https://github.com/google-research/crossbeam
공식 코드CrossBeam: Learning to Search in Bottom-Up Program Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
CrossBeam: Learning to Search in Bottom-Up Program Synthesis
SpreadsheetCoder: Formula Prediction from Semi-structured Context
Learning Graph Structure With A Finite-State Automaton Layer
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Incremental Sampling Without Replacement for Sequence Models
TinyverseGP: Towards a Modular Cross-domain Benchmarking Framework for Genetic Programming
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code Stacks
NeuRI: Diversifying DNN Generation via Inductive Rule Inference
Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases
Large Language Models Synergize with Automated Machine Learning
Automating the Design of Multigrid Methods with Evolutionary Program Synthesis
Transformer-based Program Synthesis for Low-Data Environments
WatChat: Explaining perplexing programs by debugging mental models
PhaTYP: Predicting the lifestyle for bacteriophages using BERT
Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus
SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair
Less is More: Summary of Long Instructions is Better for Program Synthesis
A probabilistic and multi-objective analysis of lexicase selection and epsilon-lexicase selection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.