Search Results for author:
Found 35 papers, 10 papers with code
Is Next Token Prediction Sufficient for GPT? Exploration on Code Logic Comprehension
Our experimental results reveal that following this pretraining, both Code Llama and StarCoder, the prevalent code domain pretraining models, display significant improvements on our logically equivalent code selection task and the code completion task.
AutoDev: Automated AI-Driven Development
This enables the AI Agents to execute tasks in a fully automated manner with a comprehensive understanding of the contextual information required.
Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming
The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development.
Rethinking the Instruction Quality: LIFT is What You Need
Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data.
SUT: Active Defects Probing for Transcompiler Models
In this paper we introduce a new metrics for programming language translation and these metrics address these basic syntax errors.
Program Translation via Code Distillation
Distilled code serves as a translation pivot for any programming language, leading by construction to parallel corpora which scale to all available source code by simply applying the distillation compiler.
Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation
Software testing is a crucial aspect of software development, and the creation of high-quality tests that adhere to best practices is essential for effective maintenance.
Predicting Code Coverage without Execution
Using Machine Learning to amortize this expensive process could lower the cost of code coverage by requiring only the source code context, and the task of code coverage prediction can be a novel benchmark for judging the ability of models to understand code.
RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot
We compare our approach with the various prompt variations and state of the art methods in the task of performance bug fixing.
Transformer-based Vulnerability Detection in Code at EditTime: Zero-shot, Few-shot, or Fine-tuning?
We recognize that the current advances in machine learning can be used to detect vulnerable code patterns on syntactically incomplete code snippets as the developer is writing the code at EditTime.
Code Execution with Pre-trained Language Models
Code execution is a fundamental aspect of programming language semantics that reflects the exact behavior of the code.
Exploring and Evaluating Personalized Models for Code Generation
Large Transformer models achieved the state-of-the-art status for Natural Language Understanding tasks and are increasingly becoming the baseline model architecture for modeling source code.
DeepPERF: A Deep Learning-Based Approach For Improving Software Performance
Additionally, we evaluate DeepPERF on 50 open source C# repositories on GitHub using both benchmark and unit tests and find that our model is able to suggest valid performance improvements that can improve both CPU usage and Memory allocations.
AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations
This scenario motivates the code adaptation task -- a variant of program repair which aims to adapt variable identifiers in a pasted snippet of code to the surrounding, preexisting source code.
Generating Examples From CLI Usage: Can Transformers Help?
Continuous evolution in modern software often causes documentation, tutorials, and examples to be out of sync with changing interfaces and frameworks.
Automating Code Review Activities by Large-Scale Pre-training
In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario.
Learning to Reduce False Positives in Analytic Bug Detectors
Due to increasingly complex software design and rapid iterative development, code defects and security vulnerabilities are prevalent in modern software.
Training and Evaluating a Jupyter Notebook Data Science Assistant
We study the feasibility of a Data Science assistant powered by a sequence-to-sequence transformer by training a new model JuPyT5 on all publicly available Jupyter Notebook GitHub repositories and developing a new metric: Data Science Problems (DSP).
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window.
Program Merge Conflict Resolution via Neural Transformers
Our model achieves 63-68% accuracy for merge resolution synthesis, yielding nearly a 3x performance improvement over existing semi-structured, and 2x improvement over neural program merge tools.
Distilling Transformers for Neural Cross-Domain Search
Pre-trained transformers have recently clinched top spots in the gamut of natural language tasks and pioneered solutions to software engineering tasks.
DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons
The joint task of bug localization and program repair is an integral part of the software development process.
Generating Bug-Fixes Using Pretrained Transformers
In this work we introduce DeepDebug: a data-driven program repair approach which learns to detect and fix bugs in Java methods mined from real-world GitHub repositories.
Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers
To demonstrate the effectiveness of our model designs, we perform extensive experiments with CodeSearchNet which contains template functions and CoNaLa which contains Stack Overflow intent-snippet pairs.
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Benchmark datasets have a significant impact on accelerating research in programming language tasks.
Ranked #1 on
Cloze Test
on CodeXGLUE - CT-maxmin
PyMT5: multi-mode translation of natural language and Python code with transformers
Simultaneously modeling source code and natural language has many exciting applications in automated software development and understanding.
CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models.
GraphCodeBERT: Pre-training Code Representations with Data Flow
Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables.
Ranked #3 on
Type prediction
on ManyTypes4TypeScript
Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformers
In this paper we present an approach to support developers in writing unit test cases by generating accurate and useful assert statements.
Unit Test Case Generation with Transformers and Focal Context
We execute the test cases, collect test coverage information, and compare them with test cases generated by EvoSuite and GPT-3, finding that our approach outperforms GPT-3 and has comparable coverage w. r. t.
IntelliCode Compose: Code Generation Using Transformer
In software development through integrated development environments (IDEs), code completion is one of the most widely used features.
Pythia: AI-assisted Code Completion System
In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia.
Fast Approximate Matching of Cell-Phone Videos for Robust Background Subtraction
We identify a novel instance of the background subtraction problem that focuses on extracting near-field foreground objects captured using handheld cameras.
Large Scale Visual Recommendations From Street Fashion Images
We describe a completely automated large scale visual recommendation system for fashion.
Large-Scale Video Summarization Using Web-Image Priors
Given the enormous growth in user-generated videos, it is becoming increasingly important to be able to navigate them efficiently.
