Vlad I Morariu

document understanding (2) self-supervised learning (1) in-context learning (1) multimodal learning (1) visual grounding (1) synthetic data generation (1) document analysis (1) region of interest (1) large multimodal model (1) multimodal large language model (1) multimodal embedding (1) grounded generation (1) element localization (1) document layout (1) multimodal grounding (1) layout understanding (1) generative feedback (1) large language model (1) multi-agent system (1) document localization (1)