Rohan Wadhawan's picture

3 1 7

Rohan Wadhawan

rohan598

·

https://www.rohanwadhawan.com

AI & ML interests

Natural Language Generation, Computer Vision, LLM, Multimodal Learning, Generative AI

Articles

Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?

Organizations

rohan598's activity

upvoted a paper 9 months ago

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models

Paper • 2401.13311 • Published Jan 24 • 10