Papers - Mark Goldstein

Flow Map Learning Via Non-Gradient Vector Flow

Mark Goldstein, Anshuk Uppal, Raghav Singhal, Aahlad Manas Puli, Rajesh Ranganath

ICLR 2026

[arXiv]

Time After Time: Scalable Effect Estimation for Interventions on When and What to Do

Yoav Wald, Mark Goldstein, Yonathan Efroni, Wouter A.C. van Amsterdam, Rajesh Ranganath

ICLR 2025

[arXiv]

Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities

Adriel Saporta, Aahlad Puli, Mark Goldstein, Rajesh Ranganath

NeurIPS 2024

[arXiv]

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

Nanye Ma, Mark Goldstein, Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden, Saining Xie

ECCV 2024

Transformer-based architecture for generative modeling using stochastic interpolants, surpassing DiT on ImageNet benchmarks.

[arXiv] [Code]

What's the Score? Automated Denoising Score Matching for Nonlinear Diffusions

Raghav Singhal, Mark Goldstein, Rajesh Ranganath

ICML 2024

[arXiv]

Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes

Yifan Chen, Mark Goldstein, Mengjian Hua, Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden

ICML 2024

Generative modeling framework for probabilistic forecasting of dynamical systems using stochastic interpolants and Föllmer processes.

[arXiv]

Stochastic Interpolants with Data-Dependent Couplings

Michael S. Albergo, Mark Goldstein, Nicholas M. Boffi, Rajesh Ranganath, Eric Vanden-Eijnden

ICML 2024 (Spotlight)

Extends stochastic interpolants to conditional generative modeling through learned data-dependent couplings.

[arXiv]

A Dynamic Risk Score for Early Prediction of Cardiogenic Shock Using Machine Learning

Yuxuan Hu, Mark Goldstein, Rajesh Ranganath et al.

European Heart Journal: Acute Cardiovascular Care, 2024

[arXiv] [Journal]

QTNet: Predicting Drug-Induced QT Prolongation with AI-Enabled Electrocardiograms

Hao Zhang, Constantine Tarabanis, Neil Jethani, Mark Goldstein, Silas Smith, Larry A. Chinitz, Rajesh Ranganath, Yindalon Aphinyanaphongs, Lior Jankelson

JACC: Clinical Electrophysiology, 2024

[SSRN]

Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions

Mark Goldstein, Raghav Singhal, Rajesh Ranganath

ICLR 2023

[arXiv]

Survival Mixture Density Networks

Xintian Han, Mark Goldstein, Rajesh Ranganath

MLHC 2022 (PMLR)

[arXiv]

Learning Invariant Representations with Missing Data

Mark Goldstein, Jörn-Henrik Jacobsen, Olina Chau, Adriel Saporta, Aahlad Puli, Rajesh Ranganath, Andrew C. Miller

CLeaR 2022

[arXiv]

Inverse-Weighted Survival Games

Mark Goldstein, Xintian Han, Aahlad Puli, Thomas Wies, Adler J. Perotte, Rajesh Ranganath

NeurIPS 2021

A new way to estimate survival models by playing games involving both the failure and censoring distribution.

[arXiv]

Understanding Failures in Out-of-Distribution Detection with Deep Generative Models

Lily H. Zhang, Mark Goldstein, Rajesh Ranganath

ICML 2021

[arXiv]

X-CAL: Explicit Calibration for Survival Analysis

Mark Goldstein, Xintian Han, Aahlad Puli, Adler J. Perotte, Rajesh Ranganath

NeurIPS 2020

[arXiv]