Deep model improves software code understanding.
problem Software code's long context challenges existing models.
method Inspired by human memory, uses LSTM for long-term dependencies.
result Demonstrated effectiveness on Java project corpus.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,341 papers · 148 categories
Trend · papers per month
48 results for “software code”
Develops deep learning for logical code segmentation.
problem Lack of logically segmented source code.
method Novel deep learning approach to generate logical code segments.
result Improves software analysis tasks like commenting, bug detection, and code synthesis.
Deep learning detects software vulnerabilities from source code.
problem Automated detection of software vulnerabilities in source code.
method Deep feature representation learning on lexed source code.
result Deep learning can effectively detect software vulnerabilities.
DeepSoft aims to model software development for risk prediction and intervention.
problem Manual feature engineering and traditional classification problems in software analytics.
method End-to-end deep learning framework using Long Short Term Memory architecture.
result DeepSoft predicts future risks and recommends interventions in software development.
TreeCaps improves code comprehension for software developers.
problem Processing code efficiently for software developers.
method Tree-based capsule networks for capturing code syntactical structures and dependencies.
result TreeCaps outperforms other approaches in classifying program functionalities.
Convolutional neural network summarizes code comments across multiple languages.
problem Insufficient or missing comments in source code.
method Language-agnostic encoder-decoder model with open vocabulary.
result Comparable results to state-of-the-art on single-language data; first results on multi-language data.
Survey of software developers' experience with Github Copilot tool.
problem Investigate developers' acceptance of AI-generated code.
method Survey with 18 questions distributed to 42 programmers.
result Mixed developer opinions, mostly positive but reluctance to use.
Generative Adversarial Network repairs software bugs without labeled data.
problem Automated repair of software vulnerabilities.
method Adversarial learning approach mapping between source and target domains.
result Effective at repairing software vulnerabilities, close to seq2seq approaches.
This paper uses machine learning to assist automation engineers in decision making.
problem Imperfect decision making by automation engineers leads to multiple iterations and increased time for software development.
method Defined challenges and proposed solutions using machine learning for automation engineering, including code classification, finding similar code snippets, and hardware selection.
result Paragraph embedding techniques achieved an F1-score of 72% for classifying automation using code snippets, and autoencoder models for hardware recommendation achieved p@3 and p@5 of 0.79 and 0.95, respectively.
MISIM improves code similarity systems with neural learning.
problem Improving accuracy of code semantics similarity systems.
method Context-aware semantics structure and neural code similarity scoring algorithm.
result MISIM achieves 8.08% better accuracy than state-of-the-art systems.
Paper presents machine learning approach for detecting software vulnerabilities.
problem Detect subtle security vulnerabilities in production software.
method Data-driven approach using machine learning on C and C++ code.
result Highest performing model achieves AUC of 0.87 on ROC curve.
Multimodal deep learning improves flaw detection in software programs.
problem Current flaw detection relies on single software representations.
method Adapted multimodal deep learning models for flaw detection.
result Multimodal models outperform traditional deep learning models.
Models of complex systems are often formalized as sequential software simulators: computationally intensive programs that iteratively build up probable system configurations given parameters and initial conditions. These simulators enable modelers to capture effects that are difficult to characterize analytically or su…
funcGNN uses graph neural networks to estimate program similarity efficiently.
problem Estimating accurate program similarity for software engineering tasks.
method funcGNN trains on labeled CFG pairs to predict GED between unseen programs using effective embedding vectors.
result funcGNN achieves lower error rate (0.00194) and is 23 times faster than traditional methods.
Graph2Diff neural network predicts precise code changes for build errors.
problem Fixing build errors in software development.
method Represented code and errors as graphs, used Graph Neural Network to predict precise diffs.
result Graph2Diff achieves over double the accuracy of DeepDelta in predicting precise code changes.
SAPS synthesizes code from natural language specifications.
problem Efficiently translating complex NL specifications into executable code.
method Structure-aware neural network using abstract syntax trees and LSTM.
result SAPS produces correct programs in over 92% of cases.
Accelerator synthesizes deep learning inference from C code using FPGA hardware.
problem Efficiently implementing deep learning models on FPGAs.
method Parallelized C code using Pthreads, high-level synthesis, reduced precision, zero-weight-skipping.
result Peak performance of 138 effective GOPS on VGG-16 on Intel Arria 10 SoC FPGA.
New model creates code semantics vectors for better understanding.
problem Improving code understanding and embedding quality.
method Siamese recurrent neural network on Python source code.
result Model significantly outperforms bag-of-tokens embeddings.
Devign uses graph neural networks to identify vulnerabilities efficiently.
problem Challenging and tedious process of identifying vulnerabilities in software systems.
method Devign employs a graph neural network to classify graph-level vulnerabilities using comprehensive code semantic representations.
result Devign significantly outperforms state-of-the-art models in vulnerability identification.
Import2vec creates embeddings for software libraries to improve learning tasks.
problem Developing semantic representations for software libraries.
method Applied word embedding techniques from NLP to library packages.
result Library vectors capture meaningful relationships among libraries.
Neural network identifies undeclared variables and infers their types.
problem Undeclared variable errors in programs.
method Trained on structural semantic details of AST, identifies and infers types of undeclared variables.
result Correctly identified and inferred types for 80% of programs with undeclared variable errors.
Quantifying Process Quality: The Role of Effective Organizational Learning in Software Evolutioncs.SE
Improving software quality through effective organizational learning.
problem Lack of reliable quantification methods for software evolution.
method Leveraging application lifecycle management data to identify and address managerial practices.
result Effective learning from past processes improves software quality indirectly.
Paper develops multilingual job classification for ISCO and KZiS.
problem Classifying job advertisements for accurate occupation coding.
method Transformer architecture for hierarchical multi-class classification.
result Hierarchical structure improves prediction accuracy by 1-2 percentage points.
TomOpt: Differential optimisation for task- and constraint-aware design of particle detectors in the context of muon tomographyphysics.ins-det
TomOpt optimizes muon detector designs using differentiable programming.
problem Designing efficient particle detectors for muon tomography.
method Differentiable programming for muon interaction modeling, inference, and optimisation.
result Demonstrated end-to-end differentiable and inference-aware optimisation of particle physics instruments.
RNNs learn device models from input/output data.
problem Learning complex device models from limited data.
method Empirical study using RNNs to model six different devices.
result RNNs can generate functional software-only models of hardware devices.
CoNCRA uses CNN to find code snippets matching developer intent.
problem Finding relevant code snippets using general search engines.
method Convolutional Neural Network approach to code retrieval.
result Improved code retrieval by 5% on average, top 3 positions 80% of the time.
We model GitHub interactions as a temporal knowledge graph for software engineering questions.
problem Insufficient performance of existing temporal models on extrapolated queries and time prediction.
method Introduced an extension to current temporal models using relative temporal information.
result Improved performance on extrapolated queries and time prediction.
SySeVR uses deep learning to detect software vulnerabilities.
problem Detecting software vulnerabilities is challenging and important.
method SySeVR combines syntax and semantic information to represent programs for deep learning.
result SySeVR detects 15 unknown vulnerabilities, including 7 unknown and 8 silently patched ones.
Deep learning improves death cause coding accuracy.
problem Geospatial discrepancies in human-coded death certificates.
method Deep artificial neural network model trained on CépiDc database.
result 97.8% accuracy in automated coding compared to 75% for Iris software.
PyTorch Geometric Signed Directed fills the gap for GNNs on signed and directed graphs.
problem Lack of unified software packages for GNNs on signed and directed networks.
method Developed a software package with GNN models, synthetic and real-world data, and evaluation metrics.
result Demonstrates the effectiveness of the implemented methods through experiments.
Paper proposes graph-based separable transforms for video coding.
problem Improving video coding efficiency by better capturing residual block statistics.
method Derives graph-based separable transforms (GBSTs) from line graphs with weights determined by parameters.
result GBSTs achieve about 0.4% average coding gain over existing transforms in VVC.
Python tool assesses European agricultural production resilience.
problem Estimating resilience of European agricultural production systems.
method Python software to compute annual production resilience indicator.
result Demonstrates resilience of European agricultural production.
While developing their software, professional object-oriented (OO) software developers keep in their minds an image of the subtyping relation between types in their software. The goal of this paper is to present an observation about the graph of the subtyping relation in Java, namely the observation that, after the add…
EgoCoder synthesizes programs from text using neural networks.
problem Automatically generating programs to meet software developer demand.
method Hierarchical sequential neural network model to parse and synthesize programs.
result EgoCoder effectively captures hierarchical and sequential program patterns.
MLPerf benchmarks ML training to drive performance improvements.
problem Unique challenges in ML training benchmarks.
method Developed MLPerf to overcome ML training's specific challenges.
result Quantitatively evaluated MLPerf's effectiveness.
Neural networks model code edits from source code changes.
problem Modeling dynamic changes in source code.
method Developed neural networks to learn and predict code edits.
result Attentional and pointer network components provide best performance.
Graph-based ML improves defect prediction in software development.
problem Challenges in predicting defect-prone changes in complex software development.
method Building contribution graphs from developers and source files, using graph-based ML for defect prediction.
result Graph-based ML leads to significantly better defect prediction (F1 score up to 77.55%, MCC up to 53.16%).
Tangent automates derivatives in Python, improving expressiveness and performance.
problem Efficiently calculating derivatives for complex models in Python.
method Source-code transformation for dynamically typed array programming.
result Demonstrates improved expressiveness and performance in automatic differentiation.
Unsupervised method constructs knowledge graph from text and code.
problem Lack of structured knowledge in scientific literature and code.
method Word embedding, clustering, and dimensionality reduction techniques.
result Enhanced understanding of scientific literature and code.
The word2vec software of Tomas Mikolov and colleagues (https://code.google.com/p/word2vec/ ) has gained a lot of traction lately, and provides state-of-the-art word embeddings. The learning models behind the software are described in two research papers. We found the description of the models in these papers to be some…
New method provides fine-grained feedback on interactive student programs.
problem Time-consuming manual grading of interactive student programs.
method Meta-exploration approach using reinforcement learning.
result 94.3% accuracy in providing fine-grained feedback.
Reduces deep learning training data for faster testing.
problem Resource-intensive deep learning training with full data sets.
method Evaluated different training set reduction methods.
result Training set reduction is useful in resource-constrained environments.
GPflow uses TensorFlow for Gaussian process computations.
problem Efficient Gaussian process inference and prediction.
method Variational inference, automatic differentiation, GPU hardware exploitation.
result GPflow accelerates Gaussian process computations using TensorFlow and Python.
AutoGraph improves Python coding for machine learning, combining ease and performance.
problem The trade-off between ease of writing and scalability in machine learning code.
method Source code transformation using staged programming in Python, delaying type-dependent decisions until runtime.
result Usability improvements with no performance loss compared to native TensorFlow graphs.
SABCEMM simulates economic market models with millions of agents.
problem Efficiently simulating large-scale economic market models.
method Object-oriented C++ implementation, XML configuration, abstract model class.
result Different random number generators significantly impact ABCEM model run time.
Paper checks SSC for matrix factorizations using Gurobi.
problem Checking the SSC for various matrix factorizations.
method Formulated as a non-convex quadratic optimization problem over a bounded set, solved with Gurobi.
result SSC can be checked in reasonable time for realistic scenarios.
Inspired by the paper on quantum knots and knot mosaics [23] and grid diagrams (or arc presentations), used extensively in the computations of Heegaard-Floer knot homology [2,3,7,24], we construct the more concise representation of knot mosaics and grid diagrams via mirror-curves. Tame knot theory is equivalent to knot…
Paper introduces HISA for efficient FHE computations.
problem Efficiently evaluating encrypted neural networks.
method Developed HISA for FHE applications, including compiler and runtime.
result Generated code is faster than hand-optimized implementations.