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/salt-nlp/dylan

공식 코드

A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

https://github.com/samholt/l2mac

공식 코드

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation

https://github.com/sani903/interactivesweagents

공식 코드

Interactive Agents to Overcome Ambiguity in Software Engineering

https://github.com/sanjayss34/codevqa

공식 코드

Modular Visual Question Answering via Code Generation

https://github.com/scale-lab/MetRex

공식 코드

MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs

https://github.com/scaleapi/plansearch

공식 코드

Planning In Natural Language Improves LLM Search For Code Generation

https://github.com/scientific-computing-lab-nrcn/monocoder

공식 코드

MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks

https://github.com/scientific-computing-lab-nrcn/mpi-rical

공식 코드

MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers

https://github.com/scientific-computing-lab-nrcn/mpi-rigen

공식 코드

MPIrigen: MPI Code Generation through Domain-Specific Language Models

https://github.com/scientific-computing-lab/monocoder

공식 코드

MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks

https://github.com/seamoke/Human-Think-Language

공식 코드

How Do Humans Write Code? Large Models Do It the Same Way Too

https://github.com/secureaiautonomylab/autosafecoder

공식 코드

AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing

https://github.com/seekingdream/ppm

공식 코드

PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models

https://github.com/seketeam/deveval

공식 코드

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories

https://github.com/seketeam/evocodebench

공식 코드

EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories

https://github.com/sensellm/reflectioncoder

공식 코드

ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation

https://github.com/sewoonglab/byte-sampler

공식 코드

Sampling from Your Language Model One Byte at a Time

https://github.com/sfu-db/CleanAgent

공식 코드

CleanAgent: Automating Data Standardization with LLM-based Agents

https://github.com/shahinhonarvar/turbulence-benchmark

공식 코드

Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code

https://github.com/shailja-thakur/vgen

공식 코드

Benchmarking Large Language Models for Automated Verilog RTL Code Generation

https://github.com/sharc-lab/gnn-builder

공식 코드

GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization

https://github.com/shirley-wu/daco

공식 코드

DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation

https://github.com/shixun404/FT_KMeans

공식 코드

FT K-means: A High-Performance K-means on GPU with Fault Tolerance

https://github.com/shoushouyu/automated-paper-to-code

공식 코드

AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers

https://github.com/shubhamrgandhi/codegen-strong-weak-collab

공식 코드

An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation

https://github.com/shuishida/langprop

공식 코드

LangProp: A code optimization framework using Large Language Models applied to driving

https://github.com/shuyanzhou/doccoder

공식 코드

DocPrompting: Generating Code by Retrieving the Docs

https://github.com/shuyanzhou/docprompting

공식 코드

DocPrompting: Generating Code by Retrieving the Docs

https://github.com/si0wang/vicrit

공식 코드

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

https://github.com/sinaris76/turtlebench

공식 코드

TurtleBench: A Visual Programming Benchmark in Turtle Geometry

https://github.com/sjtu-compling/mela

공식 코드

MELA: Multilingual Evaluation of Linguistic Acceptability

https://github.com/skpig/MPSC

공식 코드

Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency

https://github.com/slp-rl/budget-realloc

공식 코드

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation

https://github.com/smartdataanalytics/codecai

공식 코드

Transformer with Tree-order Encoding for Neural Program Generation

https://github.com/snowflakedb/arcticinference

공식 코드

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

https://github.com/songmzhang/dskdv2

공식 코드

A Dual-Space Framework for General Knowledge Distillation of Large Language Models

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