Neil Jethani

@neiljethani

MD/PhD student @ School of Medicine/Courant Institute of Mathematical Science, NYU

New York, New York

neiljethani.github.io

Joined March 2021

Following

Followers

Replies Reposts Media

Pinned
Neil Jethani
@neiljethani
Mar 23, 2022
Many people in XAI prefer SHAP, but SHAP can be very slow in practice. Our new ICLR 2022 paper addresses this problem by introducing FastSHAP, a new method to estimate Shapley values in a single forward pass using a learned explainer model openreview.net/forum?id=Zq2G_… 🧵⬇️
2
Neil Jethani
@neiljethani
Mar 23, 2023
A really neat paper by @_rk_singhal and @marikgoldstein that automates the selection of the diffusion processes used by diffusion-based generative models
Raghav Singhal
@_rk_singhal
Mar 23, 2023
1/ We are excited to share new work on diffusion-based generative models (DBGMs)! This work introduces a large class of noising processes (diffusions) that are easy to use and shows the benefits of building DBGMs with them. Joint work with @marikgoldstein Rajesh Ranganath.
Neil Jethani
@neiljethani
Jul 19, 2021
Exciting new work published by our lab characterizing issues with using deep generative models for out-of-distribution detection!
Lily Zhang ✈️ICML
@lilyhzhang
Jul 16, 2021
Excited to share our ICML paper "Understanding Failures in Out-of-distribution Detection with Deep Generative Models" (with @marikgoldstein and Rajesh Ranganath), now on arxiv! arxiv.org/abs/2107.06908 1/9
Neil Jethani
@neiljethani
Jul 16, 2021
My first paper (arxiv.org/abs/2103.01890, blog post:tinyurl.com/dj2zjm7r) is out! TL;DR: We introduce REAL-X, a method for making real-time selections of important features in an instance of data (without encoding the prediction). Check out how we explain chest x-rays! (1/6)
2