9 papers
Stress Testing Unlearning Algorithms
Noam Diamant, Ethan Fetaya, Neta Glazer
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…
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…
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…
Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance
Gal Vinograd, Idan Achituve, Ethan Fetaya
We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models that promotes diversity among samples gen…
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…