| Do Transformers Really Perform Badly for Graph Representation? C Ying, T Cai, S Luo, S Zheng, G Ke, D He, Y Shen, TY Liu NeurIPS 2021, arXiv preprint arXiv:2106.05234, 2021 | 2182 | 2021 |
| Medusa: Simple llm inference acceleration framework with multiple decoding heads T Cai, Y Li, Z Geng, H Peng, JD Lee, D Chen, T Dao ICML 2024, arXiv preprint arXiv:2401.10774, 2024 | 523 | 2024 |
| Snapkv: Llm knows what you are looking for before generation Y Li, Y Huang, B Yang, B Venkitesh, A Locatelli, H Ye, T Cai, P Lewis, ... NeurIPS 2024, arXiv preprint arXiv:2404.14469, 2024 | 385 | 2024 |
| Graphnorm: A principled approach to accelerating graph neural network training T Cai, S Luo, K Xu, D He, T Liu, L Wang ICML 2021, arXiv preprint arXiv:2009.03294, 2020 | 277 | 2020 |
| Large language models as tool makers T Cai, X Wang, T Ma, X Chen, D Zhou ICLR 2024, arXiv preprint arXiv:2305.17126, 2023 | 252 | 2023 |
| Adversarially robust generalization just requires more unlabeled data R Zhai, T Cai, D He, C Dan, K He, J Hopcroft, L Wang arXiv preprint arXiv:1906.00555, 2019 | 191 | 2019 |
| Towards a Theoretical Framework of Out-of-Distribution Generalization H Ye, C Xie, T Cai, R Li, Z Li, L Wang NeurIPS 2021, arXiv preprint arXiv:2106.04496, 2021 | 168 | 2021 |
| Convergence of adversarial training in overparametrized neural networks R Gao, T Cai, H Li, CJ Hsieh, L Wang, JD Lee NeurIPS 2019 Spotlight, arXiv preprint arXiv:1906.07916, 13029-13040, 2019 | 165 | 2019 |
| Rest: Retrieval-based speculative decoding Z He, Z Zhong, T Cai, JD Lee, D He NAACL 2024, arXiv preprint arXiv:2311.08252, 2023 | 154 | 2023 |
| What Makes Convolutional Models Great on Long Sequence Modeling? Y Li, T Cai, Y Zhang, D Chen, D Dey ICLR 2023, arXiv preprint arXiv:2210.09298, 2022 | 144 | 2022 |
| DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models M Li, T Cai, J Cao, Q Zhang, H Cai, J Bai, Y Jia, MY Liu, K Li, S Han CVPR 2024, arXiv preprint arXiv:2402.19481, 2024 | 122 | 2024 |
| Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot J Su, Y Chen, T Cai, T Wu, R Gao, L Wang, JD Lee NeurIPS 2020, arXiv preprint arXiv:2009.11094, 2020 | 114 | 2020 |
| Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models M Li, Y Lin, Z Zhang, T Cai, X Li, J Guo, E Xie, C Meng, JY Zhu, S Han ICLR 2025, arXiv preprint arXiv:2411.05007, 2024 | 96 | 2024 |
| Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons B Zhang, T Cai, Z Lu, D He, L Wang ICML 2021, arXiv preprint arXiv:2102.05363, 12368-12379, 2021 | 92 | 2021 |
| Locally differentially private (contextual) bandits learning K Zheng, T Cai, W Huang, Z Li, L Wang NeurIPS 2020, arXiv preprint arXiv:2006.00701, 2020 | 81 | 2020 |
| Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems T Cai, R Gao, J Hou, S Chen, D Wang, D He, Z Zhang, L Wang NeurIPS 2019 Beyond First Order Methods in ML Workshop, arXiv preprint arXiv …, 2019 | 81 | 2019 |
| A Theory of Label Propagation for Subpopulation Shift T Cai, R Gao, JD Lee, Q Lei ICML 2021, arXiv preprint arXiv:2102.11203, 2021 | 68 | 2021 |
| Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding S Luo, S Li, T Cai, D He, D Peng, S Zheng, G Ke, L Wang, TY Liu NeurIPS 2021, arXiv preprint arXiv:2106.12566, 2021 | 66 | 2021 |
| Jetmoe: Reaching llama2 performance with 0.1 m dollars Y Shen, Z Guo, T Cai, Z Qin arXiv preprint arXiv:2404.07413, 2024 | 60 | 2024 |
| MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations K Huang, J Guo, Z Li, X Ji, J Ge, W Li, Y Guo, T Cai, H Yuan, R Wang, ... arXiv preprint arXiv:2502.06453, 2025 | 52 | 2025 |
Di HePeking UniversityVerified email at pku.edu.cn
