❤️NL2Code A website where we can share the advances in large language models for NL2Code researches. ✏️Add Your Own Model/Benchmark/Metric/Product Follow the guide (model template, benchmar...

📙Model: CodeQwen1.5 📚Publisher: huggingface 🏠Author Affiliation: Qwen Group Model Size: 7B

📙Model: aiXcoder 📚Publisher: huggingface 🏠Author Affiliation: Peking University Model Size: 7B

📙Paper: SWE-agent 📚Publisher: arxiv 🏠Author Affiliation: Princeton University Contribution: SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can fix bugs and issues i...

📙Paper: The RealHumanEval Evaluating Large Language Models’ Abilities to Support Programmers GitHub: RealHumanEval 📚Publisher: arxiv 🏠Author Affiliation: MIT-IBM Watson AI Lab; Massachuset...

📙Paper: Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback 📚Publisher: arxiv 🏠Author Affiliation: Huazhong University of Science and Techno...

🗂️Benchmark Name: EvoCodeBench 📚Publisher: Arxiv 🏠Author Affiliation: Peking University 🔗URL: https://github.com/seketeam/EvoCodeBench

📙Paper: CodeS Natural Language to Code Repository via Multi-Layer Sketch 📚Publisher: arxiv 🏠Author Affiliation: Chinese Academy of Sciences; Peking University; Huawei; Shandong University ...

📙Paper: devika 📚Publisher: github 🏠Author Affiliation: stitionai Contribution: Devika is an advanced AI software engineer that can understand high-level human instructions, break them down...

📙Product: OpenDevin 📚Publisher: github 🏠Author Affiliation: OpenDevin Contribution: Devin represents a cutting-edge autonomous agent designed to navigate the complexities of software engin...