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.

168,786 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “code2vec”

Towards Demystifying Dimensions of Source Code Embeddingscs.LG

Paper explores understanding of neural source code embeddings.

problem Lack of understanding of contents and characteristics of code2vec embeddings.

method Small case study using code2vec embeddings to create binary SVM classifiers and compare performance with handcrafted features.

result Code2vec embeddings perform similarly to handcrafted features and have more evenly distributed information gains.

source code embeddings neural networks machine learning binary SVM information gains

2020-08-29abs ↗pdf ↗

Embedding Java Classes with code2vec: Improvements from Variable Obfuscationcs.LG

Improves code2vec for Java classes by obfuscating variable names.

problem Code2vec's reliance on variable names makes it vulnerable to typos and attacks.

method Obfuscate variable names during code2vec training and aggregate method embeddings for class-level predictions.

result Obfuscated variable names improve model's robustness and accuracy.

code2vec variable obfuscation Java classes source code analysis machine learning

2020-04-06abs ↗pdf ↗

code2vec: Learning Distributed Representations of Codecs.LG

We present a neural model for representing snippets of code as continuous distributed vectors ("code embeddings"). The main idea is to represent a code snippet as a single fixed-length $\textit{code vector}$ , which can be used to predict semantic properties of the snippet. This is performed by decomposing code to a col…

2018-03-26abs ↗pdf ↗