Rui Cao

Rui Cao is a Researcher at the Department of Computer Science and Technology at the University of Cambridge, located in the William Gates Building. Their work focuses on multimodal AI systems, particularly addressing challenges in misinformation detection, hate speech moderation, and the analysis of internet memes. Rui's research integrates computer vision, natural language processing, and large language models to tackle real-world societal issues such as online toxicity and factual verification.

Key research emphases include:

• Multimodal fact-checking systems (e.g., AVerImaTeC dataset)
• LLM-based hallucination mitigation in vision-language models
• Automated hate speech detection in memes and live video streams
• Zero-shot and few-shot learning for visual question answering
• Tools for meme analysis (e.g., Matk Toolkit)

Recent work has explored adversarial data augmentation (HateGAN), modular neural architectures for hateful meme detection (Pro-CAP), and frameworks for resolving conflicting evidence in automated fact-checking. Their contributions span both technical advancements and ethical considerations in AI deployment.

Research has been published in top-tier venues, with a focus on applications to social media content moderation and misinformation mitigation. No awards or grants are explicitly listed in the provided materials.