Papers Program Synthesis
“Program Synthesis” 태그가 달린 논문 538편 · 필터 해제
Latent Programmer: Discrete Latent Codes for Program Synthesis
In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that a…
Document SummarizationProgram SynthesisSelf-Supervised LearningMulti-Plane Program Induction with 3D Box Priors
We consider two important aspects in understanding and editing images: modeling regular, program-like texture or patterns in 2D planes, and 3D posing of these planes in the scene. Unlike prior work on image-based program…
Program inductionProgram SynthesisGRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts
Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specific…
Program SynthesisLearning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from leveraging program structure like control…
Code CompletionLearning to ExecuteProgram RepairProgram Synthesis+1Dreaming with ARC
Current machine learning algorithms are highly specialized to whatever it is they are meant to do –– e.g. playing chess, picking up objects, or object recognition. How can we extend this to a system that could solve a w…
ARCObject RecognitionProgram SynthesisAutomated Generation of Executable Cross-Language Background Knowledge
Certain problems require specific semanticknowledge to be solved, e.g. the transformation “January→1”.Without the requireddomain specific knowledge, a program synthesizer can’t generalize toward…
Program SynthesisFusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
Parametric computer-aided design (CAD) is a standard paradigm used to design manufactured objects, where a 3D shape is represented as a program supported by the CAD software. Despite the pervasiveness of parametric CAD a…
CAD ReconstructionProgram SynthesisGoal-directed Generation of Discrete Structures with Conditional Generative Models
Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding exam…
Heuristic SearchProgram Synthesisreinforcement-learningReinforcement Learning+1Optimal Neural Program Synthesis from Multimodal Specifications
Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings; however, it requires integrating noisy…
Program SynthesisvalidAdversarial Synthetic Datasets for Neural Program Synthesis
Program synthesis is the task of automatically generating a program consistent with a given specification. A natural way to specify programs is to provide examples of desired input-output behavior, and many current progr…
Program SynthesisSQUARES: A SQL Synthesizer Using Query Reverse Engineering
Nowadays, many data analysts are domain experts, but they lack programming skills. As a result, many of them can provide examples of data transformations but are unable to produce the desired query. Hence, there is an in…
Enumerative SearchProgram SynthesisSQL SynthesisType-driven Neural Programming by Example
In this thesis we look into programming by example (PBE), which is about finding a program mapping given inputs to given outputs. PBE has traditionally seen a split between formal versus neural approaches, where formal a…
Program SynthesisVocal Bursts Type PredictionProcess Discovery for Structured Program Synthesis
A core task in process mining is process discovery which aims to learn an accurate process model from event log data. In this paper, we propose to use (block-) structured programs directly as target process models so as …
Program SynthesisRobot Action Selection Learning via Layered Dimension Informed Program Synthesis
Action selection policies (ASPs), used to compose low-level robot skills into complex high-level tasks are commonly represented as neural networks (NNs) in the state of the art. Such a paradigm, while very effective, suf…
Autonomous DrivingProgram RepairProgram SynthesisCode Building Genetic Programming
In recent years the field of genetic programming has made significant advances towards automatic programming. Research and development of contemporary program synthesis methods, such as PushGP and Grammar Guided Genetic …
Program SynthesisBUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration
Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs by writing sub-programs and then analyzin…
Program SynthesisSemi-supervised Learning From Demonstration Through Program Synthesis: An Inspection Robot Case Study
Semi-supervised learning improves the performance of supervised machine learning by leveraging methods from unsupervised learning to extract information not explicitly available in the labels. Through the design of a sys…
ClusteringcounterfactualDecision MakingModel Predictive Control+1SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
Parametric computer-aided design (CAD) is the dominant paradigm in mechanical engineering for physical design. Distinguished by relational geometry, parametric CAD models begin as two-dimensional sketches consisting of g…
Program SynthesisSynthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis
The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it still remains a challenge to synthesize …
Program SynthesisProgramming by Rewards
We formalize and study ``programming by rewards'' (PBR), a new approach for specifying and synthesizing subroutines for optimizing some quantitative metric such as performance, resource utilization, or correctness over a…
Program Synthesis