A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues
Paper • 2305.04530 • Published
This space contains the cold start checkpoints of ModCR on PMR and VCR.
It also includes the pretrained phrase-level text-language alignmenter.
More detailed Description of ModCR are presented in Paper Link: https://arxiv.org/pdf/2305.04530.pdf
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support