Pradyumna Narayana

multimodal learning (7) vision-language model (2) navigation agent (2) image understanding (2) vision-language navigation (2) contrastive learning (2) vision-and-language navigation (2) knowledge distillation (1) text-to-image synthesis (1) few-shot learning (1) text style transfer (1) weak supervision (1) deep learning (1) multimodal retrieval (1) content moderation (1) image captioning (1) multi-modal large language model (1) cross-modal alignment (1) vision language model (1) convolutional neural network (1)