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.
RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation
Eye of Judgement: Dissecting the Evaluation of Russian-speaking LLMs with POLLUX
Cascading Adversarial Bias from Injection to Distillation in Language Models
Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards
Self-Correcting Code Generation Using Small Language Models
VERINA: Benchmarking Verifiable Code Generation
Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static Verification
OSS-UAgent: An Agent-based Usability Evaluation Framework for Open Source Software
LLM Performance for Code Generation on Noisy Tasks
Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems
SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving
Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach
Training Language Models to Generate Quality Code with Program Analysis Feedback
HiLDe: Intentional Code Generation via Human-in-the-Loop Decoding
DeepRTL2: A Versatile Model for RTL-Related Tasks
Rendering-Aware Reinforcement Learning for Vector Graphics Generation
An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning
Style2Code: A Style-Controllable Code Generation Framework with Dual-Modal Contrastive Representation Learning
Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation
Learning to Reason without External Rewards
Large Language Models in Code Co-generation for Safe Autonomous Vehicles
ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection
Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation
An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation
LEGO-Compiler: Enhancing Neural Compilation Through Translation Composability
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Large Language Models for IT Automation Tasks: Are We There Yet?
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
Architectures of Error: A Philosophical Inquiry into AI and Human Code Generation
Autocomp: LLM-Driven Code Optimization for Tensor Accelerators
SEW: Self-Evolving Agentic Workflows for Automated Code Generation
ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.