Papers with Code 아카이브

Code Generation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 28
보존된 평가 기록: 241

Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.

Source: Deep Learning for Source Code Modeling and Generation

Image source: Measuring Coding Challenge Competence With APPS

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/facebookresearch/coder_reviewer_reranking

공식 코드

Coder Reviewer Reranking for Code Generation

https://github.com/facebookresearch/docagent

공식 코드

DocAgent: A Multi-Agent System for Automated Code Documentation Generation

https://github.com/facebookresearch/llama

공식 코드

LLaMA: Open and Efficient Foundation Language Models

https://github.com/facebookresearch/mbr-exec

공식 코드

Natural Language to Code Translation with Execution

https://github.com/fangwei123456/spikingjelly

공식 코드

SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence

https://github.com/fanqiwan/fusellm

공식 코드

Knowledge Fusion of Large Language Models

https://github.com/fdevinc/ungar

공식 코드

Ungar $\unicode{x2013}$ A C++ Framework for Real-Time Optimal Control Using Template Metaprogramming

https://github.com/ffd8ffe/babelbench

공식 코드

BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data

https://github.com/fhaer/llm-cmi

공식 코드

Conceptual Model Interpreter for Large Language Models

https://github.com/fhaer/multi-agent-llm-system

공식 코드

Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications

https://github.com/flagopen/taco

공식 코드

TACO: Topics in Algorithmic COde generation dataset

https://github.com/floridsleeves/llmdebugger

공식 코드

Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step

https://github.com/floridsleeves/robustapi

공식 코드

Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation

https://github.com/flowss/bugsinllms

공식 코드

Bugs in Large Language Models Generated Code: An Empirical Study

https://github.com/foundationagents/aflow

공식 코드

AFlow: Automating Agentic Workflow Generation

https://github.com/fsoft-ai4code/agilecoder

공식 코드

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology

https://github.com/fsoft-ai4code/hyperagent

공식 코드

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

https://github.com/fsoft-ai4code/srank-coderanker

공식 코드

Functional Overlap Reranking for Neural Code Generation

https://github.com/fsoft-ai4code/thevault

공식 코드

The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

https://github.com/fudanselab/classeval

공식 코드

ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation

https://github.com/fuyu-quant/iblm

공식 코드

Inductive-bias Learning: Generating Code Models with Large Language Model

https://github.com/gabegrand/lilo

공식 코드

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

https://github.com/gabeguo/any-order-speculative-decoding

공식 코드

Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding

https://github.com/gabeorlanski/bimodal-code-generation

공식 코드

Evaluating How Fine-tuning on Bimodal Data Effects Code Generation

https://github.com/gabeorlanski/stackoverflow-encourages-cheating

공식 코드

Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation

https://github.com/gair-nlp/factool

공식 코드

FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios

https://github.com/galirage/gpr-bench

공식 코드

Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets

https://github.com/gangiswag/cornstack

공식 코드

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

https://github.com/gautierdag/tokenizer-bench

공식 코드

Getting the most out of your tokenizer for pre-training and domain adaptation

https://github.com/geekan/metagpt

공식 코드

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

https://github.com/geliang0114/nvagent

공식 코드

nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow

https://github.com/gen-verse/cure

공식 코드

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

https://github.com/gersteinlab/biocoder

공식 코드

BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models

https://github.com/gersteinlab/locagent

공식 코드

LocAgent: Graph-Guided LLM Agents for Code Localization

https://github.com/gersteinlab/ml-bench

공식 코드

ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code

https://github.com/ghost-in-moss/ghostos

공식 코드

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.