14 citations · 16 across the 5 of their papers we have counts for
5 papers
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
Tsachi Blau, Moshe Kimhi, Yonatan Belinkov +2
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates…
Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency
Maor Dikter, Tsachi Blau, Chaim Baskin
Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as…
GRAM: Global Reasoning for Multi-Page VQA
Tsachi Blau, Sharon Fogel, Roi Ronen +6
The increasing use of transformer-based large language models brings forward the challenge of processing long sequences. In document visual question answering (DocVQA), leading met…
Class-Conditioned Transformation for Enhanced Robust Image Classification
Tsachi Blau, Roy Ganz, Chaim Baskin +2
Robust classification methods predominantly concentrate on algorithms that address a specific threat model, resulting in ineffective defenses against other threat models. Real-worl…
Threat Model-Agnostic Adversarial Defense using Diffusion Models
Tsachi Blau, Roy Ganz, Bahjat Kawar +2
Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world…