Papers with Code
Papers with Code at Beyond Market Intelligence is a file of 2 stories. The newest of them: “Explore how an open-source community is reshaping access to AI research” and “Explore how hybrid search transforms discovery on Papers with Code”. Papers with Code is back, and this time it belongs to everyone. Building a better search engine for research papers rarely comes down to a single clever trick. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every Papers with Code story on Beyond Market Intelligence, newest first.
Explore how an open-source community is reshaping access to AI research
Papers with Code is back, and this time it belongs to everyone. Hugging Face has open-sourced the revived AI research tracker under an Apache 2.0 license, inviting the community to build the best paper interface together. Niels Rogge, working with Claude and Codex, resurrected the original site Meta acquired and shut down. The codebase is now public on GitHub, with a FastAPI backend, React frontend, and a publicly available API.
Explore how hybrid search transforms discovery on Papers with Code
Building a better search engine for research papers rarely comes down to a single clever trick. On Papers with Code, Niels Rogge shows how combining PostgreSQL's pgvector with Qwen3 embeddings creates a hybrid system that outperforms keyword or semantic search alone. What stands out is the pragmatic stack: batch embeddings via Hugging Face Jobs, storage in Buckets, and a live model on Inference Endpoints. That same infrastructure drives related-paper recommendations. It's a thoughtful, reproducible approach.