ExPO-HM ...
Official implementation of ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection, accepted at ICLR 2026. The approach uses multimodal reinforcement learning (GRPO) for interpretable and explainable content moderation.
Jingbiao Mei
PhD student at University of Cambridge
- Cambridge, UK
- University of Cambridge
- Website
- Google Scholar
- GitHub