Wei Li（李伟）

About Me

I am an Associate Professor at the Institute of Computing Technology, Chinese Academy of Sciences. My journey in this field began at the same institute, where I earned my Ph.D. in 2019.

My research primarily explores the fields of Cross-Modal Generation, Natural Language Generation, and Multi-modal Learning. A significant aspect of my work is dedicated to UNIfied-MOdal learning (UNIMO). This approach aims to integrate various data modalities, such as text, images, and other modalities, for advanced multimodal understanding and generation.

For a detailed look at my work and researches, feel free to explore my academic profiles: Google Scholar, DBLP. If you have any inquiries or wish to discuss academic collaborations, please do not hesitate to email me.

News:

• [2024.05.16] 4 paper have been accepted by ACL 2024, 3 Main Conference + 1 Findings.
• [2023.05.02] 1 paper (WeCheck) for NLG factuality evaluation, has been accepted by ACL 2023, Main Conference.
• [2023.04.27] 1 paper (FactGen) for faithful text generation, has been accepted by Journal of Artificial Intelligence Research, 2023.
• [2022.10.07] 3 paper have been accepted by EMNLP 2022, 1 Main Conference + 2 Findings.
• [2022.03.10] A survey on faithfulness in natural language generation has been published on arxiv.
• [2022.02.24] 2 paper have been accepted by ACL 2022, 1 Main Conference + 1 Findings.
• [2021.08.26] 1 paper has been accepted by EMNLP 2021, Main Conference.
• [2021.05.06] 3 paper have been accepted by ACL 2021, Main Conference.
• [2021.04.14] 1 paper has been accepted by SIGIR 2021, Full Paper.
• [2020.04.03] 1 paper has been accepted by ACL 2020, Main Conference.

Publications:

• [ACL 2024] Wei Li*, Xue Xu*, Jiachen Liu, Xinyan Xiao. UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion. [PDF] [code]
• [ACL 2024] Wenhao Wu, Wei Li*, Xinyan Xiao, Jiachen Liu, Sujian Li. InstructEval: Instruction-Tuned Text Evaluator from Human Preference. [PDF]
• [ACL 2024] Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li*, Zixuan Li, Jian Guo, Huawei Shen, Yuanzhuo Wang. Unlocking the Power of Large Language Models for Entity Alignment. [PDF]
• [ACL 2024] Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Xiang Li, Zhilei Hu, Long Bai, Wei Li*, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng. KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction. [PDF] [code]
• [ACL 2023] Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Sujian Li and Yajuan Lyu. WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning.. Main Confereance of ACL 2023, long paper. [PDF] [code]
• [JAIR 2023] Zhibin Lan, Wei Li, Jinsong Su, Xinyan Xiao, Jiachen Liu, Wenhao Wu, Yajuan Lyu. FactGen: Faithful Text Generation by Factuality-aware Pre-training and Contrastive Ranking Fine-tuning. Journal of Artificial Intelligence Research, 2023.
• [Arxiv 2022] Wei Li, Xue Xu, Xinyan Xiao, Jiachen Liu, Hu Yang, Guohao Li, Zhanpeng Wang, Zhifan Feng, Qiaoqiao She, Yajuan Lyu, Hua Wu. UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal Guidance. [PDF] [code]
• [EMNLP 2022] Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Sujian Li and Yajuan Lyu. Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation.. Main Confereance of EMNLP 2022, long paper.
• [EMNLP 2022] Wenhao Wu, Wei Li , Jiachen Liu, Xinyan Xiao, Ziqiang Cao, Sujian Li and Hua Wu. FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness. Findings of EMNLP 2022, long paper.
• [EMNLP 2022] Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo and Xueqi Cheng. HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning. Findings of EMNLP 2022, long paper [PDF] [code]
• [Arxiv 2022] Wei Li, Wenhao Wu, Moye Chen, Jiachen Liu, Xinyan Xiao and Hua Wu. Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods (52 pages). [PDF]
• [ACL 2022] Wei Li, Can Gao, Guochenng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu and Haifeng Wang. End-to-End Unified Vision-Language Grounded Learning. Findings of ACL 2022, long paper [PDF] [code]
• [ACL 2022] Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng. Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning. ACL 2022, short paper, Main Conference. [PDF]
• [EMNLP 2021] Moye Chen*, Wei Li*, Jiachen Liu, Xinyan Xiao, Hua Wu and Haifeng Wang. SgSum: Transforming Multi-document Summarization into Sub-graph Selection. EMNLP 2021 long paper, Main Conference. (* indicates equal contribution) [PDF] [code]
• [ACL 2021] Wei Li*, Can Gao*, Guochenng Niu*, Xinyan Xiao*, Hao Liu, Jiachen Liu, Hua Wu and Haifeng Wang. UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning. ACL 2021 long paper, Main Conference. (* indicates equal contribution) [PDF] [code]
• [ACL 2021] Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Ziqiang Cao, Sujian Li, Hua Wu and Haifeng Wang. BASS: Boosting Abstractive Summarization with Unified Semantic Graph. ACL 2021 long paper, Main Conference. [PDF]
• [ACL 2021] Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang and Xueqi Cheng. Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs. ACL 2021 long paper, Main Conference. [PDF]
• [SIGIR 2021] Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, Huawei Shen, Yuanzhuo Wang and Xueqi Cheng. Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning. SIGIR2021 Full paper. [PDF] [code]
• [ACL 2020] Wei Li, Xinyan Xiao, Jiachen Liu, Hua Wu and Haifeng Wang. Leveraging Graph to Improve Abstractive Multi-Document Summarization. ACL 2020 long paper, Main Conference. [PDF] [code]
• [FGCS 2020] Wei Li and Hai Zhuge. Probabilistic inference on uncertain semantic link network and its application in event identification. Future Generation Computer Systems, pp: 32-42, 2020
• [TKDE 2019] Wei Li and Hai Zhuge. Abstractive multi-document summarization based on semantic link network. IEEE Transactions on Knowledge and Data Engineering, 2019
• [IEEE Access 2019] Wei Li, Dezhi Cheng, Lei He, Yuanzhuo Wang and Xiaolong Jin. Joint Event Extraction Based on Hierarchical Event Schemas from FrameNet. IEEE Access, 2019
• [EMNLP 2018] Wei Li, Xinyan Xiao, Yajuan Lyu and Yuanzhuo Wang. Improving neural abstractive document summarization with explicit information selection modeling. Proceedings of EMNLP2018, the 2018 Conference on Empirical Methods in Natural Language Processing.
• [EMNLP 2018] Wei Li, Xinyan Xiao, Yajuan Lyu and Yuanzhuo Wang. Improving neural abstractive document summarization with structural regularization. Proceedings of EMNLP2018, the 2018 Conference on Empirical Methods in Natural Language Processing.
• [COLING 2016] Wei Li, Lei He and Hai Zhuge. Abstractive news summarization based on event semantic link network. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers.
• [COLING 2016] Lei He, Wei Li and Hai Zhuge. Exploring differential topic models for comparative summarization of scientific papers. Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers.
• [EMNLP 2015] Wei Li. Abstractive multi-document summarization with semantic information extraction. Proceedings of EMNLP2015, the 2015 Conference on Empirical Methods in Natural Language Processing.

Experience:

• [Nov 2023 - Now]: Associate Professor, Institute of Computing Technology, Chinese Academy of Sciences, Personal Pages
• [July 2021 - Nov. 2023]: Senior Engineer, NLP & KG Department, Baidu Inc.
• [July 2019 - Oct. 2021]: Postdoc, Baidu Inc. and Beijing University of Posts and Telecommunications. Supervisor: Prof. Haifeng Wang and Junping Du
• [Sept. 2012 - June 2019]: PhD, Institute of Computing Technology, Chinese Academy of Sciences. Supervisor: Prof. Yuanzhuo Wang
• [Sept. 2008 - June 2012]: B.E, School of Computer Science, Wuhan University