| Pyramid vision transformer: A versatile backbone for dense prediction without convolutions W Wang, E Xie, X Li, DP Fan, K Song, D Liang, T Lu, P Luo, L Shao ICCV 2021, 2021 | 2649 | 2021 |
| Mass: Masked sequence to sequence pre-training for language generation K Song, X Tan, T Qin, J Lu, TY Liu ICML 2019, 2019 | 1013 | 2019 |
| Pvt v2: Improved baselines with pyramid vision transformer W Wang, E Xie, X Li, DP Fan, K Song, D Liang, T Lu, P Luo, L Shao Computational Visual Media 8 (3), 415-424, 2022 | 737 | 2022 |
| Mpnet: Masked and permuted pre-training for language understanding K Song, X Tan, T Qin, J Lu, TY Liu NeurIPS 2020, 2020 | 599 | 2020 |
| HuggingGPT: Solving AI tasks with ChatGPT and Its Friends in Huggingface Y Shen, K Song, X Tan, D Li, W Lu, Y Zhuang NeurIPS 2023, 2023 | 290 | 2023 |
| NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search J Xu, X Tan, R Luo, K Song, J Li, T Qin, TY Liu KDD 2021, 2021 | 54 | 2021 |
| Bi-modal progressive mask attention for fine-grained recognition K Song, XS Wei, X Shu, RJ Song, J Lu IEEE Transactions on Image Processing 29, 7006-7018, 2020 | 49 | 2020 |
| SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint Z Sheng, K Song, X Tan, Y Ren, W Ye, S Zhang, T Qin AAAI 2021, 2020 | 42 | 2020 |
| Generating adversarial examples with conditional generative adversarial net P Yu, K Song, J Lu 2018 24th international conference on pattern recognition (ICPR), 676-681, 2018 | 30 | 2018 |
| Analyzing and Mitigating Interference in Neural Architecture Search J Xu, X Tan, K Song, R Luo, Y Leng, T Qin, TY Liu, J Li ICML 2022, 2021 | 22 | 2021 |
| DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling L Xue, K Song, D Wu, X Tan, NL Zhang, T Qin, WQ Zhang, TY Liu ACL 2021, 2021 | 18 | 2021 |
| Mixed-phoneme bert: Improving bert with mixed phoneme and sup-phoneme representations for text to speech G Zhang, K Song, X Tan, D Tan, Y Yan, Y Liu, G Wang, W Zhou, T Qin, ... INTERSPEECH 2022, 2022 | 16 | 2022 |
| Double path networks for sequence to sequence learning K Song, X Tan, D He, J Lu, T Qin, TY Liu COLING 2018, 2018 | 16 | 2018 |
| Coarse-to-fine: A dual-view attention network for click-through rate prediction K Song, Q Huang, F Zhang, J Lu Knowledge-Based Systems 216, 106767, 2021 | 14 | 2021 |
| Neural Machine Translation with Error Correction K Song, X Tan, J Lu IJCAI 2020, 2020 | 13 | 2020 |
| Hybrid self-attention network for machine translation K Song, X Tan, F Peng, J Lu arXiv preprint arXiv:1811.00253, 2018 | 13 | 2018 |
| LightPAFF: A two-stage distillation framework for pre-training and fine-tuning K Song, H Sun, X Tan, T Qin, J Lu, H Liu, TY Liu arXiv preprint arXiv:2004.12817, 2020 | 11 | 2020 |
| Connecting large language models with evolutionary algorithms yields powerful prompt optimizers Q Guo, R Wang, J Guo, B Li, K Song, X Tan, G Liu, J Bian, Y Yang arXiv preprint arXiv:2309.08532, 2023 | 10 | 2023 |
| DiffusionNER: Boundary Diffusion for Named Entity Recognition Y Shen, K Song, X Tan, D Li, W Lu, Y Zhuang ACL 2023, 2023 | 9 | 2023 |
| SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition Y Leng, X Tan, W Liu, K Song, R Wang, XY Li, T Qin, E Lin, TY Liu AAAI 2023, 2022 | 8 | 2022 |
Xu Tan (谭旭)Principal Research Manager, Microsoft Research Asia在 microsoft.com 的电子邮件经过验证
