Research

@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}
}

@article{BASIRIFARD2026136204,
  title = {A Hyperparameter Tuning Strategy for an {{LSTM}} Model to Simulate Reservoir Outflows: Large-Scale Evaluation across 441 Dams in the {{CONUS}}},
  author = {Basirifard, Milad and Zhang, Jiaorui and Cao, Jie and Liu, Xiaofeng and Hong, Yi and Yang, Tiantian},
  year = {2026},
  journal = {Journal of Hydrology},
  volume = {679},
  pages = {136204},
  issn = {0022-1694},
  doi = {10.1016/j.jhydrol.2026.136204},
  url = {https://www.sciencedirect.com/science/article/pii/S0022169426013016}
}

@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{cai2026llmpowered,
  title = {LLM-Powered Multi-Agent Attacks on Cooperative Spectrum Sensing},
  author = {Cai, Yu and He, Ziang and Luo, Yanyan and Zhang, Ziyue and Cao, Jie and Liu, Yuchen and Luo, Zhengping and Zhao, Shangqing},
  booktitle = {Proceedings of the IEEE International Conference on Computer Communications and Networks (ICCCN)},
  year = {2026}
}

@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}
}

@inproceedings{naim2025edm,
  title = {Towards Actionable Pedagogical Feedback: A Multi- Perspective Analysis of Mathematics Teaching and Tutoring Dialogue},
  booktitle = {Proceedings of the 18th International Conference on Educational Data Mining},
  author = {Naim, Jannatun and Cao, Jie and Tasneem, Fareen and Jacobs, Jennifer and Milne, Brent and Martin, James and Sumner, Tamara},
  year = {2025},
  month = jul,
  pages = {328--341},
  publisher = {International Educational Data Mining Society},
  doi = {10.5281/zenodo.15870177},
  venue = {Palermo, Italy},
  url = "https://educationaldatamining.org/EDM2025/proceedings/2025.EDM.long-papers.201/index.html"
}

@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 = {Proceedings of the 31st International Conference on Computational Linguistics},
  pages = {7671--7684},
  year = {2025},
  address = {Abu Dhabi, UAE},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.coling-main.513/}
}

@inproceedings{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},
  booktitle = {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}
}