Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.

SALMONN: Speech Audio Language Music Open Neural Network

PandaGPT: One Model To Instruction-Follow Them All

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

LLaSM: Large Language and Speech Model

Grounded Language-Image Pre-training

Training LLMs with QLoRA + FSDP

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

Code for our Natural Language Understand (NLU) project may 2022: Applying Self Debiasing Techniques to Toxic Language Detection Models

A benchmark of the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks

Full label data dump of etherscan in JSON/CSV.

Evaluating the robustness of text-conditioned OD models such as MDETR

DS-GA 1013 Mathematical Tools for Data Science

Code for a project forecasting wildfire risk in California using GIS data

This holds iPython notebooks and lecture slides for the Intro to Data Science Master's course I teach at NYU.