This project proposes an instructions-based abstracting approach CapAlign for harmful memes detection, in zero-shot visual question- answering settings. Please refer to our paper for more details: Junhui Ji†, Xuanrui Lin†, and Usman Naseem. 2024. CapAlign: Improving Cross Modal Alignment via Informative Captioning for Harmful Meme Detection. In Proceedings of the ACM Web Conference 2024 (WWW ’24), May 13–17, 2024, Singapore, Singapore. ACM, New York, NY, USA, 10 pages. https://doi.org/10.1145/3589334.3648146