---
title: "CVRH — paper by Pan et al. (2026) — summary and ideas"
description: "The authors argue that earlier systems overlook how event roles connect arguments. 6.9% F1. 38 references."
authors: ["Bangze Pan", "Yang Li", "Ruili Pu", "Suge Wang", "Jian Liao", "JianXing Zheng", "Xiaoli Li", "Deyu Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.978/"
doi: "10.18653/v1/2026.findings-acl.978"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/pan-2026-cvrh-cross-modal-variational-role/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pan-2026-cvrh-cross-modal-variational-role/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/) / CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction

# CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction

**Authors:** Bangze Pan, [Yang Li](https://md.research.elamur.ai/free/en/authors/yang-li/), Ruili Pu, Suge Wang, Jian Liao, JianXing Zheng, [Xiaoli Li](https://md.research.elamur.ai/free/en/authors/xiaoli-li/) and Deyu Li · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.978/) · [PDF](https://aclanthology.org/2026.findings-acl.978.pdf) · [DOI 10.18653/v1/2026.findings-acl.978](https://doi.org/10.18653/v1/2026.findings-acl.978) · [OpenAlex](https://openalex.org/W7166830173)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Multi-modal Event Argument Extraction (MEAE) means finding every argument of a given event across text and images and assigning each one its role. The authors argue that earlier systems overlook how event roles connect arguments. Those systems mostly rely on weak alignment of single-modality representations or on generative data augmentation. For example, several detected "people" in a photo are hard to label as Agent versus Person without help from the text.

CVRH works in two stages:
- **Shared encoder.** Built on the differential Transformer, it projects candidate text entities and image objects into a common space while keeping look-alike candidates distinct.
- **Role hypergraph.** Each document gets a hypergraph with candidate arguments as nodes and event roles as hyperedges. Every hyperedge merges an LLM-generated role explanation with a learnable dynamic variational vector. Nodes and hyperedges are then updated iteratively.

On the M2E2 benchmark, CVRH reports a 6.9% F1 gain over the previous state of the art. This suggests that explicitly modelling high-order, role-level links between arguments benefits cross-modal extraction.

## Key points
- **Evaluation and results:** CVRH is evaluated on M2E2. It reaches F1 of 40.2 for text, 25.3 for vision and 40.1 for multi-modal arguments.
- **Ablations:** Removing the LLM role interpretation information (RII) causes the largest drop, to 36.1 text F1 and 37.1 multi-modal F1. Removing the variational vector, swapping DiffTrans for a standard Transformer, or dropping the node distance loss also lowers scores.
- **Threshold tuning:** The best hyperedge aggregation threshold β and argument discrimination threshold τ vary by modality:
  - text: 0.3 / 0.5
  - multi-modal: 0.4 / 0.5
  - vision: 0.6 / 0.4
- **MLLM comparison:** Qwen2.5-VL-7B and LLaVA1.5-7B were also tested. Their F1 scores are about 32–33 for text and multi-modal arguments but only 13.7–14.5 for visual ones. This supports the authors' view that visual arguments are the main bottleneck.
- **Limitations:** Visual extraction stays weak because the role hyperedges are mainly text-based. The scarcity of MEAE data also limits testing on easily confused role types.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Singapore University of Technology and Design](https://md.research.elamur.ai/free/en/universities/singapore-university-of-technology-and-design/) — University, Singapore, Singapore · 49 works · 11,074 citations
- [Shanxi University](https://md.research.elamur.ai/free/en/universities/shanxi-university/) — University, Taiyuan, China · 2 works · 30 citations
- [Shanxi University of Finance and Economics](https://md.research.elamur.ai/free/en/universities/shanxi-university-of-finance-and-economics/) — University, Taiyuan, China · 2 works · 22 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Bangze Pan, Yang Li, Ruili Pu, Suge Wang, Jian Liao, JianXing Zheng, Xiaoli Li and Deyu Li. 2026. CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{pan2026cvrh,
  title = {{CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction}},
  author = {Bangze Pan, Yang Li, Ruili Pu, Suge Wang, Jian Liao, JianXing Zheng, Xiaoli Li and Deyu Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.978},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.978}
}
```

- [← previous CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech](https://md.research.elamur.ai/free/en/papers/saidi-2026-cv-18-ner-augmented-common/)
- [next → CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models](https://md.research.elamur.ai/free/en/papers/oba-2026-cxmp-linguistic-minimal-pair-benchmark/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

38 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Zhangtao Cheng, Jienan Zhang, Xovee Xu, Goce Trajcevski, Ting Zhong, and Fan Zhou. 2024. Retrieval-augmented hypergraph for multimodal social media popularity prediction. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, page 445–455, New York, NY, USA… [find](https://scholar.google.com/scholar?q=Zhangtao+Cheng%2C+Jienan+Zhang%2C+Xovee+Xu%2C+Goce+Trajcevski%2C+Ting+Zhong%2C+and+Fan+Zhou%2E+2024%2E+Retrieval%2Daugmented+hypergraph+for+multimodal+social+media+popularity+prediction%2E+In+Proceedings+of+the+30th+AC)
2. Yiming Cui, Bin Sun, Tao Jiang, and Hongrui Cui. 2025. Multimedia event extraction based on multimodal low-dimensional feature representation space. Signal, Image and Video Processing, 19(5):1863–1711. [find](https://scholar.google.com/scholar?q=Yiming+Cui%2C+Bin+Sun%2C+Tao+Jiang%2C+and+Hongrui+Cui%2E+2025%2E+Multimedia+event+extraction+based+on+multimodal+low%2Ddimensional+feature+representation+space%2E+Signal%2C+Image+and+Video+Processing%2C+19%285%29%3A1863%E2%80%931711)
3. Yunkai Dang, Kaichen Huang, Jiahao Huo, Yibo Yan, Sirui Huang, Dongrui Liu, Mengxi Gao, Jie Zhang, Chen Qian, Kun Wang, Yong Liu, Jing Shao, Hui Xiong, and Xuming Hu. 2024. Explainable and interpretable multimodal large language models: A comprehensive survey. Preprint, arXiv:2412.02104. — [arXiv:2412.02104](https://arxiv.org/abs/2412.02104) [find](https://scholar.google.com/scholar?q=Yunkai+Dang%2C+Kaichen+Huang%2C+Jiahao+Huo%2C+Yibo+Yan%2C+Sirui+Huang%2C+Dongrui+Liu%2C+Mengxi+Gao%2C+Jie+Zhang%2C+Chen+Qian%2C+Kun+Wang%2C+Yong+Liu%2C+Jing+Shao%2C+Hui+Xiong%2C+and+Xuming+Hu%2E+2024%2E+Explainable+and+interpretab)
4. Zilin Du, Yunxin Li, Xu Guo, Yidan Sun, and Boyang Li. 2023. Training multimedia event extraction with generated images and captions. In Proceedings of the 31st ACM International Conference on Multimedia, MM ’23, page 5504–5513, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Zilin+Du%2C+Yunxin+Li%2C+Xu+Guo%2C+Yidan+Sun%2C+and+Boyang+Li%2E+2023%2E+Training+multimedia+event+extraction+with+generated+images+and+captions%2E+In+Proceedings+of+the+31st+ACM+International+Conference+on+Multime)
5. Ujun Jeong, Kaize Ding, Lu Cheng, Ruocheng Guo, Kai Shu, and Huan Liu. 2022. Nothing stands alone: Relational fake news detection with hypergraph neural networks. 2022 IEEE International Conference on Big Data (Big Data), pages 596–605. [find](https://scholar.google.com/scholar?q=Ujun+Jeong%2C+Kaize+Ding%2C+Lu+Cheng%2C+Ruocheng+Guo%2C+Kai+Shu%2C+and+Huan+Liu%2E+2022%2E+Nothing+stands+alone%3A+Relational+fake+news+detection+with+hypergraph+neural+networks%2E+2022+IEEE+International+Conference+on)
6. Manling Li, Ruochen Xu, Shuohang Wang, Luowei Zhou, Xudong Lin, Chenguang Zhu, Michael Zeng, Heng Ji, and Shih-Fu Chang. 2022. Clip-event: Connecting text and images with event structures. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16399–16408. [find](https://scholar.google.com/scholar?q=Manling+Li%2C+Ruochen+Xu%2C+Shuohang+Wang%2C+Luowei+Zhou%2C+Xudong+Lin%2C+Chenguang+Zhu%2C+Michael+Zeng%2C+Heng+Ji%2C+and+Shih%2DFu+Chang%2E+2022%2E+Clip%2Devent%3A+Connecting+text+and+images+with+event+structures%2E+In+2022+IEE)
7. Manling Li, Alireza Zareian, Qi Zeng, Spencer Whitehead, Di Lu, Heng Ji, and Shih-Fu Chang. 2020. Cross-media structured common space for multimedia event extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2557–2568, Online. Association for… [find](https://scholar.google.com/scholar?q=Manling+Li%2C+Alireza+Zareian%2C+Qi+Zeng%2C+Spencer+Whitehead%2C+Di+Lu%2C+Heng+Ji%2C+and+Shih%2DFu+Chang%2E+2020%2E+Cross%2Dmedia+structured+common+space+for+multimedia+event+extraction%2E+In+Proceedings+of+the+58th+Annual)
8. Qian Li, Cheng Ji, Shu Guo, Kun Peng, Qianren Mao, and Shangguang Wang. 2025a. Variational multimodal hypergraph attention network for multi-modal relation extraction. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI ’25. [find](https://scholar.google.com/scholar?q=Qian+Li%2C+Cheng+Ji%2C+Shu+Guo%2C+Kun+Peng%2C+Qianren+Mao%2C+and+Shangguang+Wang%2E+2025a%2E+Variational+multimodal+hypergraph+attention+network+for+multi%2Dmodal+relation+extraction%2E+In+Proceedings+of+the+Thirty%2DFou)
9. Qian Li, Cheng Ji, Shu Guo, Kun Peng, Qianren Mao, and Shangguang Wang. 2025b. Variational multimodal hypergraph attention network for multi-modal relation extraction. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI ’25. [find](https://scholar.google.com/scholar?q=Qian+Li%2C+Cheng+Ji%2C+Shu+Guo%2C+Kun+Peng%2C+Qianren+Mao%2C+and+Shangguang+Wang%2E+2025b%2E+Variational+multimodal+hypergraph+attention+network+for+multi%2Dmodal+relation+extraction%2E+In+Proceedings+of+the+Thirty%2DFou)
10. Jian Liu, Yufeng Chen, and Jinan Xu. 2022. Multimedia event extraction from news with a unified contrastive learning framework. In Proceedings of the 30th ACM International Conference on Multimedia, MM ’22, page 1945–1953, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Jian+Liu%2C+Yufeng+Chen%2C+and+Jinan+Xu%2E+2022%2E+Multimedia+event+extraction+from+news+with+a+unified+contrastive+learning+framework%2E+In+Proceedings+of+the+30th+ACM+International+Conference+on+Multimedia%2C+M)
11. Junrui Liu, Tong Li, Di Wu, Zifang Tang, Yuan Fang, and Zhen Yang. 2025a. An aspect performance-aware hypergraph neural network for review-based recommendation. In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, page 503–511, New York, NY, USA. Association f… [find](https://scholar.google.com/scholar?q=Junrui+Liu%2C+Tong+Li%2C+Di+Wu%2C+Zifang+Tang%2C+Yuan+Fang%2C+and+Zhen+Yang%2E+2025a%2E+An+aspect+performance%2Daware+hypergraph+neural+network+for+review%2Dbased+recommendation%2E+In+Proceedings+of+the+Eighteenth+ACM+In)
12. Maofu Liu, Bingying Zhou, Huijun Hu, Chen Qiu, and Xiaokang Zhang. 2025b. Cross-modal event extraction via visual event grounding and semantic relation filling. Information Processing & Management, 62(3):104027. [find](https://scholar.google.com/scholar?q=Maofu+Liu%2C+Bingying+Zhou%2C+Huijun+Hu%2C+Chen+Qiu%2C+and+Xiaokang+Zhang%2E+2025b%2E+Cross%2Dmodal+event+extraction+via+visual+event+grounding+and+semantic+relation+filling%2E+Information+Processing+%26+Management%2C+62)
13. Wanlong Liu, Shaohuan Cheng, Dingyi Zeng, and Qu Hong. 2023. Enhancing document-level event argument extraction with contextual clues and role relevance. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12908–12922, Toronto, Canada. Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Wanlong+Liu%2C+Shaohuan+Cheng%2C+Dingyi+Zeng%2C+and+Qu+Hong%2E+2023%2E+Enhancing+document%2Dlevel+event+argument+extraction+with+contextual+clues+and+role+relevance%2E+In+Findings+of+the+Association+for+Computation)
14. Yang Liu, Fang Liu, Licheng Jiao, Qianyue Bao, Long Sun, Shuo Li, Lingling Li, and Xu Liu. 2024. Multi-grained gradual inference model for multimedia event extraction. IEEE Transactions on Circuits and Systems for Video Technology, 34(10):10507–10520. [find](https://scholar.google.com/scholar?q=Yang+Liu%2C+Fang+Liu%2C+Licheng+Jiao%2C+Qianyue+Bao%2C+Long+Sun%2C+Shuo+Li%2C+Lingling+Li%2C+and+Xu+Liu%2E+2024%2E+Multi%2Dgrained+gradual+inference+model+for+multimedia+event+extraction%2E+IEEE+Transactions+on+Circuits+an)
15. Haoran Luo, E. Haihong, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Ze min Kuang, Meina Song, Yifan Zhu, and Anh Tuan Luu. 2025. Hypergraphrag: Retrieval-augmented generation via hypergraph-structured knowledge representation. [find](https://scholar.google.com/scholar?q=Haoran+Luo%2C+E%2E+Haihong%2C+Guanting+Chen%2C+Yandan+Zheng%2C+Xiaobao+Wu%2C+Yikai+Guo%2C+Qika+Lin%2C+Yu+Feng%2C+Ze+min+Kuang%2C+Meina+Song%2C+Yifan+Zhu%2C+and+Anh+Tuan+Luu%2E+2025%2E+Hypergraphrag%3A+Retrieval%2Daugmented+generatio)
16. Sarah Pratt, Mark Yatskar, Luca Weihs, Ali Farhadi, and Aniruddha Kembhavi. 2020. Grounded situation recognition. [find](https://scholar.google.com/scholar?q=Sarah+Pratt%2C+Mark+Yatskar%2C+Luca+Weihs%2C+Ali+Farhadi%2C+and+Aniruddha+Kembhavi%2E+2020%2E+Grounded+situation+recognition%2E)
17. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In Proceedings of the 38th Internatio…
18. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). J. Mach. Learn. Res., 21:140:1–140:67.
19. Philipp Seeberger, Dominik Wagner, and Korbinian Riedhammer. 2024. MMUTF: Multimodal multimedia event argument extraction with unified template filling. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6539–6548, Miami, Florida, USA. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Philipp+Seeberger%2C+Dominik+Wagner%2C+and+Korbinian+Riedhammer%2E+2024%2E+MMUTF%3A+Multimodal+multimedia+event+argument+extraction+with+unified+template+filling%2E+In+Findings+of+the+Association+for+Computationa)
20. Lin Sun, Kai Zhang, Qingyuan Li, and Renze Lou. 2024. Umie: Unified multimodal information extraction with instruction tuning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(17):19062– 19070. [find](https://scholar.google.com/scholar?q=Lin+Sun%2C+Kai+Zhang%2C+Qingyuan+Li%2C+and+Renze+Lou%2E+2024%2E+Umie%3A+Unified+multimodal+information+extraction+with+instruction+tuning%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+38%2817%29%3A190)
21. Rejin Varghese and Sambath M. 2024. Yolov8: A novel object detection algorithm with enhanced performance and robustness. In 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pages 1–6. [find](https://scholar.google.com/scholar?q=Rejin+Varghese+and+Sambath+M%2E+2024%2E+Yolov8%3A+A+novel+object+detection+algorithm+with+enhanced+performance+and+robustness%2E+In+2024+International+Conference+on+Advances+in+Data+Engineering+and+Intelligen)
22. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 6000–6010, Red Hook, NY, USA. Cur…
23. C Walker, S Strassel, J Medero, and K Maeda. 2006. [find](https://scholar.google.com/scholar?q=C+Walker%2C+S+Strassel%2C+J+Medero%2C+and+K+Maeda%2E+2006%2E)
24. Ace 2005 multilingual training corpus. Progress of Theoretical Physics Supplement, 110(110):261–276. [find](https://scholar.google.com/scholar?q=Ace+2005+multilingual+training+corpus%2E+Progress+of+Theoretical+Physics+Supplement%2C+110%28110%29%3A261%E2%80%93276%2E)
25. Qizhi Wan, Tao Liu, Changxuan Wan, Rong Hu, Keli Xiao, and Yuxin Shuai. 2025. Event pattern-instance graph: A multi-round role representation learning strategy for document-level event argument extraction. In Findings of the Association for Computational Linguistics: ACL 2025, pages 1865–1877, Vienn… [find](https://scholar.google.com/scholar?q=Qizhi+Wan%2C+Tao+Liu%2C+Changxuan+Wan%2C+Rong+Hu%2C+Keli+Xiao%2C+and+Yuxin+Shuai%2E+2025%2E+Event+pattern%2Dinstance+graph%3A+A+multi%2Dround+role+representation+learning+strategy+for+document%2Dlevel+event+argument+extrac)
26. Bin Wang, Meishan Zhang, Hao Fei, Yu Zhao, Bobo Li, Shengqiong Wu, Wei Ji, and Min Zhang. 2024. Speechee: A novel benchmark for speech event extraction. In Proceedings of the 32nd ACM International Conference on Multimedia, MM ’24, page 10449–10458, New York, NY, USA. Association for Computing Machi… [find](https://scholar.google.com/scholar?q=Bin+Wang%2C+Meishan+Zhang%2C+Hao+Fei%2C+Yu+Zhao%2C+Bobo+Li%2C+Shengqiong+Wu%2C+Wei+Ji%2C+and+Min+Zhang%2E+2024%2E+Speechee%3A+A+novel+benchmark+for+speech+event+extraction%2E+In+Proceedings+of+the+32nd+ACM+International+Co)
27. Guanghui Wang, Dexi Liu, Jian-Yun Nie, Qizhi Wan, Rong Hu, Xiping Liu, Wanlong Liu, and Jiaming Liu. 2025a. DEGAP: Dual event-guided adaptive prefixes for templated-based event argument extraction with slot querying. In Proceedings of the 31st International Conference on Computational Linguistics, p… [find](https://scholar.google.com/scholar?q=Guanghui+Wang%2C+Dexi+Liu%2C+Jian%2DYun+Nie%2C+Qizhi+Wan%2C+Rong+Hu%2C+Xiping+Liu%2C+Wanlong+Liu%2C+and+Jiaming+Liu%2E+2025a%2E+DEGAP%3A+Dual+event%2Dguided+adaptive+prefixes+for+templated%2Dbased+event+argument+extraction+wit)
28. Xiaoyu Wang, Tao Sun, Gengchen Liu, Zhi Yang, Jiahui Liu, and Zimeng Xu. 2025b. Mgfsg-ee: A method based on multi-grained fusion and scene graph enhancement for event extraction. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM ’25, page 3103–3112… [find](https://scholar.google.com/scholar?q=Xiaoyu+Wang%2C+Tao+Sun%2C+Gengchen+Liu%2C+Zhi+Yang%2C+Jiahui+Liu%2C+and+Zimeng+Xu%2E+2025b%2E+Mgfsg%2Dee%3A+A+method+based+on+multi%2Dgrained+fusion+and+scene+graph+enhancement+for+event+extraction%2E+In+Proceedings+of+the)
29. Meng Wei, Long Chen, Wei Ji, Xiaoyu Yue, and Tat-Seng Chua. 2022. Rethinking the two-stage framework for grounded situation recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3):2651–2658. [find](https://scholar.google.com/scholar?q=Meng+Wei%2C+Long+Chen%2C+Wei+Ji%2C+Xiaoyu+Yue%2C+and+Tat%2DSeng+Chua%2E+2022%2E+Rethinking+the+two%2Dstage+framework+for+grounded+situation+recognition%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+)
30. Bo Xu, Erchen Yu, Jiahui Zhou, Hongfei Lin, and Linlin Zong. 2025a. HyperHatePrompt: A hypergraph-based prompting fusion model for multimodal hate detection. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3825–3835, Abu Dhabi, UAE. Association for Computation… [find](https://scholar.google.com/scholar?q=Bo+Xu%2C+Erchen+Yu%2C+Jiahui+Zhou%2C+Hongfei+Lin%2C+and+Linlin+Zong%2E+2025a%2E+HyperHatePrompt%3A+A+hypergraph%2Dbased+prompting+fusion+model+for+multimodal+hate+detection%2E+In+Proceedings+of+the+31st+International+C)
31. Hao Xu, Yunxiao Zhao, Jiayang Zhang, Zhiqiang Wang, and Ru Li. 2025b. LOG: A local-to-global optimization approach for retrieval-based explainable multi-hop question answering. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9085–9095, Abu Dhabi, UAE. Associat… [find](https://scholar.google.com/scholar?q=Hao+Xu%2C+Yunxiao+Zhao%2C+Jiayang+Zhang%2C+Zhiqiang+Wang%2C+and+Ru+Li%2E+2025b%2E+LOG%3A+A+local%2Dto%2Dglobal+optimization+approach+for+retrieval%2Dbased+explainable+multi%2Dhop+question+answering%2E+In+Proceedings+of+the+3)
32. Tianzhu Ye, Li Dong, Yuqing Xia, Yutao Sun, Yi Zhu, Gao Huang, and Furu Wei. 2025. Differential transformer. In International Conference on Representation Learning, volume 2025, pages 144–164. [find](https://scholar.google.com/scholar?q=Tianzhu+Ye%2C+Li+Dong%2C+Yuqing+Xia%2C+Yutao+Sun%2C+Yi+Zhu%2C+Gao+Huang%2C+and+Furu+Wei%2E+2025%2E+Differential+transformer%2E+In+International+Conference+on+Representation+Learning%2C+volume+2025%2C+pages+144%E2%80%93164%2E)
33. Jianfei Yu, Jing Jiang, Li Yang, and Rui Xia. 2020. [Improving multimodal named entity recognition via entity span detection with unified multimodal transformer](https://md.research.elamur.ai/free/en/papers/yu-2020-improving-multimodal-named-entity-recognition/). In Proceedings of the 58th Annual Meeting of • MMUTF (Seeberger et al., 2024) designs an event template and uses text prompts along with th…
34. Yawen Zeng, Qin Jin, Tengfei Bao, and Wenfeng Li. 2023. Multi-modal knowledge hypergraph for diverse image retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3):3376–3383. [find](https://scholar.google.com/scholar?q=Yawen+Zeng%2C+Qin+Jin%2C+Tengfei+Bao%2C+and+Wenfeng+Li%2E+2023%2E+Multi%2Dmodal+knowledge+hypergraph+for+diverse+image+retrieval%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+37%283%29%3A3376%E2%80%933383%2E)
35. VEGSRF (Liu et al., 2025b) leverages textual event information to focus on image details and employs an image event template to mine potential relationships among image event arguments. [find](https://scholar.google.com/scholar?q=VEGSRF+%28Liu+et+al%2E%2C+2025b%29+leverages+textual+event+information+to+focus+on+image+details+and+employs+an+image+event+template+to+mine+potential+relationships+among+image+event+arguments%2E)
36. Yunxiao Zhao, Zhiqiang Wang, Xiaoli Li, Jiye Liang, and Ru Li. 2024. AGR: Reinforced causal agent-guided self-explaining rationalization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 510–518, Bangkok, Thailand. Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Yunxiao+Zhao%2C+Zhiqiang+Wang%2C+Xiaoli+Li%2C+Jiye+Liang%2C+and+Ru+Li%2E+2024%2E+AGR%3A+Reinforced+causal+agent%2Dguided+self%2Dexplaining+rationalization%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+f)
37. Changmeng Zheng, Junhao Feng, Ze Fu, Yi Cai, Qing Li, and Tao Wang. 2021. Multimodal relation extraction with efficient graph alignment. In Proceedings of the 29th ACM International Conference on Multimedia, MM ’21, page 5298–5306, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Changmeng+Zheng%2C+Junhao+Feng%2C+Ze+Fu%2C+Yi+Cai%2C+Qing+Li%2C+and+Tao+Wang%2E+2021%2E+Multimodal+relation+extraction+with+efficient+graph+alignment%2E+In+Proceedings+of+the+29th+ACM+International+Conference+on+Mult)
38. A • MGFSG-EE (Wang et al., 2025b) enhances the capability of MEE by modeling the co-occurrence and background information between text and images. [find](https://scholar.google.com/scholar?q=A+%E2%80%A2+MGFSG%2DEE+%28Wang+et+al%2E%2C+2025b%29+enhances+the+capability+of+MEE+by+modeling+the+co%2Doccurrence+and+background+information+between+text+and+images%2E)

*Updated 1 November 2026*