11 papers
CRAW: Codec Robust Audio Watermarking
David Chernin, Ethan Fetaya
Recent advances in generative speech models have made it increasingly difficult to distinguish authentic from synthetic audio, enabling new forms of fraud and misinformation. Audio…
Stress Testing Unlearning Algorithms
Noam Diamant, Neta Glazer, Ethan Fetaya
Recently, machine unlearning, the removal of specific training data influence from a model, has gained increasing attention. In large language models (LLMs), unlearning is particul…
Diverse Sampling in Diffusion Models with Divergence-Free Particle Guidance
Gal Vinograd, Idan Achituve, Ethan Fetaya
Modern generative models can produce high-quality samples, but independent samples under the same condition often yields highly similar outputs. Particle-based methods increase div…
PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space
Asaf Buchnick, Aviv Shamsian, Aviv Navon +1
Text-to-image generation has progressed rapidly, but faithfully generating complex scenes requires extensive trial-and-error to find the exact prompt. In the prompt inversion task,…
Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering
Neta Glazer, Lenny Aharon, Ethan Fetaya
Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-langu…
SSNAPS: Audio-Visual Separation of Speech and Background Noise with Diffusion Inverse Sampling
Yochai Yemini, Yoav Ellinson, Rami Ben-Ari +2
This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on g…
LR-DWM: Efficient Watermarking for Diffusion Language Models
Ofek Raban, Ethan Fetaya, Gal Chechik
Watermarking (WM) is a critical mechanism for detecting and attributing AI-generated content. Current WM methods for Large Language Models (LLMs) are predominantly tailored for aut…
Spatially Grounded Concept-Based Image Classification
Ran Eisenberg, Amit Rozner, Ethan Fetaya +1
Deep neural networks can achieve high accuracy while relying on evidence that is hard to inspect or misaligned with the intended task. Concept Bottleneck Models (CBMs) expose human…
Diffusion-Based Unsupervised Audio-Visual Speech Separation in Noisy Environments with Noise Prior
Yochai Yemini, Rami Ben-Ari, Sharon Gannot +1
In this paper, we address the problem of single-microphone speech separation in the presence of ambient noise. We propose a generative unsupervised technique that directly models b…
Object-Centric Open-Vocabulary Image-Retrieval with Aggregated Features
Hila Levi, Guy Heller, Dan Levi +1
The task of open-vocabulary object-centric image retrieval involves the retrieval of images containing a specified object of interest, delineated by an open-set text query. As work…
Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning?
Guy Heller, Ethan Fetaya
Bayesian learning via Stochastic Gradient Langevin Dynamics (SGLD) has been suggested for differentially private learning. While previous research provides differential privacy bou…