A library for mechanistic interpretability of GPT-style language models

Code and data for "AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks" (TMLR 2024)

A PyTorch-based Speech Toolkit

DeepTTC: a transformer-based model for predicting cancer drug response

TUGDA is a novel multi-task unsupervised domain adaptation method that leverages transfer learning from tasks/domains in a unified framework.

Code and Data for M3A: Multimodal Multi-speaker Mergers & Acquisitions at ACL-IJCNLP 2021 (main)

Tamr Toolbox

Contrastive Predictive Coding for Automatic Speaker Verification

R wrapper for U.S. Department of Education College Scorecard Data API

Kaggle - Freesound General-Purpose Audio Tagging Challenge - Solution code

Detect whether a social media comment is insulting or derogatory

The OpenAPI Specification Repository

Mixed-effects models in R using S4 classes and methods with RcppEigen

R lfactors package

Stability Selection with Error Control

Scrapes Google Trends data over long timescales and stitches together for daily data

Fast n-dimensional filtering and grouping of records.