Tomomi Ozawa's starred repositories
AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Exploiting-Cultural-Biases-via-Homoglyphs
[Journal of Artificial Intelligence Research] Source code for our paper "Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis".
time-series-papers
An up-to-date list of time-series related papers in AI venues.
TradeMaster
TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning :fire: :zap: :rainbow:
spinningup
An educational resource to help anyone learn deep reinforcement learning.
lattice-estimator
An attempt at a new LWE estimator
do-not-answer
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
wefe
WEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
responsible-ai-toolbox-mitigations
Python library for implementing Responsible AI mitigations.
DS-Career-Resources
Compilation of resources for aspiring data scientists
PurpleLlama
Set of tools to assess and improve LLM security.
guardrails
Adding guardrails to large language models.
ai-deadlines
:alarm_clock: AI conference deadline countdowns
smartnoise-sdk
Tools and service for differentially private processing of tabular and relational data
MirrorDataGenerator
MirrorDataGenerator is a python tool that generates synthetic data based on user-specified causal relations among features in the data. It focuses on how features relate with demographic attributes (e.g. gender, race, disability status, etc), which are considered as sensitive information for certain domains (e.g. employment, housing, etc).