Noise-resilient RAG 구조를 통한 VLM의 외부 지식 추론 안정성 확보
📄Paper: RORA-VLM: Robust Retrieval Augmentation for Vision Language Models
📄Paper: RORA-VLM: Robust Retrieval Augmentation for Vision Language Models
LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?
Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models