| Augmentation-adapted retriever improves generalization of language models as generic plug-in Z Yu, C Xiong, S Yu, Z Liu ACL 2023, 2023 | 90 | 2023 |
| An in-depth look at gemini's language abilities SN Akter, Z Yu, A Muhamed, T Ou, A Bäuerle, ÁA Cabrera, K Dholakia, ... arXiv preprint arXiv:2312.11444, 2023 | 72* | 2023 |
| MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models Z Yu, S Das, C Xiong NeurIPS 2024, 2024 | 56 | 2024 |
| Group-Level Data Selection for Efficient Pretraining Z Yu, F Peng, J Lei, A Overwijk, W Yih, C Xiong NeurIPS 2025, 2025 | 5* | 2025 |
| Automatic label sequence generation for prompting sequence-to-sequence models Z Yu, T Gao, Z Zhang, Y Lin, Z Liu, M Sun, J Zhou COLING 2022, 2022 | 5 | 2022 |
| Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning X Li, Z Yu, C Xiong ICLR 2025, 2024 | 4 | 2024 |
| Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search W Shi, Z Yu, F Feng, X He, C Xiong arXiv preprint arXiv:2502.00955, 2025 | 3 | 2025 |
| FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models H Kang, Z Yu, C Xiong arXiv preprint arXiv:2505.20225, 2025 | 1 | 2025 |
| RePro: Training Language Models to Faithfully Recycle the Web for Pretraining Z Yu, C Xiong arXiv preprint arXiv:2510.10681, 2025 | | 2025 |
Chenyan XiongAssociate Professor, Carnegie Mellon UniversityVerified email at cs.cmu.edu
