Papers by Huaiwen Zhang
Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels, but their effective integration is non-trivial. |
| Approach: | They propose a global label propagation network with LLM-based pseudo labels for multimodal fake news detection which integrates LLM capabilities via label propagations. |
| Outcome: | The proposed model outperforms state-of-the-art models on benchmark datasets showing that it can propagate pseudo labels among all samples. |
MSCode: Advancing Human Motion-Language Understanding via Modality-Shared Codebook (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for motion understanding lack precise alignment between motion and modalities . existing methods lack precise semantics and a mismatch between motion, text . |
| Approach: | They propose a modality-shared codebook that enables unified representation learning and precise alignment between motion and linguistic modalities. |
| Outcome: | The proposed model surpasses current state-of-the-art methods in many areas . it enables unified representation learning and precise alignment of motion and modalities . |
CSI: An Investigative Multi-Agent Framework for Explainable Short Video Fake News Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for short video fake news detection rely on black-box MSLMs with poor explainability and superficial understanding or on specific prompt strategies for Multimodal Large Language Models (MLLMs) |
| Approach: | They propose a multi-agent framework called CSI for short video fake news detection. |
| Outcome: | The proposed framework provides rigorous explanations while achieving state-of-the-art performance on two real-world datasets. |
Cross-domain Rumor Detection via Test-Time Adaptation and Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches focus on within-domain tasks, resulting in suboptimal performance in cross-domain scenarios due to domain shifts. |
| Approach: | They propose a framework that incorporates both single-domain model and target graph adaptation strategies tailored to the unique requirements of cross-domain rumor detection. |
| Outcome: | The proposed framework surpasses existing methods in rumor detection on social media. |