2025

REDEEMing Modality Information Loss: Retrieval-Guided Conditional Generation for Severely Modality Missing Learning
REDEEMing Modality Information Loss: Retrieval-Guided Conditional Generation for Severely Modality Missing Learning

Jian Lang, Rongpei Hong, Zhangtao Cheng, Yong Wang, Ting Zhong, Fan Zhou† († corresponding author)

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025 CCF-A Full Paper

We propose REDEEM, the extension work of our RAGPT accetped to AAAI 2025, a novel framework that pioneers a retrieval-guided conditional generation paradigm for enhancing the robustness of pre-trained Multimodal Transformer.

[Paper] [Code]

REDEEMing Modality Information Loss: Retrieval-Guided Conditional Generation for Severely Modality Missing Learning

Jian Lang, Rongpei Hong, Zhangtao Cheng, Yong Wang, Ting Zhong, Fan Zhou† († corresponding author)

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025 CCF-A Full Paper

We propose REDEEM, the extension work of our RAGPT accetped to AAAI 2025, a novel framework that pioneers a retrieval-guided conditional generation paradigm for enhancing the robustness of pre-trained Multimodal Transformer.

[Paper] [Code]

Biting Off More Than You Can Detect: Retrieval-Augmented Multimodal Experts for Short Video Hate Detection
Biting Off More Than You Can Detect: Retrieval-Augmented Multimodal Experts for Short Video Hate Detection

Jian Lang, Rongpei Hong, Jin Xu, Xovee Xu, Yili Li, Fan Zhou† († corresponding author)

The Web Conference (WWW) 2025 CCF-A Full Paper

We introduce MoRE (Mixture of Retrieval-augmented multimodal Experts), a novel framework designed to enhance short video hate detection.

[Paper] [Code]

Biting Off More Than You Can Detect: Retrieval-Augmented Multimodal Experts for Short Video Hate Detection

Jian Lang, Rongpei Hong, Jin Xu, Xovee Xu, Yili Li, Fan Zhou† († corresponding author)

The Web Conference (WWW) 2025 CCF-A Full Paper

We introduce MoRE (Mixture of Retrieval-augmented multimodal Experts), a novel framework designed to enhance short video hate detection.

[Paper] [Code]

Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning
Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning

Jian Lang*, Zhangtao Cheng*, Ting Zhong, Fan Zhou† (* equal contribution, † corresponding author)

The Association for the Advancement of Artificial Intelligence (AAAI) 2025 CCF-A Full Paper

We propose RAGPT, a novel Retrieval-AuGmented dynamic Prompt Tuning framework for enhancing the robustness of pre-trained Multimodal Transformer under modality missing conditions.

[Paper] [Code]

Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning

Jian Lang*, Zhangtao Cheng*, Ting Zhong, Fan Zhou† (* equal contribution, † corresponding author)

The Association for the Advancement of Artificial Intelligence (AAAI) 2025 CCF-A Full Paper

We propose RAGPT, a novel Retrieval-AuGmented dynamic Prompt Tuning framework for enhancing the robustness of pre-trained Multimodal Transformer under modality missing conditions.

[Paper] [Code]

Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation
Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation

Rongpei Hong*, Jian Lang*, Ting Zhong, Fan Zhou† (* equal contribution, † corresponding author)

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2025 CCF-A Full Paper

We propose CRAVE, a novel CRoss-domAin retrieVal augmEntation framework that transfers knowledge from resource-rich image-text domain to enhance malicious video detection.

[Paper] [Code]

Borrowing Eyes for the Blind Spot: Overcoming Data Scarcity in Malicious Video Detection via Cross-Domain Retrieval Augmentation

Rongpei Hong*, Jian Lang*, Ting Zhong, Fan Zhou† (* equal contribution, † corresponding author)

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2025 CCF-A Full Paper

We propose CRAVE, a novel CRoss-domAin retrieVal augmEntation framework that transfers knowledge from resource-rich image-text domain to enhance malicious video detection.

[Paper] [Code]

Seeing the Unseen in Micro-Video Popularity Prediction: Self-Correlation Retrieval for Missing Modality Generation
Seeing the Unseen in Micro-Video Popularity Prediction: Self-Correlation Retrieval for Missing Modality Generation

Zhangtao Cheng*, Jian Lang*, Ting Zhong, Fan Zhou† (* equal contribution, † corresponding author)

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025 CCF-A Full Paper

We propose SCRAG, a novel Self-Correlation Retrieval-Augmented Generative framework designed to enhance missing-modality robustness in micro-video popularity prediction.

[Paper] [Code]

Seeing the Unseen in Micro-Video Popularity Prediction: Self-Correlation Retrieval for Missing Modality Generation

Zhangtao Cheng*, Jian Lang*, Ting Zhong, Fan Zhou† (* equal contribution, † corresponding author)

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025 CCF-A Full Paper

We propose SCRAG, a novel Self-Correlation Retrieval-Augmented Generative framework designed to enhance missing-modality robustness in micro-video popularity prediction.

[Paper] [Code]

Following Clues, Approaching the Truth: Explainable Micro-Video Rumor Detection via Chain-of-Thought Reasoning
Following Clues, Approaching the Truth: Explainable Micro-Video Rumor Detection via Chain-of-Thought Reasoning

Rongpei Hong, Jian Lang, Jin Xu, Zhangtao Cheng, Ting Zhong†, Fan Zhou († corresponding author)

The Web Conference (WWW) 2025 CCF-A Full Paper

In this work, we introduce ExMRD, a novel Explainable Micro-video Rumor Detection (MVRD) framework designed to generate detailed and coherent explanations for enhancing MVRD.

[Paper] [Code]

Following Clues, Approaching the Truth: Explainable Micro-Video Rumor Detection via Chain-of-Thought Reasoning

Rongpei Hong, Jian Lang, Jin Xu, Zhangtao Cheng, Ting Zhong†, Fan Zhou († corresponding author)

The Web Conference (WWW) 2025 CCF-A Full Paper

In this work, we introduce ExMRD, a novel Explainable Micro-video Rumor Detection (MVRD) framework designed to generate detailed and coherent explanations for enhancing MVRD.

[Paper] [Code]

REAL: Retrieval-Augmented Prototype Alignment for Improved Fake News Video Detection
REAL: Retrieval-Augmented Prototype Alignment for Improved Fake News Video Detection

Yili Li, Jian Lang, Rongpei Hong, Qing Chen, Zhangtao Cheng, Jia Chen, Ting Zhong, Fan Zhou† († corresponding author)

IEEE International Conference on Multimedia & Expo (ICME) 2025 CCF-B Full Paper

We propose a novel model-agnostic framework REAL that generates manipulation-aware representations to enhance existing methods in detecting fake news videos.

[Paper] [Code]

REAL: Retrieval-Augmented Prototype Alignment for Improved Fake News Video Detection

Yili Li, Jian Lang, Rongpei Hong, Qing Chen, Zhangtao Cheng, Jia Chen, Ting Zhong, Fan Zhou† († corresponding author)

IEEE International Conference on Multimedia & Expo (ICME) 2025 CCF-B Full Paper

We propose a novel model-agnostic framework REAL that generates manipulation-aware representations to enhance existing methods in detecting fake news videos.

[Paper] [Code]

Predicting Micro-video Popularity via Multi-modal Retrieval Augmentation
Predicting Micro-video Popularity via Multi-modal Retrieval Augmentation

Ting Zhong, Jian Lang, Yifan Zhang, Zhangtao Cheng†, Kunpeng Zhang, Fan Zhou († corresponding author)

Special Interest Group on Information Retrieval (SIGIR) 2024 CCF-A Short Paper

We present MMRA, a multi-modal retrieval-augmented popularity prediction model that enhances prediction accuracy using relevant retrieved information.

[Paper] [Code]

Predicting Micro-video Popularity via Multi-modal Retrieval Augmentation

Ting Zhong, Jian Lang, Yifan Zhang, Zhangtao Cheng†, Kunpeng Zhang, Fan Zhou († corresponding author)

Special Interest Group on Information Retrieval (SIGIR) 2024 CCF-A Short Paper

We present MMRA, a multi-modal retrieval-augmented popularity prediction model that enhances prediction accuracy using relevant retrieved information.

[Paper] [Code]

Generative Thinking, Corrective Action: User-Friendly Composed Image Retrieval via Automatic Multi-Agent Collaboration
Generative Thinking, Corrective Action: User-Friendly Composed Image Retrieval via Automatic Multi-Agent Collaboration

Zhangtao Cheng, Yuhao Ma, Jian Lang, Rongpei Hong, Kunpeng Zhang, Yong Wang, Ting Zhong, Fan Zhou† († corresponding author)

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025 CCF-A Full Paper

We propose a novel framework -- Automatic Multi-Agent Collaboration for Zero-Shot Composed Image Retrieval (AutoCIR).

[Paper] [Code]

Generative Thinking, Corrective Action: User-Friendly Composed Image Retrieval via Automatic Multi-Agent Collaboration

Zhangtao Cheng, Yuhao Ma, Jian Lang, Rongpei Hong, Kunpeng Zhang, Yong Wang, Ting Zhong, Fan Zhou† († corresponding author)

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025 CCF-A Full Paper

We propose a novel framework -- Automatic Multi-Agent Collaboration for Zero-Shot Composed Image Retrieval (AutoCIR).

[Paper] [Code]

In-context Prompt-augmented Micro-video Popularity Prediction
In-context Prompt-augmented Micro-video Popularity Prediction

Zhangtao Cheng, Jiao Li, Jian Lang, Ting Zhong, Fan Zhou† († corresponding author)

The Association for the Advancement of Artificial Intelligence (AAAI) 2025 CCF-A Full Paper

Inspired by prompt learning, we propose ICPF, a novel In-Context Prompt-augmented Framework to enhance popularity prediction.

[Paper] [Code]

In-context Prompt-augmented Micro-video Popularity Prediction

Zhangtao Cheng, Jiao Li, Jian Lang, Ting Zhong, Fan Zhou† († corresponding author)

The Association for the Advancement of Artificial Intelligence (AAAI) 2025 CCF-A Full Paper

Inspired by prompt learning, we propose ICPF, a novel In-Context Prompt-augmented Framework to enhance popularity prediction.

[Paper] [Code]