Course Readings
This page contains relevant papers, courses, and webpages organized by topic.
Topic: Code Large Language Models
- Code Llama - [2023]
- StarCoder - [2023]
- DeepSeek Coder - [2024]
- CodeSage - [2024]
- Llama - [2023]
- Llama 2 - [2023]
- CodeFuse - [2023]
- Casual Masking - [2022]
- SantaCoder - [2023]
- The Stack - [2022]
- 8K token context length - [2024]
- Fill-in-the-middle - [2022]
- Multi-Query-Attention - [2019]
- BERT - [2018]
- DeepSeek Coder Repo
- CodeFuse - [2023]
- Fill-in-the-middle - [2022]
- CodeGen - [2022]
- BPE - [2015]
- RoPE - [2021]
- Large Language Models Meet NL2Code - [2023]
- A Survey on Language Models for Code - [2023]
- Deep Learning for Source Code Modeling and Generation - [2020]
- CodeT5+ (Encoder-Decoder Models) - [2023]
- CodeFusion (Diffusion Models) - [2023]
- DALL-E 2 - [2022]
Topic: Evaluation of Code Models
- LiveCodeBench Repo
- HumanEval/Codex (Accuracy) - [2021]
- ReCode: Robustness Evaluation of Code Generation Models (Trustworthiness) - [2022]
- MBPP - [2021]
- DevBench: A Comprehensive Benchmark for Software Development - [2024]
- DevEval: Evaluating Code Generation in Practical Software Projects - [2024]
- CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion - [2023]
- Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT - [2023]
- ReCode: Robustness Evaluation of Code Generation Models (Trustworthiness) - [2022]
- CodeXGLUE - [2021]
- XLCoST - [2022]
- APPS - [2021]
- CodeContest/AlphaCode - [2022]
- DS-1000 - [2022]
- xCodeEval - [2023]
- BigCode Eval Harness
- BigCodeBench
- LMSYS Coding
Topic: Improving Code Generation
- CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context - [2022]
- RepoFusion: Training Code Models to Understand Your Repository - [2023]
- Guiding Language Models of Code with Global Context using Monitors - [2023]
- CodePlan: Repository-level Coding using LLMs and Planning - [2023]
- A^3-CodGen: A Repository-Level Code Generation Framework for Code Reuse with Local-Aware, Global-Aware, and Third-Party-Library-Aware - [2023]
- REPOFUSE: Repository-Level Code Completion with Fused Dual Context - [2024]
- Generation-Augmented Retrieval for Open-domain Question Answering - [2020]
- Query2doc: Query Expansion with Large Language Models - [2023]
Topic: Interpretability of Code Models
- Explainable AI - [2021]
- Rethinking Interpretability in the Era of Large Language Models - [2024]
- Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges - [2021]
- Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach - [2023]
- Benchmarking Causal Study to Interpret Large Language Models for Source Code - [2023]
- Towards Causal Deep Learning for Vulnerability Detection - [2023]
References
This course draws inspiration from the following sources:
- Generative Model for Code -- COMS 6998 by Baishakhi Ray, Columbia University
- Introduction to Program Synthesis -- 6.S981 by Armando Solar-Lezama, MIT
- Program Synthesis -- CSE 291 by Nadia Polikarpova, UCSD
- Program Synthesis for Everyone -- CS294 by Ras Bodik and Emina Torlak, University of Washington