publications

2026

1. Preprint

   

   Beyond the Target: From Imitation to Collaboration in Speculative Decoding

   Jinze Li, Yixing Xu, Guanchen Li, and 7 more authors

   2026

   preprint

   Bib

   @misc{li2026spad,
     title = {Beyond the Target: From Imitation to Collaboration in Speculative Decoding},
     author = {Li, Jinze and Xu, Yixing and Li, Guanchen and Xu, Jinfeng and Yang, Shuo and Zhang, Yang and Yin, Xuanwu and Li, Dong and Ngai, Edith C.H. and Barsoum, Emad},
     year = {2026},
     note = {preprint},
   }

2. ACL

   

   OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory

   Jinze Li, Yang Zhang, Xin Yang, and 5 more authors

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Main Conference Long Papers), 2026

   arXiv Bib

   @inproceedings{li2026ocrmemory,
     title = {OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory},
     author = {Li, Jinze and Zhang, Yang and Yang, Xin and Qu, Jiayi and Xu, Jinfeng and Yang, Shuo and Ding, Junhua and Ngai, Edith C.H.},
     booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Main Conference Long Papers)},
     year = {2026},
   }

3. ICLR

   

   Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match

   Jinze Li, Yixing Xu, Guanchen Li, and 6 more authors

   In The Fourteenth International Conference on Learning Representations (ICLR), 2026

   arXiv Bib

   @inproceedings{li2026fly,
     title = {Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match},
     author = {Li, Jinze and Xu, Yixing and Li, Guanchen and Yang, Shuo and Xu, Jinfeng and Yin, Xuanwu and Li, Dong and Ngai, Edith C.H. and Barsoum, Emad},
     booktitle = {The Fourteenth International Conference on Learning Representations (ICLR)},
     year = {2026},
   }

2025

1. ICML

   

   Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

   Jinze Li, Yixing Xu, Haiduo Huang, and 4 more authors

   In Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025

   arXiv Bib

   @inproceedings{li2025gumiho,
     title = {Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding},
     author = {Li, Jinze and Xu, Yixing and Huang, Haiduo and Yin, Xuanwu and Li, Dong and Ngai, Edith C.H. and Barsoum, Emad},
     booktitle = {Proceedings of the 42nd International Conference on Machine Learning (ICML)},
     year = {2025},
   }