Hey, I'm Eliahu Horwitz

Currently, I am a Computer Science PhD student at the Hebrew University of Jerusalem, studying under the supervision of Prof. Yedid Hoshen.

However, research has not always been my priority. Beginning as a self-taught software developer, I have worked with a variety of technologies across the tech stack. More recently, I have pursued a career in research. My passion is demystifying complex ideas and developing simpler, intuitive alternatives.


Publications

Recovering the Pre-Fine-Tuning Weights of Generative Models

Arxiv Preprint
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 fine-tuning. This practice is considered safe, as no current method can recover the unsafe, pre-fine-tuning model weights. In this paper, we demonstrate that this assumption is often false. Concretely, we present Spectral DeTuning, a method that can recover the weights of the pre-fine-tuning model using a few low-rank (LoRA) fine-tuned models. In contrast to previous attacks that attempt to recover pre-fine-tuning capabilities, our method aims to recover the exact pre-fine-tuning weights. Our approach exploits this new vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.

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

We present the first diffusion-based method that is able to perform text-based motion and appearance editing of general, real-world videos. Our approach uses a video diffusion model to combine, at inference time, the low-resolution spatio-temporal information from the original video with new, high resolution information that it synthesized to align with the guiding text prompt. We extend our method for animating images, bringing them to life by adding motion to existing or new objects, and camera movements.

Conffusion: Confidence Intervals for Diffusion Models

Arxiv Preprint
Eliahu Horwitz, Yedid Hoshen

We construct a confidence interval around each generated pixel such that the true value of the pixel is guaranteed to fall within the interval with a probability set by the user. Since diffusion models parametrize the data distribution, a straightforward way of constructing such intervals is by drawing multiple samples and calculating their bounds. However, this method has several drawbacks: i) slow sampling speeds ii) suboptimal bounds iii) requires training a diffusion model per task. To mitigate these shortcomings we propose Conffusion, wherein we fine-tune a pre-trained diffusion model to predict interval bounds in a single forward pass. We show that Conffusion outperforms the baseline method while being three orders of magnitude faster.

Anomaly Detection Requires Better Representations

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

In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks.
We then argue that tackling the next-generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.

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

VAND Workshop - CVPR 2023
Eliahu Horwitz, Yedid Hoshen

We conduct a careful study seeking answers to several questions: questions:
(1) Do current 3D AD&S methods truly outperform state-of-the-art 2D methods on 3D data?
(2) Is 3D information potentially useful for AD&S?
(3) What are the key properties of successful 3D AD&S representations?
(4) Are there complementary benefits from using 3D shape and color modalities?

DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample

ICCV, 2021 (Oral)
Yael Vinker*, Eliahu Horwitz*, Nir Zabari, Yedid Hoshen

We present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network.