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/Intelligent-CAT-Lab/AlphaTrans

공식 코드

AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation

https://github.com/JHU-CLSP/NeoCoder

공식 코드

Benchmarking Language Model Creativity: A Case Study on Code Generation

https://github.com/JetBrains-Research/codegen-metrics

공식 코드

Out of the BLEU: how should we assess quality of the Code Generation models?

https://github.com/Jun-jie-Huang/CoCoNote

공식 코드

Contextualized Data-Wrangling Code Generation in Computational Notebooks

https://github.com/Kodezi/Chronos

공식 코드

Kodezi Chronos: A Debugging-First Language Model for Repository-Scale, Memory-Driven Code Understanding

https://github.com/LZhengisme/self-infilling

공식 코드

Self-Infilling Code Generation

https://github.com/LingmaTongyi/Codev-Bench

공식 코드

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?

https://github.com/MAIL-Tele-AI/MalwareBench

공식 코드

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges

https://github.com/MarcOedingen/ChatGPT-Code-Detection

공식 코드

ChatGPT Code Detection: Techniques for Uncovering the Source of Code

https://github.com/Masum06/Text2App

공식 코드

Text2App: A Framework for Creating Android Apps from Text Descriptions

https://github.com/Mayur-Palavalli/LLM-IaC-generation

공식 코드

Using a Feedback Loop for LLM-based Infrastructure as Code Generation

https://github.com/Microsoft/PointerSQL

공식 코드

Natural Language to Structured Query Generation via Meta-Learning

https://github.com/NEUIR/CONAN

공식 코드

Building A Coding Assistant via the Retrieval-Augmented Language Model

https://github.com/NecoraNyaru/PInG

공식 코드

Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding

https://github.com/NellyW8/VeriReason

공식 코드

VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation

https://github.com/Nickolas-option/QA_on_Tabular_Data_SemEval2025_Task8

공식 코드

Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA

https://github.com/NoujoudNader/AiCode_DeepSeek

공식 코드

LLM & HPC:Benchmarking DeepSeek's Performance in High-Performance Computing Tasks

https://github.com/PlusLabNLP/Re-ReST

공식 코드

Re-ReST: Reflection-Reinforced Self-Training for Language Agents

https://github.com/Pranjal2041/AdaptiveConsistency

공식 코드

Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs

https://github.com/PrimisAI/nexus

공식 코드

Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation

https://github.com/PurCL/ProSec

공식 코드

ProSec: Fortifying Code LLMs with Proactive Security Alignment

https://github.com/RISElabQueens/InterTrans

공식 코드

InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation

https://github.com/RUCAIBox/Slow_Thinking_with_LLMs

공식 코드

ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests

https://github.com/RUCKBReasoning/DPO_Text2SQL

공식 코드

Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL

https://github.com/RickySkywalker/TheoremLlama

공식 코드

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

https://github.com/RuYunW/ADG-Seq2Seq

공식 코드

Embedding API Dependency Graph for Neural Code Generation

https://github.com/RyanLoil/ProjectEval

공식 코드

ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation

https://github.com/SEU-ProactiveSecurity-Group/LLM-PD

공식 코드

Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense

https://github.com/SS47816/AGI-Elo

공식 코드

AGI-Elo: How Far Are We From Mastering A Task?

https://github.com/SWU-CS-MediaLab/SADH

공식 코드

Self-supervised asymmetric deep hashing with margin-scalable constraint

https://github.com/SalesforceAIResearch/CodeChain

공식 코드

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

https://github.com/SalesforceAIResearch/PersDistill

공식 코드

Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation

https://github.com/SalesforceAIResearch/indict_code_gen

공식 코드

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness

https://github.com/Shadeeb-Hossain/LLM-for-RISC/blob/main/RISC_LLM.rar

공식 코드

Using LLM such as ChatGPT for Designing and Implementing a RISC Processor: Execution,Challenges and Limitations

https://github.com/ShambhaviCodes/CLIPOT

공식 코드

Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time Adaptation

https://github.com/SkAndMl/gpt-variations

공식 코드

Towards smaller, faster decoder-only transformers: Architectural variants and their implications

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