3 papers
cs.CL2024
Unified Multimodal Interleaved Document Representation for Retrieval
Jaewoo Lee, Joonho Ko, Jinheon Baek +2
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typ…
cs.CV2024
Concept-skill Transferability-based Data Selection for Large Vision-Language Models
Jaewoo Lee, Boyang Li, Sung Ju Hwang
Instruction tuning, or supervised finetuning on extensive task-specific data, is necessary for Large Vision-Language Models (LVLMs) to generalize well across a broad range of visio…
cs.CV2023
STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment
Jaewoo Lee, Jaehong Yoon, Wonjae Kim +2
Continuously learning a variety of audio-video semantics over time is crucial for audio-related reasoning tasks in our ever-evolving world. However, this is a nontrivial problem an…