fengji.zhang's starred repositories
Vocabulary-Transfer
Implementation of the paper "Fine-Tuning Transformers: Vocabulary Transfer" https://arxiv.org/pdf/2112.14569.pdf
nested-bigrams
A repository containing the source code, datasets, and ranked features for the Nested Bigrams method proposed in a paper published in ICDMW. This method is designed for authorship attribution in source code to address cybersecurity issues.
Graphormer
Graphormer is a general-purpose deep learning backbone for molecular modeling.
awesome-ai4code
A collection of recent papers, benchmarks and datasets of AI4Code domain.
code-stylometry-UF
Source code for the approach used in the paper Towards Improving Code Stylometry in Underground Forums. https://www.sciendo.com/article/10.2478/popets-2022-0007.
awesome-program
A curated list of papers related to program synthesis, program induction, program execution, program and code repair, and programmatic reinforcement learning.
Authorship-StyloMatrix
Learning Stylometric Representation for Authorship Analysis
style-pooling
Repo for the EMNLP 2021 paper "Style Pooling: An Empirical Study of Automatic Text Style Obfuscation"
code_stylometry
De-anonymizing Programmers via Code Stylometry
authorship_attribution
The dataset clawed from Github for authorship attribution of source code is provided for learning purposes. It contains 40 authors' repositories in the way of compressed packages.
source2vec
Source code embeddings for various programming languages
Video-Swin-Transformer
This is an official implementation for "Video Swin Transformers".
TimeSformer
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
awesome-code-formatters
A curated list of awesome code formatting tools and libraries
PatrickStar
PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.
pan_2020_2021_authorship_verification
Source code for the PAN 20/21 shared tasks