RAG - a Testerpce Collection

Testerpce 's Collections

Agent

MoE

RAG

State space LLM

Partial layer training LLMs

Math

Dataset and Data processing

Video understanding

Reinforcement learning

RAG

updated 30 days ago

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Paper • 2410.08815 • Published Oct 11 • 41