@article{yan2026grl,
  title = {AI Agent for Hydrologic Modeling: Definition, Development and Application},
  author = {Yan, Songkun and Chen, Mengye and Li, Zhi and Wen, Yixin and Zhu, Siyu and Zhang, Mofan and Liu, Di and Cao, Jie and Chen, Xiaodong and Deng, Chengbin and Yang, Tiantian and Hong, Yang},
  journal = {Geophysical Research Letters},
  year = {2026},
  month = {June},
  url = {https://essopenarchive.org/doi/full/10.22541/essoar.176894821.13120988/v1}
}

@inproceedings{liu2026beyond,
  title = {Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing},
  author = {Liu, Yiming and Zhang, Ziyue and Xu, Zhichao and Yu, Xin and Tang, Yingheng and Jiang, Tianyu and Cao, Jie},
  booktitle = {Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2026)},
  year = {2026},
  url = {https://arxiv.org/abs/2607.01964}
}

@article{xu2025rethinking,
  title = {Rethinking On-policy Optimization for Query Augmentation},
  author = {Xu, Zhichao and Zhuang, Shengyao and Ma, Xueguang and Chen, Bingsen and Tian, Yijun and Mo, Fengran and Li, Tao and Cao, Jie and Srikumar, Vivek},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2026},
  month = {June},
  url = {https://openreview.net/forum?id=mmqbjhz5Br}
}

@misc{li2026hydroagentclosinggapfrontier,
  title = {HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL},
  author = {Li, Zhi and Yan, Songkun and Cao, Jie and Zhang, Mofan and Wei, Anjiang and Yoo, Jinwoong and Hong, Yang},
  year = {2026},
  eprint = {2605.17792},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2605.17792}
}

@article{tang2026matterchat,
  title = {A Multimodal Large Language Model for Materials Science},
  author = {Yingheng Tang and Wenbin Xu and Jie Cao and Weilu Gao and Steve Farrell and Benjamin Erichson and Michael W. Mahoney and Andy Nonaka and Zhi Yao},
  journal = {Nature Machine Intelligence},
  year = {2026},
  doi = {10.1038/s42256-026-01214-y},
  url = {https://doi.org/10.1038/s42256-026-01214-y},
  publisher = {Nature Publishing Group}
}

@inproceedings{li2026translation,
  title = {Translation via Annotation: A Computational Study of Translating Classical Chinese into Japanese},
  author = {Li, Zilong and Cao, Jie},
  booktitle = {Proceedings of the 2026 Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026)},
  year = {2026},
  url = {https://aclanthology.org/2026.eacl-long.285/}
}

@article{ZHANG2025134145,
  title = {A {{Mamba-type}} of Deep State Space Model for Reservoir Release Simulation with a Large-Scale Verification over 441 Dams across {{CONUS}}},
  author = {Zhang, Jiaorui and Yue, Haowen and Basirifard, Milad and Cao, Jie and Yang, Tiantian},
  year = {2025},
  journal = {Journal of Hydrology},
  pages = {134145},
  issn = {0022-1694},
  doi = {10.1016/j.jhydrol.2025.134145},
  url = {https://www.sciencedirect.com/science/article/pii/S0022169425014830},
  keywords = {Large scale,Release simulation,SHAP,Structured State Space Model,Water management}
}

@inproceedings{jayanth2025emnlp,
  title = {Do LLMs Encode Frame Semantics? Evidence from Frame Identification},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  author = {Chundru, Jayanth Krishna and Poddar, Rudrashis and Cao, Jie and Jiang, Tianyu},
  year = {2025},
  month = Nov,
  publisher = "Association for Computational Linguistics",
  venue = {Suzhou, China},
  url = "https://aclanthology.org/2025.emnlp-main.1499/"
}

@inproceedings{huynh2025ounlp,
  title = {OUNLP at TSAR 2025 Shared Task: Multi-Round Text Simplifier via Code Generation},
  author = {Huynh, Cuong and Cao, Jie},
  booktitle = {Proceedings of the Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)},
  year = {2025},
  url = {https://aclanthology.org/2025.tsar-1.19/}
}

@article{vis-pruning2024,
  title = {"Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches},
  author = {Li, Zhimin and Liu, Shusen and Yu, Xin and Kailkhura, Bhavya and Cao, Jie and Diffenderfer, James Daniel and Bremer, Peer-Timo and Pascucci, Valerio},
  url = {https://doi.org/10.1109/tvcg.2024.3514996},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  year = {2024}
}

@article{songkun2025sea,
  title = {AQUAH: Automatic Quantification and Unified Agent in Hydrology},
  author = {Yan, Songkun and Li, Zhi and Zhu, Siyu and Wen, Yixin and Zhang, Mofan and Chen, Mengye and Cao, Jie and Hong, Yang},
  journal = {1st Workshop on Sustainability with Earth Observation and AI (co-located with ICCV 2025)},
  url = {https://arxiv.org/abs/2508.02936},
  year = {2025}
}

@inproceedings{talkmove-llm-2024,
  author = {Moreau-Pernet, Baptiste and Tian, Yu and Sawaya, Sandra and Foltz, Peter and Cao, Jie and Milne, Brent and Christie, Thomas},
  title = {Classifying Tutor Discursive Moves at Scale in Mathematics Classrooms with Large Language Models},
  year = {2024},
  isbn = {9798400706332},
  publisher = {Association for Computing Machinery},
  url = {https://doi.org/10.1145/3657604.3664664},
  doi = {10.1145/3657604.3664664},
  booktitle = {Proceedings of the Eleventh ACM Conference on Learning @ Scale},
  pages = {361–365},
  numpages = {5},
  keywords = {discourse analysis, llm classification, math tutor training},
  location = {Atlanta, GA, USA},
  series = {L@S '24}
}

@inproceedings{talkmove-coling-2024,
  title = {Enhancing Talk Moves Analysis in Mathematics Tutoring through Classroom Teaching Discourse},
  author = {Cao, Jie and Suresh, Abhijit and Jacobs, Jennifer and Clevenger, Charis and Howard, Amanda and Brown, Chelsea and Milne, Brent and Fischaber, Tom and Sumner, Tamara and Martin, James H.},
  booktitle = {The 31st International Conference on Computational Linguistics},
  year = {2025}
}

@article{ananya-acl23,
  title = {Mind the Gap between the Application Track and the Real World},
  author = {Ganesh, Ananya and Cao, Jie and Perkoff, E. Margaret and Southwell, Rosy and Palmer, Martha and Kann, Katharina},
  journal = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023},
  year = {2023}
}

@inproceedings{perkoff2023comparing,
  title = {Comparing Neural Question Generation Architectures for Reading Comprehension},
  author = {Perkoff, E. Margaret and Bhattacharyya, Abhidip and Cai, Jon and Cao, Jie},
  booktitle = {Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)},
  year = {2023},
  url = {https://aclanthology.org/2023.bea-1.47/}
}

@article{cao-jigsaw23,
  title = {Designing an AI Partner for Jigsaw Classrooms},
  author = {Cao, Jie and Dickler, Rachel and Grace, Marie and Roncone, Alessandro and Hirshfield, Leanne and Walker, Marilyn and Palmer, Martha},
  journal = {Workshop on Language-Based AI Character Interaction with Children},
  year = {2023}
}

@article{cao-umap23,
  title = {A Comparative Analysis of Automatic Speech Recognition Errors in Small Group Classroom Discourse},
  author = {Cao, Jie and Ganesh, Ananya and Cai, Jon and Southwell, Rosy and Perkoff, Margaret and Regan, Michael and Kann, Katharina and Martin, James and Palmer, Martha and D'Mello, Sidney},
  journal = {Proceedings of the 31st ACM Conference on User Modeling Adaptation and Personalization},
  year = {2023}
}

@article{jon-dda2022,
  title = {Dependency Dialogue Acts — Annotation Scheme and Case Study},
  author = {Cai, Jon and King, Brendan D. and Perkoff, Margaret and Dudy, Shiran and Cao, Jie and Grace, Marie and Wojarnik, Natalia and Ganesh, Ananya and Martin, James and Palmer, Martha and Walker, Marilyn and Flanigan, Jeffrey},
  journal = {The 13th International Workshop on Spoken Dialogue Systems Technology},
  year = {2022}
}

@article{dissertation-proquest,
  title = {Inductive Biases for Deep Linguistic Structured Prediction with Independent Factorization},
  author = {Cao, Jie},
  journal = {Available from ProQuest Dissertations & Theses A&I;ProQuest Dissertations & Theses Global. (2777357718)},
  year = {2022}
}

@article{cao2021dbqencoder,
  title = {Database Workload Characterization with Query Plan Encoders},
  author = {Paul, Debjyoti and Cao, Jie and Li, Feifei and Srikumar, Vivek},
  journal = {Proceedings of the VLDB Endowment},
  volume = {15},
  number = {4},
  pages = {923--935},
  year = {2021},
  publisher = {VLDB Endowment}
}

@inproceedings{cao2021comparative,
  title = {A Comparative Study on Schema-Guided Dialogue State Tracking},
  author = {Cao, Jie and Zhang, Yi},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages = {782--796},
  year = {2021}
}

@inproceedings{cao2019amazon,
  title = {Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring},
  author = {Cao, Jie and Zhang, Yi and Youssef, Adel and Srikumar, Vivek},
  booktitle = {Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the Conference on Natural Language Learning},
  pages = {138--148},
  year = {2019}
}

@inproceedings{rhetorical-poetry2019,
  title = {Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation},
  author = {Liu, Zhiqiang and Fu, Zuohui and Cao, Jie and {de Melo}, Gerard and Tam, Yik-Cheung and Niu, Cheng and Zhou, Jie},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  location = {Florence, Italy}
}

@inproceedings{cao2019observing,
  title = {Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes},
  author = {Cao, Jie and Tanana, Michael and Imel, Zac and Poitras, Eric and Atkins, David and Srikumar, Vivek},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  location = {Florence, Italy}
}

@inproceedings{jie2019dstc,
  title = {End-to-end Gated Self-attentive Memory Network for Dialog Response Selection},
  author = {Sun, Shuo and Tam, Yik-Cheung and Cao, Jie and Yan, Canxiang and Fu, Zuohui and Niu, Cheng and Zhou, Jie},
  booktitle = {AAAI DSTC7 Workshop (Equal Contribution)},
  year = {2019},
  location = {Honolulu, USA}
}

@inproceedings{ke2015distributed,
  title = {A Distributed SVM Method Based on the Iterative MapReduce},
  author = {Ke, Xijiang and Jin, Hai and Xie, Xia and Cao, Jie},
  booktitle = {Semantic Computing (ICSC), IEEE International Conference on},
  pages = {116--119},
  year = {2015},
  organization = {IEEE}
}

@inproceedings{xie2012jrbridge,
  title = {JRBridge: A framework of large-scale statistical computing for R},
  author = {Xie, Xia and Cao, Jie and Jin, Hai and Ke, Xijiang and Cao, Wenzhi},
  booktitle = {Services Computing Conference (APSCC), IEEE Asia-Pacific},
  pages = {27--34},
  year = {2012},
  organization = {IEEE}
}