Hammad Ayyubi

multimodal learning (7) large language model (2) external knowledge (2) vision-language model (2) image captioning (2) weakly supervised learning (2) visual question answering (1) curriculum learning (1) benchmark evaluation (1) named entity recognition (1) weakly-supervised learning (1) natural language processing (1) document understanding (1) video understanding (1) semantic alignment (1) self-supervised learning (1) visual grounding (1) synthetic data generation (1) visual reasoning (1) video captioning (1)