Program Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 3
- 보존된 평가 기록
- 5
Program synthesis is the process of automatically generating a program or code snippet that satisfies a given specification or set of requirements. This can include generating code from a formal specification, a natural language description, or example inputs and outputs. The primary goal of program synthesis is to minimize human intervention in the coding process, reduce errors, and improve productivity.
Program synthesis often involves the use of advanced algorithms, artificial intelligence, and machine learning techniques to search the space of possible programs that meet the given constraints. This process can be guided by a variety of techniques, such as constraint solving, symbolic execution, and genetic algorithms.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ARiSE-Lab/Patch-as-translation
공식 코드https://github.com/ASSERT-KTH/elle-elle-aime
공식 코드RepairBench: Leaderboard of Frontier Models for Program Repair
https://github.com/ASSERT-KTH/repairbench
공식 코드RepairBench: Leaderboard of Frontier Models for Program Repair
https://github.com/AutodeskAILab/Fusion360GalleryDataset
공식 코드https://github.com/BeautyOfWeb/AffinityNet
공식 코드AffinityNet: semi-supervised few-shot learning for disease type prediction
https://github.com/CatherineWong/dreamcoder
공식 코드DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
https://github.com/ChristopherRosin/MAKESPEARE
공식 코드Stepping Stones to Inductive Synthesis of Low-Level Looping Programs
https://github.com/Hwhitetooth/random_gvfs
공식 코드Learning State Representations from Random Deep Action-conditional Predictions
https://github.com/IPRC-DIP/ANPL
공식 코드ANPL: Towards Natural Programming with Interactive Decomposition
https://github.com/JackHopkins/factorio-learning-environment
공식 코드https://github.com/JohnnyYeeee/math_prog_synth_env
공식 코드A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis
https://github.com/LChenGit/OMP_serial_dataset
공식 코드Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation
https://github.com/NecoraNyaru/PInG
공식 코드Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
https://github.com/OpenAutoCoder/Agentless
공식 코드Agentless: Demystifying LLM-based Software Engineering Agents
https://github.com/PierreBlanchart/CMBDTC
공식 코드An exact counterfactual-example-based approach to tree-ensemble models interpretability
https://github.com/PrincetonLIPS/SketchGraphs
공식 코드SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
https://github.com/Qualcomm-AI-research/codeit
공식 코드CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
https://github.com/RGAI-USZ/JS-patch-exploration-APR2021
공식 코드Exploring Plausible Patches Using Source Code Embeddings in JavaScript
https://github.com/RichardEvans/apperception
공식 코드https://github.com/RiyasaatAhmed/Text2Chart-A-Multi-Staged-Chart-Generator-from-Natural-Language-Text
공식 코드Text2Chart: A Multi-Staged Chart Generator from Natural Language Text
https://github.com/SEED-VT/FedDebug
공식 코드FedDebug: Systematic Debugging for Federated Learning Applications
https://github.com/ShangtongZhang/DeepRL
공식 코드ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
https://github.com/ShishirPatil/gorilla
공식 코드https://github.com/SkBlaz/tax2vec
공식 코드tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
https://github.com/Theomat/ProgSynth
공식 코드https://github.com/UppsalaIM/rice
공식 코드"Why did you do that?": Explaining black box models with Inductive Synthesis
https://github.com/YerbaPage/MGDebugger
공식 코드From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
https://github.com/agemagician/CodeTrans
공식 코드https://github.com/alan-turing-institute/SemAIDA
공식 코드ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
https://github.com/alcides/geneticengine
공식 코드Data types as a more ergonomic frontend for Grammar-Guided Genetic Programming
https://github.com/alejgh/wikidata-edithist-refinement
공식 코드Leveraging Wikidata's edit history in knowledge graph refinement tasks
https://github.com/ali-ghanbari/deepmufl-ase-2023
공식 코드https://github.com/amazon-science/incremental-parsing
공식 코드https://github.com/amitz25/PCCoder
공식 코드Automatic Program Synthesis of Long Programs with a Learned Garbage Collector
https://github.com/amlalejini/Tag-based-Genetic-Regulation-for-LinearGP
공식 코드Tag-based regulation of modules in genetic programming improves context-dependent problem solving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.