Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions

The codebase will be uploaded and tidied up shortly. A proper and full documentation of the codebase is expected to be provided by 28th February 2024.

P.S. (3th March, 12:50AM GMT+4): Appreciate all the attention to this work. I have been overwhelmed with a ton of work recently (e.g., reviewing duties and interviews). I just wrapped up majority of my backlog and promise to tidy up this codebase over the next 2 days. I hope for your understanding.