All Publications

Atlas of Stable Diffusion vs. Llama

We Should Chart an Atlas of All the World's Models

NeurIPS 2025 - Position Paper
Eliahu Horwitz, Nitzan Kurer, Jonathan Kahana, Liel Amar, Yedid Hoshen
Project Page arXiv 🤗 Demo Code 🤗 Dataset
An image showing an overview of ProbeLog

Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights

Arxiv Preprint
Jonathan Kahana, Or Nathan, Eliahu Horwitz, Yedid Hoshen
Project Page arXiv Code
An image showing an overview of ProbeX

Learning on Model Weights using Tree Experts

CVPR 2025
Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
Project Page arXiv Code 🤗 Dataset
An image showing an overview of ProbeGen

Deep Linear Probe Generators for Weight Space Learning

ICLR 2025
Jonathan Kahana, Eliahu Horwitz, Imri Shuval, Yedid Hoshen
Project Page arXiv Code

Data Size Recovery from Lora Weights

Workshop on Weight Space Learning - ICLR 2025
Mohammad Salama, Jonathan Kahana, Eliahu Horwitz, Yedid Hoshen
Project Page arXiv Code 🤗 Dataset

Real-Time Deepfake Detection in the Real-World

Arxiv Preprint
Bar Cavia, Eliahu Horwitz, Tal Reiss, Yedid Hoshen
Project Page arXiv Code

Unsupervised Model Tree Heritage Recovery

ICLR 2025
Eliahu Horwitz, Asaf Shul, Yedid Hoshen
Project Page arXiv Code

Distilling Datasets Into Less Than One Image

TMLR
Asaf Shul*, Eliahu Horwitz*, Yedid Hoshen
Project Page arXiv Code

Recovering the Pre-Fine-Tuning Weights of Generative Models

ICML 2024
Eliahu Horwitz, Jonathan Kahana, Yedid Hoshen
Project Page arXiv Code 🤗 Dataset

Dreamix: Video Diffusion Models are General Video Editors

Arxiv Preprint
Eyal Molad*, Eliahu Horwitz*, Dani Valevski*, Alex Rav Acha, Yossi Matias, Yael Pritch, Yaniv Leviathan†, Yedid Hoshen†
Project Page arXiv

Conffusion: Confidence Intervals for Diffusion Models

Arxiv Preprint
Eliahu Horwitz, Yedid Hoshen
Project Page arXiv Code
SSRL AD thumbnail

Anomaly Detection Requires Better Representations

SSLWIN Workshop - ECCV 2022
Tal Reiss, Niv Cohen, Eliahu Horwitz, Ron Abutbul, Yedid Hoshen
Project Page arXiv

Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection

VAND Workshop - CVPR 2023
Eliahu Horwitz, Yedid Hoshen
Project Page arXiv Code

DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample

ICCV 2021 (Oral)
Yael Vinker*, Eliahu Horwitz*, Nir Zabari, Yedid Hoshen
Project Page arXiv Code