Jinbae Im

multimodal learning (3) self-supervised learning (2) opinion summarization (2) text encoder-decoder (2) multi-task learning (1) object detection (1) scene graph generation (1) error detection (1) vision language model (1) transformer architecture (1) multimodal large language model (1) error correction (1) relation graph (1) gradient attribution (1) gradient-based attribution (1) reasoning enhancement (1) misalignment detection (1) multimodal encoder (1) error refinement (1) multimodal opinion summarization (1)