A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Songyue Han, Mingyu Wang, Jialong Zhang, et al.
A comprehensive survey of LLMs covering architectures, key technologies, interdisciplinary integrations, optimization, applications, and challenges.
Haoru Tan, Wang Wang, Sitong Wu, et al.
Dataset Distillation by Influence Matching aligns the final outcome of training by learning a compact synthetic set whose effect on converged parameters matches that of the full dataset.
Unknown
This paper investigates whether long-context language models can replace traditional tools like retrieval systems and databases for knowledge-intensive tasks.
Unknown
This paper proposes QIMG-7 and source-aware resolution to improve multimodal RAG reliability by resolving conflicts before fusion.
Unknown
This paper proposes enhancing graph-based retrieval-augmented generation (RAG) with robust retrieval techniques to improve factual accuracy.
Unknown
This paper proposes a reinforcement learning framework to make knowledge graph retrieval-augmented generation more efficient and transferable across domains.
Unknown
MedGraphRAG introduces a graph-based RAG framework to improve safety and accuracy of medical LLMs by structuring medical knowledge as a graph.
Unknown
Proposes Ket-rag, a cost-efficient multi-granular indexing framework for Graph-RAG that reduces indexing costs while maintaining retrieval quality.
Unknown
MedGraphRAG enhances LLMs for evidence-based medical responses using a graph-based retrieval-augmented generation framework.
Unknown
This paper proposes LongRAG, a framework that leverages long-context LLMs to improve the efficiency and effectiveness of retrieval-augmented generation.
Unknown
This paper introduces GraphRAG, a retrieval-augmented generation method that leverages knowledge graphs to improve downstream task performance.
Unknown
This paper introduces parametric retrieval augmented generation (Parametric RAG), which integrates parametric knowledge directly into the RAG framework to improve reliability and reduce reliance on external retrieval.