2026
ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning
AAAI 2026technical
Retrieval-augmented generation (RAG) has greatly improved Large Language Models (LLMs) by adding external knowledge. However, current RAG-based methods face difficulties with long-context video understanding due to two main challenges. First, Current RAG-based methods for long-context video understa