We evaluate DeepCode on the PaperBench benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 ...

😭 GraphRAG is good and powerful, but the official implementation is difficult/painful to read or hack. 😊 This project provides a smaller, faster, cleaner ...

Abstract: Regardless of the years of implementation, peer assessment is still with some limitations and could be applied to technical courses like computer science and software engineering, as much as ...

Abstract: Many scientific researches require the observation of microscopic images of samples under high magnetic fields. Due to the strong effect of high magnetic fields on magnetic materials and ...