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.
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?
PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models
Mind the Gap: A Practical Attack on GGUF Quantization
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
PPT: A Process-based Preference Learning Framework for Self Improving Table Question Answering Models
Evaluating the Energy-Efficiency of the Code Generated by LLMs
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation
Towards a Science of Causal Interpretability in Deep Learning for Software Engineering
R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
dKV-Cache: The Cache for Diffusion Language Models
MAPS: A Multilingual Benchmark for Global Agent Performance and Security
SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation
CLEVER: A Curated Benchmark for Formally Verified Code Generation
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
Knowledge Graph Based Repository-Level Code Generation
CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation
Text Generation Beyond Discrete Token Sampling
Self-Evolving Curriculum for LLM Reasoning
From Reasoning to Code: GRPO Optimization for Underrepresented Languages
AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection
On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
AGI-Elo: How Far Are We From Mastering A Task?
AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models
EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models
TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
Understanding Complexity in VideoQA via Visual Program Generation
Krikri: Advancing Open Large Language Models for Greek
EVALOOP: Assessing LLM Robustness in Programming from a Self-consistency Perspective
OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration
VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation
SOCIA: An End-to-End Agentic Framework for Automated Cyber-Physical-Social Simulator Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.