Chenglong Wang|王成龙

Ph.D. Student

Information

Code Languages

About Me

       I am a Ph.D student of the 2021 cohort at the Natural Language Processing Laboratory of Northeastern University (co-advisors: Prof. Tong Xiao and Prof. Jingbo Zhu). My research focuses on the methods of language model alignment, with a current emphasis on: 1) the training efficiency of large language models based on reinforcement learning; 2) the construction and training of reward models; 3) multimodal language model alignment, such as vision-llm alignment, as detailed in my publications. Additionally, I have participated in machine translation workshops such as WGT(2020), QE(2020), and WMT(Efficiency and Translation tasks, 2021).


Education

  • Northeastern University (Shenyang, China) - Computer Science and Technology (Ph.D. Student)

  • Northeastern University (Shenyang, China) - Computer Science and Technology (Bachelor)


Publications (full list)

2025:
RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data. AAAI 2025. [pdf] [code]
Chenglong Wang, Yang Gan, Yifu Huo, Yongyu Mu, Murun Yang, Qiaozhi He, Tong Xiao, Chunliang Zhang, Tongran Liu, Quan Du, Di Yang, Jingbo Zhu

2024:
LRHP: Learning Representations for Human Preferences via Preference Pairs. arXiv 2024. [pdf] [code]
Chenglong Wang, Yang Gan, Yifu Huo, Yongyu Mu, Qiaozhi He, Murun Yang, Tong Xiao, Chunliang Zhang, Tongran Liu, Jingbo Zhu
NDP: Next Distribution Prediction as a More Broad Target. arXiv 2024. [pdf] [code]
Junhao Ruan, Abudukeyumu Abudula, Xinyu Liu, Bei Li, Yinqiao Li, Chenglong Wang, Yuchun Fan, Yuan Ge, Tong Xiao, Jingbo Zhu
Cross-layer Attention Sharing for Large Language Models. arXiv 2024. [pdf] [code]
Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Qiaozhi He, Murun Yang, Tong Xiao, Jingbo Zhu
Revealing the Parallel Multilingual Learning within Large Language Models. EMNLP 2024. [pdf] [code]
Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, Jingbo Zhu
Prior Constraints-based Reward Model Training for Aligning Large Language Models. CCL 2024. [pdf] [code]
Hang Zhou, Chenglong Wang, Yimin Hu, Tong Xiao, Chunliang Zhang, Jingbo Zhu
Hybrid Alignment Training for Large Language Models. Findings of ACL 2024. [pdf] [code]
Chenglong Wang, Hang Zhou, Kaiyan Chang, Bei Li, Yongyu Mu, Tong Xiao, Tongran Liu, JingBo Zhu
Efficient Prompting Methods for Large Language Models: A Survey. arXiv 2024. [pdf]
Kaiyan Chang, Songcheng Xu, Chenglong Wang, Yingfeng Luo, Tong Xiao, Jingbo Zhu
ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation. AAAI 2024. [pdf] [code]
Chenglong Wang, Hang Zhou, Yimin Hu, Yifu Huo, Bei Li, Tongran Liu, Tong Xiao, Jingbo Zhu

2023:
Learning Evaluation Models from Large Language Models for Sequence Generation. arXiv 2023. [pdf]
Chenglong Wang, Hang Zhou, Kaiyan Chang, Tongran Liu, Chunliang Zhang, Quan Du, Tong Xiao, Jingbo Zhu

2022:
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection. Findings of EMNLP 2022. [pdf]
Chenglong Wang, Yi Lu, Yongyu Mu, Yimin Hu, Tong Xiao and Jingbo Zhu.

2021:
The NiuTrans System for the WMT21 Efficiency Task. EMNLP Workshop 2021. [pdf]
Chenglong Wang, Chi Hu, Yongyu Mu, Zhongxiang Yan, Siming Wu, Minyi Hu, Hang Cao, Bei Li, Ye Lin, Tong Xiao, Jingbo Zhu.
RankNAS: Efficient Neural Architecture Search by Pairwise Ranking. EMNLP 2021. [pdf]
Chi Hu, Chenglong Wang, Xiangnan Ma, Xia Meng, Yinqiao Li, Tong Xiao, Jingbo Zhu and Changliang Li
The NiuTrans Machine Translation Systems for WMT21. EMNLP Workshop 2021. [pdf]
Shuhan Zhou, Tao Zhou, Binghao Wei, Yingfeng Luo, Yongyu Mu, Zefan Zhou, Chenglong Wang, Xuanjun Zhou, Chuanhao Lv, Yi Jing, Laohu Wang, Jingnan Zhang, Canan Huang, Zhongxiang Yan, Chi Hu, Bei Li, Tong Xiao, Jingbo Zhu

2020:
The NiuTrans System for WNGT 2020 Efficiency Task. ACL Workshop 2020.[pdf]
Chi Hu, Bei Li, Yinqiao Li, Ye Lin, Yanyang Li, Chenglong Wang, Tong Xiao, Jingbo Zhu
The NiuTrans System for the WMT20 Quality Estimation Shared Task. ACL Workshop 2020. [pdf]
Chi Hu, Hui Liu, Kai Feng, Chen Xu, Zefan Zhou, Shiqin Yan, Yingfeng Luo, Chenglong Wang, Xia Meng, Nuo Xu, Tong Xiao, Jingbo Zhu

Softwares

Vision-LLM-Alignment: an alignment system that contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

DeepSpeed-Chat-Extension: contains some extensions of deepspeed-chat for fine-tuning LLMs (SFT+RLHF/DPO).


Professional Activities

Reviewer for ACL Rolling (aimed to ACL/EMNLP/NAACL) 2023/2024
Reviewer for COLING 2024
Reviewer for CCL 2023