Hyounghun Kim

multimodal learning (5) conversational agent (4) large language model (3) dialogue system (3) multi-session dialogue (2) vision-language transformer (2) reading comprehension (2) visual question answering (2) embodied agent (2) retrieval-augmented generation (2) benchmark evaluation (2) variational autoencoder (2) trajectory prediction (2) vision-language model (2) visual dialogue (2) neural machine translation (2) multi-modal learning (2) voice conversion (1) in-context learning (1) temporal dynamics (1)