Beyond Scores: Proximal Diffusion Models

Zhenghan Fang, Mateo Diaz, Sam Buchanan, Jeremias Sulam

arXiv 2025

Diffusion ModelsGenerative AITheory

[Paper]

Multiaccuracy and Multicalibration via Proxy Groups

Beepul Bharti, Mary Versa Clemens-Sewall, Paul H. Yi, Jeremias Sulam

International Conference of Machine Learning 2025

ML TrustworthinessTheory

[Paper]

Disentangling Safe and Unsafe Image Corruptions via Anisotropy and Locality

Ramchandran Muthukumar, Ambar Pal, Jeremias Sulam, Rene Vidal

Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) 2025

ML Robustness

[Paper]

Pitfalls and Best Practices in Evaluation of AI Algorithmic Biases in Radiology

Paul H. Yi,, Preetham Bachina, Beepul Bharti, Sean P. Garin, Adway Kanhere, Pranav Kulkarni, David Li, Vishwa S. Parekh, Samantha M. Santomartino, Linda Moy, Jeremias Sulam

Radiology (RSNA) 2025

Medical Imaging

[Paper]

Aligning Explanations with Human Communication

Jacopo Teneggi, Zhenzhen Wang, Paul H Yi, Tianmin Shu, Jeremias Sulam

arXiv 2025

ML Interpretability

[Paper]

Bi-level Graph Learning Unveils Prognosis-Relevant Tumor Microenvironment Patterns from Breast Multiplexed Digital Pathology

Zhenzhen Wang, Cesar A. Santa-Maria, Aleksander S. Popel, Jeremias Sulam

Patterns: Cell Press 2025 Cover feature

ML InterpretabilityBiomarker DiscoveryDigital Pathology

[Code] [Paper] [Press]

Concept bottleneck model with zero performance loss

Zhenzhen Wang, Aleksander Popel, Jeremias Sulam

Second Conferenceon Parsimony and Learning (CPAL 2025). 2025

ML Interpretability

[Paper]

Testing Semantic Importance via Betting

Jacopo Teneggi, Jeremias Sulam

NeurIPS 2024

ML InterpretabilityTheory

[Paper] [Code] [Demo]

Gradient-Based Saliency Maps Are Not Trustworthy Visual Explanations of Automated AI Musculoskeletal Diagnoses

Kesavan Venkatesh, Simukayi Mutasa, Fletcher Moore, Jeremias Sulam, Paul H Yi

Journal of Imaging Informatics in Medicine 2024

ML InterpretabilityBiomedical Imaging

[Paper]

Certified Robustness against Sparse Adversarial Perturbations via Data Localization

Ambar Pal, Rene Vidal, Jeremias Sulam

Transactions on Machine Learning Research (TMLR) 2024

[Paper]

Pivotal auto-encoder via self-normalizing relu

Nelson Goldenstein, Jeremias Sulam, Yaniv Romano

IEEE Transactions on Signal Processing 2024

Sparse CodingTheory

[Paper]

Estimating and Controlling for Fairness via Sensitive Attribute Predictors

Beepul Bharti, Paul H. Yi, Jeremias Sulam

NeurIPS 2023

[Paper]

How To Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control

Jacopo Teneggi, Matthew Tivnan, Webster J. Stayman, Jeremias Sulam

International Conference on Machine Learning (ICML) 2023

[Paper] [Code]

Fast Hierarchical Games for Image Explanations

Jacopo Teneggi, Alexandre Luster, Jeremias Sulam

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023

[Paper]

WaveSep: A Flexible Wavelet-Based Approach for Source Separation in Susceptibility Imaging

Zhenghan Fang, Hyeong-Geol Shin, Peter van Zijl, Xu Li, Jeremias Sulam

MLCN (MICCAI Workshop) 2023

[Paper]

Understanding Noise-Augmented Training for Randomized Smoothing

Ambar Pal, Jeremias Sulam

Transactions of Machine Learning Research (TMLR) 2023

[Paper]

Sparsity-aware generalization theory for deep neural networks

Ramchandran Muthukumar, Jeremias Sulam

COLT 2023

[Paper]

SHAP-XRT: The Shapley Value Meets Conditional Independence Testing

Jacopo Teneggi, Beepul Bharti, Yaniv Romano, Jeremias Sulam

Transactions of Machine Learning Research (TMLR) 2023

[Paper]

Medical imaging data science competitions should report dataset demographics and evaluate for bias

Sean P. Garin, Vishwa S. Parekh, Jeremias Sulam, Paul H. Yi

Nature Medicine 2023

[Paper]

Examination-level supervision for deep learning–based intracranial hemorrhage detection at head CT

Jacopo Teneggi, Paul H. Yi, Jeremias Sulam

Radiology: Artificial Intelligence 2023 Cover feature

[Paper] [Press]

DeepSTI: Towards Tensor Reconstruction using Fewer Orientations in Susceptibility Tensor Imaging

Zhenghan Fang, Kuo-Wei Lai, Peter van Zijl, Xu Li, Jeremias Sulam

Medical Image Analysis 2023

[Paper] [Code]

Cross-modality supervised image restoration enables nanoscale tracking of synaptic plasticity in living mice

Yu Kang T. Xu, Austin R. Graves, Gabrielle I. Coste, Richard L. Huganir, Dwight E. Bergles, Adam S. Charles, Jeremias Sulam

Nature Methods 2023

[Paper] [Code]

Adversarial robustness of sparse local Lipschitz predictors

Ramchandran Muthukumar, Jeremias Sulam

SIAM Journal on Mathematics of Data Science 2023

[Paper]

Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images

Zhenzhen Wang, Carla Saoud, Sintawat Wangsiricharoen, Aaron W. James, Aleksander S. Popel, Jeremias Sulam

IEEE Transactions on Medical Imaging 2022

Digital Pathology

[Paper]

Recovery and Generalization in Over-Realized Dictionary Learning

Jeremias Sulam, Chong You, Zhihui Zhu

Journal of Machine Learning Research (JMLR) 2022

[Paper]

Antibody structure prediction using interpretable deep learning

Jeffrey A. Ruffolo, Jeremias Sulam, Jeffrey J. Gray

Patterns 2022

[Paper]

Deciphering antibody affinity maturation with language models and weakly supervised learning

Jeffrey A. Ruffolo, Jeffrey J. Gray, Jeremias Sulam

Machine Learning for Structural Biology Workshop, NeurIPS 2021

[Paper]

A Geometric Analysis of Neural Collapse with Unconstrained Features

Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu

NeurIPS (Spotlight) 2021

[Paper]

Learning to solve TV regularized problems with unrolled algorithms

Hamza Cherkaoui, Jeremias Sulam, Thomas Moreau

NeurIPS 2020

Inverse ProblemsTheory

[Paper]

Conformal Symplectic and Relativistic Optimization

Gui França, Jeremias Sulam, Daniel P. Robinson, Rene Vidal

NeurIPS 2020

Theory

[Paper]

Adversarial Robustness of Supervised Sparse Coding

Jeremias Sulam, Ramchandran Muthukumar, Raman Arora

NeurIPS 2020

ML RobustnessTheory

[Paper]

Variations on the Convolutional Sparse Coding Model

Ives Rey-Otero, Jeremias Sulam, Michael Elad

IEEE Transactions on Signal Processing 2020

Sparse Coding

[Paper]

On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks

Jeremias Sulam, Aviad Aberdam, Amir Beck, Michael Elad

IEEE Transactions on Pattern Analysis and Machine Intelligence 2019

Sparse CodingTheory

[Paper]

Multi Layer Sparse Coding: the Holistic Way

Aviad Aberdam, Jeremias Sulam, Michael Elad

SIAM Journal on Mathematics of Data Science 2019

Sparse CodingTheory

[Paper]

Improving Pursuit Algorithms Using Stochastic Resonance

Dror Simon, Jeremias Sulam, Yaniv Romano, Yue Lue, Michael Elad

IEEE Transactions on Signal Processing 2019

Sparse CodingInverse Problems

[Paper]

Adversarial Noise Attacks of Deep Learning Architectures – Stability Analysis via Sparse Modeled Signals

Yaniv Romano, Aviad Aberdam, Jeremias Sulam, Michael Elad

Journal of Mathematical Imaging and Vision 2019

Sparse CodingML Robustness

[Paper]

From Local to Global Sparse Modeling

Jeremias Sulam

PhD Thesis, Technion - Israel Institute of Technology 2018

[Thesis]

Theoretical Foundations of Deep Learning via Sparse Representations

Vardan Papyan, Yaniv Romano, Jeremias Sulam, Michael Elad

IEEE Signal Processing Magazine 2018

TheorySparse Coding

[Paper]

Projecting onto the Multi-Layer Convolutional Sparse Coding Model

Jeremias Sulam, Vardan Papyan, Yaniv Romano, Michael Elad

International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2018

Sparse CodingTheory

[Paper]

Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding

Vardan Papyan, Jeremias Sulam, Michael Elad

IEEE Transactions on Signal Processing 2017

TheorySparse Coding

[Paper]

Maximizing AUC with Deep Learning for Classification of Imbalanced Mammogram Datasets

Jeremias Sulam, Rami Ben-Ari, Pavel Kisilev

Eurographics Workshop on Visual Computing for Biology and Medicine 2017

Medical Imaging

[Paper]

Dynamical system classification with diffusion embedding for ECG-based person identification

Jeremias Sulam, Yaniv Romano, Ronen Talmon

Signal Processing 2017

Signal ProcessingEKG

[Paper]

Trainlets: Dictionary Learning in High Dimensions

Jeremias Sulam, Boaz Ophir, Michael Zibulevsky, Michael Elad

IEEE Transactions on Signal Processing 2016

Sparse CodingInverse Problems

[Paper]

Large Inpainting of Face Images with Trainlets

Jeremias Sulam, Michael Elad

IEEE Signal Processing Letters 2016

Inverse ProblemsSparse Coding

[Paper]

Fusion of Ultrasound Harmonic Imaging with Clutter Removal Using Sparse Signal Separation

J. Turek, J. Sulam, I. Yavne, M. Elad

ICASSP 2015