Cards

Developer-Gathered, AI-Crafted, Human-Checked.

RAG vs KAG: A Comparative Analysis of Retrieval-Augmented Generation and Knowledge-Augmented Generation

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

On the Theoretical Limitations of Embedding-Based Retrieval

Key-value memory in the brain

Learning Facts at Scale with Active Reading

Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework

Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward

AGENT KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

RAPTOR: RECURSIVE ABSTRACTIVE PROCESSING FOR TREE-ORGANIZED RETRIEVAL

LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval

Enhancing Retrieval-Augmented Generation: A Study of Best Practices

Don’t Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning

Retrieval-Augmented Reasoning with Lean Language Models

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

Building a web search engine from scratch in two months with 3 billion neural embeddings

Lost in the Middle: How Language Models Use Long Contexts

The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs

LEANN: A Low-Storage Vector Index

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion