publications | Ming Li

Jan 2026	Two papers were accepted by ICLR 2026!
Sep 2025	Two papers were accepted by NeurIPS 2025!
Aug 2025	Two papers were accepted by EMNLP 2025!
Jul 2025	One paper was accepted by COLM 2025!
May 2025	Three papers were accepted by ACL 2025, including one oral!
Jan 2025	One paper was accepted by NAACL 2025!
Jan 2025	One paper was accepted by ICLR 2025!
May 2024	Three papers were accepted by ACL 2024!
Mar 2024	One paper was accepted by NAACL 2024!
Oct 2023	One paper was accepted by Instruction Workshop @ NeurIPS 2023!
Oct 2023	One paper was accepted by EMNLP 2023!

favorite preprints

Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

Ming Li , Xirui Li , and Tianyi Zhou

2026

arXiv Bib PDF Code Website

@misc{li2026doessocializationemergeai,
  title = {Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook},
  author = {Li, Ming and Li, Xirui and Zhou, Tianyi},
  year = {2026},
  eprint = {2602.14299},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url = {https://arxiv.org/abs/2602.14299},
}

When AI Navigates the Fog of War

Ming Li , Xirui Li , and Tianyi Zhou

2026

arXiv Bib PDF Code Website

@misc{li2026ainavigatesfogwar,
  title = {When AI Navigates the Fog of War},
  author = {Li, Ming and Li, Xirui and Zhou, Tianyi},
  year = {2026},
  eprint = {2603.16642},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
  url = {https://arxiv.org/abs/2603.16642},
}

selected publications

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory

Ming Li , Nan Zhang , Chenrui Fan , and 6 more authors

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , Nov 2025

arXiv Bib PDF Code Website

@inproceedings{li-etal-2025-understanding,
  title = {Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld{'}s Episode Theory},
  author = {Li, Ming and Zhang, Nan and Fan, Chenrui and Jiao, Hong and Fu, Yanbin and Peters, Sydney and Xu, Qingshu and Lissitz, Robert and Zhou, Tianyi},
  editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  month = nov,
  year = {2025},
  address = {Suzhou, China},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.emnlp-main.922/},
  doi = {10.18653/v1/2025.emnlp-main.922},
  pages = {18267--18288},
  isbn = {979-8-89176-332-6},
}

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Ming Li , Yanhong Li , and Tianyi Zhou

In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Jul 2025

arXiv Bib PDF Code Website

@inproceedings{li-etal-2025-happened,
  title = {What Happened in {LLM}s Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective},
  author = {Li, Ming and Li, Yanhong and Zhou, Tianyi},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month = jul,
  year = {2025},
  address = {Vienna, Austria},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.acl-long.1545/},
  doi = {10.18653/v1/2025.acl-long.1545},
  pages = {32017--32154},
  isbn = {979-8-89176-251-0},
}

Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning

Ming Li , Pei Chen , Chenguang Wang , and 5 more authors

In Findings of the Association for Computational Linguistics: ACL 2025 , Jul 2025

arXiv Bib PDF Code Website

@inproceedings{li-etal-2025-mosaic,
  title = {Mosaic-{IT}: Cost-Free Compositional Data Synthesis for Instruction Tuning},
  author = {Li, Ming and Chen, Pei and Wang, Chenguang and Zhao, Hongyu and Liang, Yijun and Hou, YuPeng and Liu, Fuxiao and Zhou, Tianyi},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
  month = jul,
  year = {2025},
  address = {Vienna, Austria},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.findings-acl.1297/},
  doi = {10.18653/v1/2025.findings-acl.1297},
  pages = {25287--25318},
  isbn = {979-8-89176-256-5},
}

ATLAS: Agent Tuning via Learning Critical Steps

Zhixun Chen , Ming Li , Yuxuan Huang , and 3 more authors

In Findings of the Association for Computational Linguistics: ACL 2025 , Jul 2025

arXiv Bib PDF

@inproceedings{chen-etal-2025-atlas,
  title = {{ATLAS}: Agent Tuning via Learning Critical Steps},
  author = {Chen, Zhixun and Li, Ming and Huang, Yuxuan and Du, Yali and Fang, Meng and Zhou, Tianyi},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
  month = jul,
  year = {2025},
  address = {Vienna, Austria},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.findings-acl.1299/},
  doi = {10.18653/v1/2025.findings-acl.1299},
  pages = {25334--25349},
  isbn = {979-8-89176-256-5},
}

RuleR: Improving LLM Controllability by Rule-based Data Recycling

Ming Li , Han Chen , Chenguang Wang , and 3 more authors

In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers) , Apr 2025

arXiv Bib PDF Code Website

@inproceedings{li-etal-2025-ruler,
  title = {{R}ule{R}: Improving {LLM} Controllability by Rule-based Data Recycling},
  author = {Li, Ming and Chen, Han and Wang, Chenguang and Nguyen, Dang and Li, Dianqi and Zhou, Tianyi},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)},
  month = apr,
  year = {2025},
  address = {Albuquerque, New Mexico},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.naacl-short.78/},
  doi = {10.18653/v1/2025.naacl-short.78},
  pages = {926--943},
  isbn = {979-8-89176-190-2},
}

BenTo: Benchmark Reduction with In-Context Transferability

Hongyu Zhao , Ming Li , Lichao Sun , and 1 more author

In The Thirteenth International Conference on Learning Representations , Apr 2025

arXiv Bib PDF Code Website

@inproceedings{zhao2025bento,
  title = {BenTo: Benchmark Reduction with In-Context Transferability},
  author = {Zhao, Hongyu and Li, Ming and Sun, Lichao and Zhou, Tianyi},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
  url = {https://openreview.net/forum?id=ki7b0qD11r},
}

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Chenrui Fan , Ming Li , Lichao Sun , and 1 more author

In Second Conference on Language Modeling , Apr 2025

arXiv Bib PDF Code Website

@inproceedings{fan2025missing,
  title = {Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?},
  author = {Fan, Chenrui and Li, Ming and Sun, Lichao and Zhou, Tianyi},
  booktitle = {Second Conference on Language Modeling},
  year = {2025},
  url = {https://openreview.net/forum?id=ufozo2Wc9e},
}

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

Yijun Liang , Ming Li , Chenrui Fan , and 7 more authors

In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track , Apr 2025

arXiv Bib PDF Code Website

@inproceedings{liang2025colorbench,
  title = {ColorBench: Can {VLM}s See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness},
  author = {Liang, Yijun and Li, Ming and Fan, Chenrui and Li, Ziyue and Nguyen, Dang and Cobbina, Kwesi Adu and Bhardwaj, Shweta and Chen, Jiuhai and Liu, Fuxiao and Zhou, Tianyi},
  booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year = {2025},
  url = {https://openreview.net/forum?id=rauWoTWls3},
}

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Ming Li , Yong Zhang , Shwai He , and 5 more authors

In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Aug 2024

arXiv Bib PDF Code Website

@inproceedings{li-etal-2024-superfiltering,
  title = {Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning},
  author = {Li, Ming and Zhang, Yong and He, Shwai and Li, Zhitao and Zhao, Hongyu and Wang, Jianzong and Cheng, Ning and Zhou, Tianyi},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month = aug,
  year = {2024},
  address = {Bangkok, Thailand},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.acl-long.769},
  pages = {14255--14273},
}

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Ming Li , Lichang Chen , Jiuhai Chen , and 3 more authors

In Findings of the Association for Computational Linguistics ACL 2024 , Aug 2024

arXiv Bib PDF Code Website

@inproceedings{li-etal-2024-selective,
  title = {Selective Reflection-Tuning: Student-Selected Data Recycling for {LLM} Instruction-Tuning},
  author = {Li, Ming and Chen, Lichang and Chen, Jiuhai and He, Shwai and Gu, Jiuxiang and Zhou, Tianyi},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  booktitle = {Findings of the Association for Computational Linguistics ACL 2024},
  month = aug,
  year = {2024},
  address = {Bangkok, Thailand and virtual meeting},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.findings-acl.958},
  pages = {16189--16211},
}

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements

Ming Li , Jiuhai Chen , Lichang Chen , and 1 more author

In Findings of the Association for Computational Linguistics: ACL 2024 , Aug 2024

arXiv Bib PDF Code Website

@inproceedings{li-etal-2024-llms-speak,
  title = {Can {LLM}s Speak For Diverse People? Tuning {LLM}s via Debate to Generate Controllable Controversial Statements},
  author = {Li, Ming and Chen, Jiuhai and Chen, Lichang and Zhou, Tianyi},
  editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2024},
  month = aug,
  year = {2024},
  address = {Bangkok, Thailand},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.findings-acl.956/},
  doi = {10.18653/v1/2024.findings-acl.956},
  pages = {16160--16176},
}

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

Ming Li , Yong Zhang , Zhitao Li , and 6 more authors

In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , Jun 2024

arXiv Bib PDF Code Website

@inproceedings{li-etal-2024-quantity,
  title = {From Quantity to Quality: Boosting {LLM} Performance with Self-Guided Data Selection for Instruction Tuning},
  author = {Li, Ming and Zhang, Yong and Li, Zhitao and Chen, Jiuhai and Chen, Lichang and Cheng, Ning and Wang, Jianzong and Zhou, Tianyi and Xiao, Jing},
  editor = {Duh, Kevin and Gomez, Helena and Bethard, Steven},
  booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  month = jun,
  year = {2024},
  address = {Mexico City, Mexico},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.naacl-long.421},
  pages = {7595--7628},
}

Reflection-Tuning: Recycling Data for Better Instruction-Tuning

Ming Li , Lichang Chen , Jiuhai Chen , and 2 more authors

In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following , Jun 2023

arXiv Bib PDF Code Website

@inproceedings{li2023reflectiontuning,
  title = {Reflection-Tuning: Recycling Data for Better Instruction-Tuning},
  author = {Li, Ming and Chen, Lichang and Chen, Jiuhai and He, Shwai and Zhou, Tianyi},
  booktitle = {NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following},
  year = {2023},
  url = {https://openreview.net/forum?id=xaqoZZqkPU},
}