publications

2025

1. NAACL

   Octopus: On-device language model for function calling of software APIs

   Wei Chen, Zhiyuan Li, and Mingyuan Ma

   In Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Industry Track, 2025

   arXiv Bib HTML

   @inproceedings{chen2025octopus,
     title = {Octopus: On-device language model for function calling of software {APIs}},
     author = {Chen, Wei and Li, Zhiyuan and Ma, Mingyuan},
     booktitle = {Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics: Industry Track},
     pages = {329--339},
     year = {2025},
   }

2. EMAS

   Octo-planner: On-device Language Model for Planner-Action Agents

   Wei Chen, Zhiyuan Li, Zhen Guo, and 1 more author

   In Proceedings of the Workshop on Empowering Multi-Agent Systems (EMAS 2025), 2025

   arXiv Bib HTML

   @inproceedings{chen2025octoplanner,
     title = {Octo-planner: On-device Language Model for Planner-Action Agents},
     author = {Chen, Wei and Li, Zhiyuan and Guo, Zhen and Shen, Yikang},
     booktitle = {Proceedings of the Workshop on Empowering Multi-Agent Systems (EMAS 2025)},
     year = {2025},
   }

3. ICDM

   DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models

   Honghui Xu, Shiva Shrestha, Wei Chen, and 2 more authors

   In IEEE International Conference on Data Mining (ICDM), 2025

   Best Paper Runner-Up Award

   arXiv Bib HTML

   @inproceedings{xu2025dpfedlora,
     title = {{DP-FedLoRA}: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models},
     author = {Xu, Honghui and Shrestha, Shiva and Chen, Wei and Li, Zhiyuan and Cai, Zhipeng},
     booktitle = {IEEE International Conference on Data Mining (ICDM)},
     year = {2025},
     note = {Best Paper Runner-Up Award},
   }

2024

1. arXiv

   AutoNeural: Co-Designing Vision-Language Models for NPU Inference

   Wei Chen, Liangmin Wu, Yunhai Hu, and 8 more authors

   arXiv preprint arXiv:2512.02924, 2024

   arXiv Bib HTML

   @article{chen2024autoneural,
     title = {{AutoNeural}: Co-Designing Vision-Language Models for {NPU} Inference},
     author = {Chen, Wei and Wu, Liangmin and Hu, Yunhai and Li, Zhiyuan and Cheng, Zhiyuan and Qian, Yicheng and Zhu, Lingyue and Hu, Zhipeng and Liang, Luoyi and Tang, Qiang and others},
     journal = {arXiv preprint arXiv:2512.02924},
     year = {2024},
   }

2. arXiv

   OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference

   Wei Chen, Zhiyuan Li, and Shuo Xin

   arXiv preprint arXiv:2412.11475, 2024

   arXiv Bib HTML

   @article{chen2024omnivlm,
     title = {{OmniVLM}: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference},
     author = {Chen, Wei and Li, Zhiyuan and Xin, Shuo},
     journal = {arXiv preprint arXiv:2412.11475},
     year = {2024},
   }

3. arXiv

   Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

   Wei Chen, Zhiyuan Li, Shuo Xin, and 1 more author

   arXiv preprint arXiv:2408.15518, 2024

   arXiv Bib HTML

   @article{chen2024dolphin,
     title = {Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models},
     author = {Chen, Wei and Li, Zhiyuan and Xin, Shuo and Wang, Yihao},
     journal = {arXiv preprint arXiv:2408.15518},
     year = {2024},
   }

4. arXiv

   Octopus v4: Graph of language models

   Wei Chen and Zhiyuan Li

   arXiv preprint arXiv:2404.19296, 2024

   arXiv Bib HTML

   @article{chen2024octopusv4,
     title = {Octopus v4: Graph of language models},
     author = {Chen, Wei and Li, Zhiyuan},
     journal = {arXiv preprint arXiv:2404.19296},
     year = {2024},
   }

5. arXiv

   Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent

   Wei Chen and Zhiyuan Li

   arXiv preprint arXiv:2404.11459, 2024

   arXiv Bib HTML

   @article{chen2024octopusv3,
     title = {Octopus v3: Technical Report for On-device Sub-billion Multimodal {AI} Agent},
     author = {Chen, Wei and Li, Zhiyuan},
     journal = {arXiv preprint arXiv:2404.11459},
     year = {2024},
   }

6. arXiv

   Octopus v2: On-device language model for super agent

   Wei Chen and Zhiyuan Li

   arXiv preprint arXiv:2404.01744, 2024

   arXiv Bib HTML

   @article{chen2024octopusv2,
     title = {Octopus v2: On-device language model for super agent},
     author = {Chen, Wei and Li, Zhiyuan},
     journal = {arXiv preprint arXiv:2404.01744},
     year = {2024},
   }

7. arXiv

   On-Device Language Models: A Comprehensive Review

   Jiajun Xu, Zhiyuan Li, Wei Chen, and 4 more authors

   arXiv preprint arXiv:2409.00088, 2024

   arXiv Bib HTML

   @article{xu2024ondevicereview,
     title = {On-Device Language Models: A Comprehensive Review},
     author = {Xu, Jiajun and Li, Zhiyuan and Chen, Wei and Wang, Qun and Gao, Xin and Cai, Qi and Ling, Ziyuan},
     journal = {arXiv preprint arXiv:2409.00088},
     year = {2024},
   }