https://github.com/jetbrains-research/lca-baselines
공식 코드Long Code Arena: a Set of Benchmarks for Long-Context Code Models
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/jianguda/afm4acs
공식 코드https://github.com/jlx0/llm-automl
공식 코드Large Language Models Synergize with Automated Machine Learning
https://github.com/jokieleung/I-MCTS
공식 코드I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search
https://github.com/jonas-schmitt/evostencils
공식 코드Automating the Design of Multigrid Methods with Evolutionary Program Synthesis
https://github.com/jongwooko/distillm-2
공식 코드DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
https://github.com/jordiae/neural-compilers
공식 코드Learning C to x86 Translation: An Experiment in Neural Compilation
https://github.com/jpickard1/brad
공식 코드https://github.com/jrohsc/Chain-of-Code-Collapse
공식 코드Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation
https://github.com/jszheng21/race
공식 코드Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
https://github.com/juliacontrol/discretepids.jl
공식 코드https://github.com/jun-jie-huang/exeds
공식 코드Execution-based Evaluation for Data Science Code Generation Models
https://github.com/justinchiu/onecommon-gpt
공식 코드https://github.com/justinphan3110/CoTexT
공식 코드https://github.com/juyongjiang/codellmsurvey
공식 코드https://github.com/juzhengz/lori
공식 코드LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
https://github.com/jwliao1209/diffqrcode
공식 코드Diffusion-based Aesthetic QR Code Generation via Scanning-Robust Perceptual Guidance
https://github.com/jxh4945777/ChatEA
공식 코드Unlocking the Power of Large Language Models for Entity Alignment
https://github.com/kaist-dmlab/monaq
공식 코드https://github.com/kamel773/code_pair_classification
공식 코드Language Models are Better Bug Detector Through Code-Pair Classification
https://github.com/kamel773/llm-code-refine
공식 코드https://github.com/kandluis/code-gen
공식 코드https://github.com/kashifraz/sdagc
공식 코드On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices
https://github.com/katsumiok/askit-artifact
공식 코드AskIt: Unified Programming Interface for Programming with Large Language Models
https://github.com/katsumiok/pyaskit
공식 코드AskIt: Unified Programming Interface for Programming with Large Language Models
https://github.com/katsumiok/ts-askit
공식 코드AskIt: Unified Programming Interface for Programming with Large Language Models
https://github.com/kcxain/musl
공식 코드Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
https://github.com/kevincl16/dsdbench
공식 코드https://github.com/keytoyze/jumpcoder
공식 코드JumpCoder: Go Beyond Autoregressive Coder via Online Modification
https://github.com/kit-hua/ETFA2019
공식 코드Interpreting OWL Complex Classes in AutomationML based on Bidirectional Translation
https://github.com/knowledge-verse-ai/texpert
공식 코드TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs
https://github.com/kraina-ai/geospatial-code-llms-dataset
공식 코드https://github.com/kyle-lyu/data-efficient-finetuning
공식 코드https://github.com/laiyao1/AnalogCoder
공식 코드AnalogCoder: Analog Circuit Design via Training-Free Code Generation
https://github.com/lapisrocks/languageagenttreesearch
공식 코드Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
https://github.com/large-scale-sustainable-computing-lsc/green-code
공식 코드GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.