2 papers
cs.CV2025
MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding
Shiwen Cao, Zhaoxing Zhang, Junming Jiao +4
Even in the era of rapid advances in large models, video understanding remains a highly challenging task. Compared to texts or images, videos commonly contain more information with…
cs.LG2024
DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering
Zijian Hei, Weiling Liu, Wenjie Ou +5
Retrieval-Augmented Generation (RAG) has recently demonstrated the performance of Large Language Models (LLMs) in the knowledge-intensive tasks such as Question-Answering (QA). RAG…