Official code for the paper Graph-level Representation Learning with Joint-Embedding Predictive Architectures published in Transactions on Machine Learning Research (TMLR)

[ICSE 2021] - InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees

A toolkit for conducting multiple static binary analysis based on Ghidra.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Statement-level deep learning model for automated software vulnerability detection in C/C++ (Accepted in MSR 2022)

Replication package for "Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection", ICSE 2024.

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

VulDeePecker: A Deep Learning-Based System for Vulnerability Detection

TensorFlow implementations of Graph Neural Networks

Sample Code for Gated Graph Neural Networks

Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks

A pytorch library for graph and hypergraph computation.

LLM101n: Let's build a Storyteller

Code for ICSE'24 Paper

Official Implementation of ICML 2023 paper: "A Generalization of ViT/MLP-Mixer to Graphs"

Code for the paper - Source Code Vulnerability Detection: Combining Code Language Models and Code Property Graph

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

aiDAPal is an IDA Pro plugin that uses a locally running LLM that has been fine-tuned for Hex-Rays pseudocode to assist with code analysis.

Implementation for MatMul-free LM.

An engine for displaying slips, the next-gen version of slides

Code for paper "PSCS: A Path-based Neural Model for SemanticCode Search"

NLQF is a tool to filter query-appropriate comments for building high-quality code search datasets.