Papers with Code 아카이브
Code Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models
Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework
CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation
Optimizing AI-Assisted Code Generation
ChainStream: An LLM-based Framework for Unified Synthetic Sensing
DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production
What You See Is Not Always What You Get: An Empirical Study of Code Comprehension by Large Language Models
Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar
MaestroMotif: Skill Design from Artificial Intelligence Feedback
Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!
Exploring Coding Spot: Understanding Parametric Contributions to LLM Coding Performance
MAGE: A Multi-Agent Engine for Automated RTL Code Generation
AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework
ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
Copyright-Protected Language Generation via Adaptive Model Fusion
PyraNet: A Multi-Layered Hierarchical Dataset for Verilog
GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models
A Comparative Study on Code Generation with Transformers
Code generation and runtime techniques for enabling data-efficient deep learning training on GPUs
HyperGraphOS: A Meta Operating System for Science and Engineering
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
Evaluating and Aligning CodeLLMs on Human Preference
HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design
Automated LaTeX Code Generation from Handwritten Math Expressions Using Vision Transformer
If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs
PoTable: Towards Systematic Thinking via Stage-oriented Plan-then-Execute Reasoning on Tables
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
Survey of different Large Language Model Architectures: Trends, Benchmarks, and Challenges
A Multi-Agent Framework for Extensible Structured Text Generation in PLCs
Towards Rich Emotions in 3D Avatars: A Text-to-3D Avatar Generation Benchmark
Does Few-Shot Learning Help LLM Performance in Code Synthesis?
Commit0: Library Generation from Scratch
CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
Training Agents with Weakly Supervised Feedback from Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.