21 citations · 56 across the 25 of their papers we have counts for
27 papers
A Dataset is Worth 1 MB
Elad Kimchi Shoshani, Leeyam Gabay, Yedid Hoshen
A dataset server must often distribute the same large payload to many clients, incurring massive communication costs. Since clients frequently operate on diverse hardware and softw…
Discovering Hidden Gems in Model Repositories
Jonathan Kahana, Eliahu Horwitz, Yedid Hoshen
Public repositories host millions of fine-tuned models, yet community usage remains disproportionately concentrated on a small number of foundation checkpoints. We investigate whet…
Alterbute: Editing Intrinsic Attributes of Objects in Images
Tal Reiss, Daniel Winter, Matan Cohen +4
We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even the shape of an obje…
LightLab: Controlling Light Sources in Images with Diffusion Models
Nadav Magar, Amir Hertz, Eric Tabellion +4
We present a simple, yet effective diffusion-based method for fine-grained, parametric control over light sources in an image. Existing relighting methods either rely on multiple i…
We Should Chart an Atlas of All the World's Models
Eliahu Horwitz, Nitzan Kurer, Jonathan Kahana +2
Public model repositories now contain millions of models, yet most models remain undocumented and effectively lost. In this position paper, we advocate for charting the world's mod…
Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights
Jonathan Kahana, Or Nathan, Eliahu Horwitz +1
With the increasing numbers of publicly available models, there are probably pretrained, online models for most tasks users require. However, current model search methods are rudim…
ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation
Daniel Winter, Asaf Shul, Matan Cohen +4
This paper introduces a tuning-free method for both object insertion and subject-driven generation. The task involves composing an object, given multiple views, into a scene specif…
Learning on Model Weights using Tree Experts
Eliahu Horwitz, Bar Cavia, Jonathan Kahana +1
The number of publicly available models is rapidly increasing, yet most remain undocumented. Users looking for suitable models for their tasks must first determine what each model…
Deep Linear Probe Generators for Weight Space Learning
Jonathan Kahana, Eliahu Horwitz, Imri Shuval +1
Weight space learning aims to extract information about a neural network, such as its training dataset or generalization error. Recent approaches learn directly from model weights,…
Dataset Size Recovery from LoRA Weights
Mohammad Salama, Jonathan Kahana, Eliahu Horwitz +1
Model inversion and membership inference attacks aim to reconstruct and verify the data which a model was trained on. However, they are not guaranteed to find all training samples…
Real-Time Deepfake Detection in the Real-World
Bar Cavia, Eliahu Horwitz, Tal Reiss +1
Recent improvements in generative AI made synthesizing fake images easy; as they can be used to cause harm, it is crucial to develop accurate techniques to identify them. This pape…
From Zero to Hero: Cold-Start Anomaly Detection
Tal Reiss, George Kour, Naama Zwerdling +2
When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot…
Unsupervised Model Tree Heritage Recovery
Eliahu Horwitz, Asaf Shul, Yedid Hoshen
The number of models shared online has recently skyrocketed, with over one million public models available on Hugging Face. Sharing models allows other users to build on existing m…
ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion
Daniel Winter, Matan Cohen, Shlomi Fruchter +3
Diffusion models have revolutionized image editing but often generate images that violate physical laws, particularly the effects of objects on the scene, e.g., occlusions, shadows…
Distilling Datasets Into Less Than One Image
Asaf Shul, Eliahu Horwitz, Yedid Hoshen
Dataset distillation aims to compress a dataset into a much smaller one so that a model trained on the distilled dataset achieves high accuracy. Current methods frame this as maxim…
Classifying Nodes in Graphs without GNNs
Daniel Winter, Niv Cohen, Yedid Hoshen
Graph neural networks (GNNs) are the dominant paradigm for classifying nodes in a graph, but they have several undesirable attributes stemming from their message passing architectu…
Recovering the Pre-Fine-Tuning Weights of Generative Models
Eliahu Horwitz, Jonathan Kahana, Yedid Hoshen
The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fi…
Detecting Deepfakes Without Seeing Any
Tal Reiss, Bar Cavia, Yedid Hoshen
Deepfake attacks, malicious manipulation of media containing people, are a serious concern for society. Conventional deepfake detection methods train supervised classifiers to dist…
Set Features for Anomaly Detection
Niv Cohen, Issar Tzachor, Yedid Hoshen
This paper proposes to use set features for detecting anomalies in samples that consist of unusual combinations of normal elements. Many leading methods discover anomalies by detec…
Representation Learning in Anomaly Detection: Successes, Limits and a Grand Challenge
Yedid Hoshen
In this perspective paper, we argue that the dominant paradigm in anomaly detection cannot scale indefinitely and will eventually hit fundamental limits. This is due to the a no fr…
No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection
Tal Reiss, Niv Cohen, Yedid Hoshen
Anomaly detection methods, powered by deep learning, have recently been making significant progress, mostly due to improved representations. It is tempting to hypothesize that anom…
Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels
Tzeviya Sylvia Fuchs, Yedid Hoshen
Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self…
Set Features for Fine-grained Anomaly Detection
Niv Cohen, Issar Tzachor, Yedid Hoshen
Fine-grained anomaly detection has recently been dominated by segmentation based approaches. These approaches first classify each element of the sample (e.g., image patch) as norma…
An Attribute-based Method for Video Anomaly Detection
Tal Reiss, Yedid Hoshen
Video anomaly detection (VAD) identifies suspicious events in videos, which is critical for crime prevention and homeland security. In this paper, we propose a simple but highly ef…