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.
Large Language Models for Scientific Synthesis, Inference and Explanation
GameGPT: Multi-agent Collaborative Framework for Game Development
Octopus: Embodied Vision-Language Programmer from Environmental Feedback
Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models
Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Mistral 7B
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
Integrating Graphs with Large Language Models: Methods and Prospects
CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation
LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation
AUTOPARLLM: GNN-Guided Automatic Code Parallelization using Large Language Models
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Predicting Emergent Abilities with Infinite Resolution Evaluation
$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
GPT-4 as an interface between researchers and computational software: improving usability and reproducibility
Large Language Models as Analogical Reasoners
Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performance
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation
GenSim: Generating Robotic Simulation Tasks via Large Language Models
CAT-LM: Training Language Models on Aligned Code And Tests
L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs
SEED: Domain-Specific Data Curation With Large Language Models
Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
Are Human-generated Demonstrations Necessary for In-context Learning?
LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression
OpenAi's GPT4 as coding assistant
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.