Tag: Vision-Language Models
Browse our exclusive articles!
Chitrakshara: Massive Multilingual Dataset for Indian Languages
Discover Chitrakshara, a large multilingual multimodal dataset designed to enhance AI models for diverse Indian languages and cultural contexts.
DISCO: Advanced Document Intelligence Evaluation Suite
Discover DISCO, a powerful suite for evaluating OCR and vision-language models across diverse documents like handwritten, multilingual, and medical forms.
SCoOP: Enhancing Uncertainty Quantification in Multi-VLM Systems
Discover SCoOP, a novel framework for uncertainty quantification and hallucination detection in multi Vision-Language Model systems, boosting AI reliabilit...