Guohong Fu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Guohong Fu has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
Nan Yu
Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China
6 shared publications- Chen Gong
Institute of Artificial Intelligence School of Computer Science and Technology Soochow University Suzhou China
5 shared publications - Ziqiang Cao
Soochow University
5 shared publications Junjie Wu
School of Computer Science and Technology Soochow University
3 shared publications- Chen Gong
Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China
2 shared publications Chengguo Lv
2 shared publications
Latest Publications
- 12 February 2026
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20 (9) , 2009351
Bridging modalities: a unified framework for textual and multimodal dialogue discourse parsing
- 12 February 2026
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20 (9) , 2009351
Bridging modalities: a unified framework for textual and multimodal dialogue discourse parsing
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12520-12532
Diversity Controlled Diffusion Model for Nuclear Instance Segmentation in Pathology
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12520-12532
Diversity Controlled Diffusion Model for Nuclear Instance Segmentation in Pathology
- Open Access
HiEAG: Evidence-Augmented Generation for Out-of-Context Misinformation Detection
Recent advancements in multimodal out-of-context (OOC) misinformation detection have made remarkable progress in checking the consistencies between different modalities for supporting or refuting image-text pairs. However, existing OOC misinformation detection methods tend to emphasize the role of internal consistency, ignoring the significant of external consistency between image-text pairs and external evidence. In this paper, we propose HiEAG, a novel Hierarchical Evidence-Augmented Generation framework to refine external consistency checking through leveraging the extensive knowledge of multimodal large language models (MLLMs). Our approach decomposes external consistency checking into a comprehensive engine pipeline, which integrates reranking and rewriting, apart from retrieval. Evidence reranking module utilizes Automatic Evidence Selection Prompting (AESP) that acquires the relevant evidence item from the products of evidence retrieval. Subsequently, evidence rewriting module leverages Automatic Evidence Generation Prompting (AEGP) to improve task adaptation on MLLM-based OOC misinformation detectors. Furthermore, our approach enables explanation for judgment, and achieves impressive performance with instruction tuning. Experimental results on different benchmark datasets demonstrate that our proposed HiEAG surpasses previous state-of-the-art (SOTA) methods in the accuracy over all samples.
Open AccessHiEAG: Evidence-Augmented Generation for Out-of-Context Misinformation Detection
Recent advancements in multimodal out-of-context (OOC) misinformation detection have made remarkable progress in checking the consistencies between different modalities for supporting or refuting image-text pairs. However, existing OOC misinformation detection methods tend to emphasize the role of internal consistency, ignoring the significant of external consistency between image-text pairs and external evidence. In this paper, we propose HiEAG, a novel Hierarchical Evidence-Augmented Generation framework to refine external consistency checking through leveraging the extensive knowledge of multimodal large language models (MLLMs). Our approach decomposes external consistency checking into a comprehensive engine pipeline, which integrates reranking and rewriting, apart from retrieval. Evidence reranking module utilizes Automatic Evidence Selection Prompting (AESP) that acquires the relevant evidence item from the products of evidence retrieval. Subsequently, evidence rewriting module leverages Automatic Evidence Generation Prompting (AEGP) to improve task adaptation on MLLM-based OOC misinformation detectors. Furthermore, our approach enables explanation for judgment, and achieves impressive performance with instruction tuning. Experimental results on different benchmark datasets demonstrate that our proposed HiEAG surpasses previous state-of-the-art (SOTA) methods in the accuracy over all samples.
- Open Access
MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection
Multimodal misinformation floods on various social media, and continues to evolve in the era of AI-generated content (AIGC). The emerged misinformation with low creation cost and high deception poses significant threats to society. While recent studies leverage general-purpose multimodal large language models (MLLMs) to achieve remarkable results in detection, they encounter two critical limitations: (1) Insufficient reasoning, where general-purpose MLLMs often follow the uniform reasoning paradigm but generate inaccurate explanations and judgments, due to the lack of the task-specific knowledge of multimodal misinformation detection. (2) Reasoning biases, where a single thinking mode make detectors a suboptimal path for judgment, struggling to keep pace with the fast-growing and intricate multimodal misinformation. In this paper, we propose MMD-Thinker, a two-stage framework for multimodal misinformation detection through adaptive multi-dimensional thinking. First, we develop tailor-designed thinking mode for multimodal misinformation detection. Second, we adopt task-specific instruction tuning to inject the tailored thinking mode into general-purpose MLLMs. Third, we further leverage reinforcement learning strategy with a mixed advantage function, which incentivizes the reasoning capabilities in trajectories. Furthermore, we construct the multimodal misinformation reasoning (MMR) dataset, encompasses more than 8K image-text pairs with both reasoning processes and classification labels, to make progress in the relam of multimodal misinformation detection. Experimental results demonstrate that our proposed MMD-Thinker achieves state-of-the-art performance on both in-domain and out-of-domain benchmark datasets, while maintaining flexible inference and token usage. Code will be publicly available at Github.
Open AccessMMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection
Multimodal misinformation floods on various social media, and continues to evolve in the era of AI-generated content (AIGC). The emerged misinformation with low creation cost and high deception poses significant threats to society. While recent studies leverage general-purpose multimodal large language models (MLLMs) to achieve remarkable results in detection, they encounter two critical limitations: (1) Insufficient reasoning, where general-purpose MLLMs often follow the uniform reasoning paradigm but generate inaccurate explanations and judgments, due to the lack of the task-specific knowledge of multimodal misinformation detection. (2) Reasoning biases, where a single thinking mode make detectors a suboptimal path for judgment, struggling to keep pace with the fast-growing and intricate multimodal misinformation. In this paper, we propose MMD-Thinker, a two-stage framework for multimodal misinformation detection through adaptive multi-dimensional thinking. First, we develop tailor-designed thinking mode for multimodal misinformation detection. Second, we adopt task-specific instruction tuning to inject the tailored thinking mode into general-purpose MLLMs. Third, we further leverage reinforcement learning strategy with a mixed advantage function, which incentivizes the reasoning capabilities in trajectories. Furthermore, we construct the multimodal misinformation reasoning (MMR) dataset, encompasses more than 8K image-text pairs with both reasoning processes and classification labels, to make progress in the relam of multimodal misinformation detection. Experimental results demonstrate that our proposed MMD-Thinker achieves state-of-the-art performance on both in-domain and out-of-domain benchmark datasets, while maintaining flexible inference and token usage. Code will be publicly available at Github.
- 7 November 2025
- Published by Elsevier in Information Processing & Management
- Vol. 63 (2)
Bidirectional GPT
- 7 November 2025
- Published by Elsevier in Information Processing & Management
- Vol. 63 (2)
Bidirectional GPT
- 4 October 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Rethinking hard training sample generation for medical image segmentation
- 4 October 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Rethinking hard training sample generation for medical image segmentation
- 4 October 2025
- Published by Elsevier in Information Processing & Management
- Vol. 63 (2)
Enhancing multi-modal aspect-based sentiment classification via emotional semantic-aware cross-modal relation inference
- 4 October 2025
- Published by Elsevier in Information Processing & Management
- Vol. 63 (2)
Enhancing multi-modal aspect-based sentiment classification via emotional semantic-aware cross-modal relation inference
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 31513-31525
Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark Approach
Xingyu Li, Chen Gong, Guohong Fu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 31513-31525
Open AccessMultimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark Approach
Xingyu Li, Chen Gong, Guohong Fu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 16 October 2024
- Published by IOS Press
- p. 322-329
PromptCD: Coupled and Decoupled Prompt Learning for Vision-Language Models
Large-scale pre-trained vision-language models (VLMs), like CLIP, have presented striking generalizability for adapting to image classification in a few shot setting. Most existing methods explore a set of learnable tokens, such as prompt learning, on data-efficient utilization for task adaptation. However, they focus on either the coupled-modality property by prompt projection or decoupled-modality characteristic by prompt consistency, which ignores effective interaction between prompts. To model the deep yet sufficient cross-modal interaction and enhance the generalization between both seen and unseen tasks, in this paper, we propose a novel coupled and decoupled prompt learning framework, dubbed PromptCD, for vision-language models. Specifically, we introduce a bi-directional coupled-modality mechanism to intensify the interaction between both vision and language branches. Additionally, we propose mixture consistency to further improve the generalization and discrimination of the models on unseen tasks. The integration of such a mechanism and consistency facilitates the proposed framework adaptation for various downstream tasks. We conduct extensive experiments on 11 image classification datasets under a range of evaluation protocols, including base-to-novel and domain generalization, and cross-dataset recognition. Experimental results demonstrate that our proposed PromptCD overall outperforms state-of-the-art methods.
- 16 October 2024
- Published by IOS Press
- p. 322-329
Open AccessPromptCD: Coupled and Decoupled Prompt Learning for Vision-Language Models
Large-scale pre-trained vision-language models (VLMs), like CLIP, have presented striking generalizability for adapting to image classification in a few shot setting. Most existing methods explore a set of learnable tokens, such as prompt learning, on data-efficient utilization for task adaptation. However, they focus on either the coupled-modality property by prompt projection or decoupled-modality characteristic by prompt consistency, which ignores effective interaction between prompts. To model the deep yet sufficient cross-modal interaction and enhance the generalization between both seen and unseen tasks, in this paper, we propose a novel coupled and decoupled prompt learning framework, dubbed PromptCD, for vision-language models. Specifically, we introduce a bi-directional coupled-modality mechanism to intensify the interaction between both vision and language branches. Additionally, we propose mixture consistency to further improve the generalization and discrimination of the models on unseen tasks. The integration of such a mechanism and consistency facilitates the proposed framework adaptation for various downstream tasks. We conduct extensive experiments on 11 image classification datasets under a range of evaluation protocols, including base-to-novel and domain generalization, and cross-dataset recognition. Experimental results demonstrate that our proposed PromptCD overall outperforms state-of-the-art methods.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 10561-10573
MODDP: A Multi-modal Open-domain Chinese Dataset for Dialogue Discourse Parsing
Chen Gong, DeXin Kong, Suxian Zhao, Xingyu Li, Guohong Fu. Findings of the Association for Computational Linguistics ACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 10561-10573
Open AccessMODDP: A Multi-modal Open-domain Chinese Dataset for Dialogue Discourse Parsing
Chen Gong, DeXin Kong, Suxian Zhao, Xingyu Li, Guohong Fu. Findings of the Association for Computational Linguistics ACL 2024. 2024.