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

Related Cards

LEANN: A Low-Storage Vector Index

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

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

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