63 citations · 150 across the 32 of their papers we have counts for
37 papers
Instance-Specific Classifier-Free Guidance for Text-to-Image Diffusion/Flow-Based Editing
Wajeeh Atrash, Tom Tirer
In recent years, a variety of prompt-based image editing methods have been developed based on text-to-image (T2I) diffusion/flow models. Image editing introduces an inherent trade-…
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
Benjamin Sterling, Mónica F. Bugallo, Tom Tirer
Diffusion/score-based models have emerged as powerful generative models, capable of generating high-quality samples that mimic the training data distribution. However, it has been…
Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks
Roy Turgeman, Tom Tirer
The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations. In particu…
Enhancing Conformal Prediction via Class Similarity
Ariel Fargion, Lahav Dabah, Tom Tirer
Conformal Prediction (CP) has emerged as a powerful statistical framework for high-stakes classification applications. Instead of predicting a single class, CP generates a predicti…
Jacobian-Aware Posterior Sampling for Inverse Problems
Liav Hen, Tom Tirer, Raja Giryes +1
Diffusion models provide powerful generative priors for solving inverse problems by sampling from a posterior distribution conditioned on corrupted measurements. Existing methods p…
(SP)-Net: A Neural Spatial Spectrum Method for DOA Estimation
Lioz Berman, Sharon Gannot, Tom Tirer
We consider the problem of estimating the directions of arrival (DOAs) of multiple sources from a single snapshot of an antenna array, a task with many practical applications. In s…
Efficient Conformal Prediction for Regression Models under Label Noise
Yahav Cohen, Jacob Goldberger, Tom Tirer
In high-stakes scenarios, such as medical imaging applications, it is critical to equip the predictions of a regression model with reliable confidence intervals. Recently, Conforma…
Catastrophic Forgetting Mitigation Through Plateau Phase Activity Profiling
Idan Mashiach, Oren Glickman, Tom Tirer
Catastrophic forgetting in deep neural networks occurs when learning new tasks degrades performance on previously learned tasks due to knowledge overwriting. Among the approaches t…
SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
Yehonathan Refael, Guy Smorodinsky, Tom Tirer +1
Low-rank gradient-based optimization methods have significantly improved memory efficiency during the training of large language models (LLMs), enabling operations within constrain…
ConfIC-RCA: Statistically Grounded Efficient Estimation of Segmentation Quality
Matias Cosarinsky, Ramiro Billot, Lucas Mansilla +5
Assessing the quality of automatic image segmentation is crucial in clinical practice, but often very challenging due to the limited availability of ground truth annotations. Rever…
LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM
Yehonathan Refael, Iftach Arbel, Ofir Lindenbaum +1
We study robust parameter-efficient fine-tuning (PEFT) techniques designed to improve accuracy and generalization while operating within strict computational and memory hardware co…
Zero-Shot Image Restoration Using Few-Step Guidance of Consistency Models (and Beyond)
Tomer Garber, Tom Tirer
In recent years, it has become popular to tackle image restoration tasks with a single pretrained diffusion model (DM) and data-fidelity guidance, instead of training a dedicated d…
Unveiling Multiple Descents in Unsupervised Autoencoders
Kobi Rahimi, Yehonathan Refael, Tom Tirer +1
The phenomenon of double descent has challenged the traditional bias-variance trade-off in supervised learning but remains unexplored in unsupervised learning, with some studies ar…
Can Kernel Methods Explain How the Data Affects Neural Collapse?
Vignesh Kothapalli, Tom Tirer
A vast amount of literature has recently focused on the "Neural Collapse" (NC) phenomenon, which emerges when training neural network (NN) classifiers beyond the zero training erro…
On Temperature Scaling and Conformal Prediction of Deep Classifiers
Lahav Dabah, Tom Tirer
In many classification applications, the prediction of a deep neural network (DNN) based classifier needs to be accompanied by some confidence indication. Two popular approaches fo…
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
Tomer Garber, Tom Tirer
Training deep neural networks has become a common approach for addressing image restoration problems. An alternative for training a "task-specific" network for each observation mod…
Deep Internal Learning: Deep Learning from a Single Input
Tom Tirer, Raja Giryes, Se Young Chun +1
Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. Th…
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
Vignesh Kothapalli, Tom Tirer, Joan Bruna
Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in…
ADIR: Adaptive Diffusion for Image Reconstruction
Shady Abu-Hussein, Tom Tirer, Raja Giryes
Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promisin…
Perturbation Analysis of Neural Collapse
Tom Tirer, Haoxiang Huang, Jonathan Niles-Weed
Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" be…
Performance Analysis of Automotive SAR With Radar Based Motion Estimation
Oded Bialer, Tom Tirer
Automotive synthetic aperture radar (SAR) can achieve a significant angular resolution enhancement for detecting static objects, which is essential for automated driving. Obtaining…
Denoiser-based projections for 2-D super-resolution multi-reference alignment
Jonathan Shani, Tom Tirer, Raja Giryes +1
We study the 2-D super-resolution multi-reference alignment (SR-MRA) problem: estimating an image from its down-sampled, circularly-translated, and noisy copies. The SR-MRA problem…
Direction of Arrival Estimation and Phase-Correction for Non-Coherent Sub-Arrays: A Convex Optimization Approach
Tom Tirer, Oded Bialer
Estimating the direction of arrival (DOA) of sources is an important problem in aerospace and vehicular communication, localization and radar. In this paper, we consider a challeng…
Extended Unconstrained Features Model for Exploring Deep Neural Collapse
Tom Tirer, Joan Bruna
The modern strategy for training deep neural networks for classification tasks includes optimizing the network's weights even after the training error vanishes to further push the…