| Eyes wide shut? exploring the visual shortcomings of multimodal llms S Tong, Z Liu, Y Zhai, Y Ma, Y LeCun, S Xie Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 228 | 2024 |
| Investigating the catastrophic forgetting in multimodal large language model fine-tuning Y Zhai, S Tong, X Li, M Cai, Q Qu, YJ Lee, Y Ma Conference on Parsimony and Learning (CPAL), 2024 | 122* | 2024 |
| Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning M Nakamoto, S Zhai, A Singh, M Sobol Mark, Y Ma, C Finn, A Kumar, ... Advances in Neural Information Processing Systems (NIPS) 36, 2024 | 106 | 2024 |
| Learning to reconstruct 3d manhattan wireframes from a single image Y Zhou, H Qi, Y Zhai, Q Sun, Z Chen, LY Wei, Y Ma Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 | 78 | 2019 |
| Complete dictionary learning via l4-norm maximization over the orthogonal group Y Zhai, Z Yang, Z Liao, J Wright, Y Ma Journal of Machine Learning Research (JMLR) 21 (165), 1-68, 2020 | 73 | 2020 |
| Unpacking reward shaping: Understanding the benefits of reward engineering on sample complexity A Gupta, A Pacchiano, Y Zhai, S Kakade, S Levine Advances in Neural Information Processing Systems (NIPS) 35, 15281-15295, 2022 | 68 | 2022 |
| Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning Y Zhai, H Bai, Z Lin, J Pan, S Tong, Y Zhou, A Suhr, S Xie, Y LeCun, Y Ma, ... arXiv preprint arXiv:2405.10292, 2024 | 38 | 2024 |
| Geometric analysis of nonconvex optimization landscapes for overcomplete learning Q Qu, Y Zhai, X Li, Y Zhang, Z Zhu International Conference on Learning Representations (ICLR), 2020 | 32 | 2020 |
| Convolutional normalization: Improving deep convolutional network robustness and training S Liu, X Li, Y Zhai, C You, Z Zhu, C Fernandez-Granda, Q Qu Advances in neural information processing systems (NIPS) 34, 28919-28928, 2021 | 28 | 2021 |
| Computational benefits of intermediate rewards for goal-reaching policy learning Y Zhai, C Baek, Z Zhou, J Jiao, Y Ma Journal of Artificial Intelligence Research (JAIR) 73, 847-896, 2022 | 26 | 2022 |
| Understanding l4-based dictionary learning: Interpretation, stability, and robustness Y Zhai, H Mehta, Z Zhou, Y Ma International conference on learning representations (ICLR), 2020 | 23 | 2020 |
| Lmrl gym: Benchmarks for multi-turn reinforcement learning with language models M Abdulhai, I White, C Snell, C Sun, J Hong, Y Zhai, K Xu, S Levine arXiv preprint arXiv:2311.18232, 2023 | 20 | 2023 |
| Analysis of the optimization landscapes for overcomplete representation learning Q Qu, Y Zhai, X Li, Y Zhang, Z Zhu arXiv preprint arXiv:1912.02427, 2019 | 17 | 2019 |
| Understanding the complexity gains of single-task rl with a curriculum Q Li, Y Zhai, Y Ma, S Levine International Conference on Machine Learning (ICML), 20412-20451, 2023 | 15 | 2023 |
| RLIF: Interactive Imitation Learning as Reinforcement Learning J Luo, P Dong, Y Zhai, Y Ma, S Levine International conference on learning representations (ICLR), 2023 | 11 | 2023 |
| White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? Y Yu, S Buchanan, D Pai, T Chu, Z Wu, S Tong, H Bai, Y Zhai, ... arXiv preprint arXiv:2311.13110, 2023 | 10 | 2023 |
| Closed-loop transcription via convolutional sparse coding X Dai, K Chen, S Tong, J Zhang, X Gao, M Li, D Pai, Y Zhai, XI Yuan, ... Conference on Parsimony and Learning (CPAL), 2024 | 6 | 2024 |
| SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training T Chu, Y Zhai, J Yang, S Tong, S Xie, D Schuurmans, QV Le, S Levine, ... arXiv preprint arXiv:2501.17161, 2025 | | 2025 |
Yi Ma (马毅)Director of School of Computing & Data Science, Hong Kong University; Professor of EECS, UC Berkeley確認したメール アドレス: hku.hk