The official repository for the paper entitled "Time Travel in LLMs: Tracing Data Contamination in Large Language Models."
-
Updated
Jun 11, 2024 - Python
The official repository for the paper entitled "Time Travel in LLMs: Tracing Data Contamination in Large Language Models."
The official repository for the paper entitled "Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models."
Source code for our paper "Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models".
My Graduation Project for Faculty of Computers and Information, Helwan Univeristy, Computer Science Department
Repository containing code and dataset of the paper "Do LLM Dream Of Ontologies?"
PyTorch code for FLD (Feature Likelihood Divergence), FID, KID, Precision, Recall, etc. using DINOv2, InceptionV3, CLIP, etc.
You will develop your algorithmic thinking skills and acquire skills in working with the main classes of algorithms used in practice: recursion and backtracking, recursion using variables, searching and sorting, as well as graph theory - implementation in computer memory, minimum spanning tree , traversal and finding the shortest path.
Official Pytorch repo of CVPR'23 and NeurIPS'23 papers on understanding replication in diffusion models.
On Memorization in Diffusion Models
In addition to helping you memorise, this code helps you do other things that I don't remember...
A game wherein the players memorize the digits shown for 5 seconds and then are given 60 seconds to memorize the numbers and their exact positions as they were visible and enter their guesses. The correct analysis of the answers whether correctly answered or wrongly answered is then shown.
Memory experiments with LLMs
Console application that aids memorization of text.
A simple script that batch defines words. Optimized for quizlet.
The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)
A re-implementation of the "Extracting Training Data from Large Language Models" paper by Carlini et al., 2020
Python 3 application. The app is designed to help you learn foreign words, terms or another data by flash card method
Code for "On Memorization in Probabilistic Deep Generative Models"
Foreign language vocabulary building program and general flashcard application.
Code for Memorization and Generalization in deep CNNs using soft gating mechanisms.
Add a description, image, and links to the memorization topic page so that developers can more easily learn about it.
To associate your repository with the memorization topic, visit your repo's landing page and select "manage topics."