Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). 2025.
Authors
- Xiangzheng Zhang
- Shi Jia (ORCID: https://orcid.org/0000-0003-2757-5480)
- Yiyu Cai (ORCID: https://orcid.org/0000-0002-8406-9536)
- Zhaojun Duan (ORCID: https://orcid.org/0000-0003-3090-4150)
- Y. Y. Du (ORCID: https://orcid.org/0000-0003-4498-8244)
- Xiaowei Lv (ORCID: https://orcid.org/0000-0003-0693-0148)
- Hejian Zou (ORCID: https://orcid.org/0000-0002-2306-9778)
- Junchen Liu (ORCID: https://orcid.org/0000-0002-2475-8495)
- Liang Wen
- Xin He (ORCID: https://orcid.org/0000-0001-8229-8143)
- Qi An
- Fengping Xiao
- Yongchao Deng
- Tanglifu Tanglifu
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-industry.24
- Citations
- 4
- Primary Topic
- Distributed and Parallel Computing Systems
- Type
- article
- Field-Weighted Citation Impact
- 5.95