Jihyung Kil

multi-modal learning (5) visual question answering (3) multimodal learning (3) zero-shot learning (2) agent system (2) autonomous agent (2) weakly supervised learning (1) visual reasoning (1) benchmark evaluation (1) human-computer interaction (1) text classification (1) embodied ai (1) instruction following (1) semantic representation (1) document representation (1) chain-of-thought reasoning (1) efficient computing (1) visual context (1) neural network optimization (1) data augmentation (1)