Research Tools: code, datasets, & models

In the Harnessing AutoMobiles for Safety, or HAMS, project, we use low-cost sensing devices to construct a virtual harness for vehicles. The goal is to monitor the state of the driver and how the vehicle…

Code and Data artifact for NeurIPS 2023 paper – “Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context”. `multispy` is a lsp client library in Python intended to be used to build applications…

Official PyTorch implementation for the paper: “Renee: End-to-end training of extreme classification models” accepted at MLSys 2023.

INTREPID (stands for INTeractive learning via REPresentatIon Discovery) is a library that contains various interactive learning algorithms that learn a representation (or a latent state) from observational data in order to complete their tasks.

Chart Reader is a web-based accessibility engine, which enables rendering of accessible visualizations for screen reader uses to read and better understand the visualizations and underlying data.

This repository contains the official code for our IEEE S&P 2023 paper using GPT-2 language models and Flair Named Entity Recognition (NER) models. It allows fine-tuning (i) undefended, (ii) differentially-private and (iii) scrubbed language models…

Syntheseus is a package for retrosynthetic planning. It contains implementations of common search algorithms and a simple API to wrap custom reaction models and write custom algorithms. It is meant to allow for simple benchmarking…

Guidance enables you to control modern language models more effectively and efficiently than traditional prompting or chaining. Guidance programs allow you to interleave generation, prompting, and logical control into a single continuous flow matching how…

BioViL-T is a Vision-Language model trained on sequences of biomedical image and text data at a scale. It does not require manual annotations and can leverage historical raw clinical image acquisitions and clinical notes. The…

A simple racer research platform that showcases various imitation learning models with a web racing game.