 |
| Adopting Linear Model to Accelerate Neural Network Training Y Liu, J Wei, Z Ma, H Jiang, Y Zhang | | |
