Hello, Brady! Thanks for compiling so many great methods into this very helpful resource. Our paper is a multimodal CoT method that has been out for a little while and improves the compositional reasoning and general multimodal capabilities of MLLMs/LMMs. Would you mind adding it to your resource? Thanks!
Hello, Brady! Thanks for compiling so many great methods into this very helpful resource. Our paper is a multimodal CoT method that has been out for a little while and improves the compositional reasoning and general multimodal capabilities of MLLMs/LMMs. Would you mind adding it to your resource? Thanks!
Paper [CVPR 2024]: https://arxiv.org/abs/2311.17076 Code: https://github.com/chancharikmitra/CCoT/tree/main