Itay Itzhak's picture

Itay Itzhak

itay1itzhak

·

https://itay1itzhak.github.io/

itay1itzhak

AI & ML interests

NLP & Deep learning

Organizations

upvoted a paper 2 months ago

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Paper • 2510.15015 • Published Oct 16, 2025 • 10

upvoted a paper 3 months ago

Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs

Paper • 2509.22582 • Published Sep 26, 2025 • 11

upvoted a paper 4 months ago

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

Paper • 2508.13650 • Published Aug 19, 2025 • 16

upvoted a paper 5 months ago

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs

Paper • 2507.07186 • Published Jul 9, 2025 • 2

upvoted 3 papers 7 months ago

Effective Red-Teaming of Policy-Adherent Agents

Paper • 2506.09600 • Published Jun 11, 2025 • 39

Multi-Domain Explainability of Preferences

Paper • 2505.20088 • Published May 26, 2025 • 20

TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations

Paper • 2505.18125 • Published May 23, 2025 • 112

upvoted 2 papers 8 months ago

Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading

Paper • 2505.02872 • Published May 4, 2025 • 17

RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation

Paper • 2504.17502 • Published Apr 24, 2025 • 55

upvoted 2 papers 9 months ago

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models

Paper • 2504.01137 • Published Apr 1, 2025 • 21

AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation

Paper • 2503.19693 • Published Mar 25, 2025 • 76

upvoted a paper 10 months ago

Inside-Out: Hidden Factual Knowledge in LLMs

Paper • 2503.15299 • Published Mar 19, 2025 • 56

upvoted a paper 11 months ago

Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs

Paper • 2502.12964 • Published Feb 18, 2025 • 3

upvoted a paper 12 months ago

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

Paper • 2501.06751 • Published Jan 12, 2025 • 32

upvoted 2 papers about 1 year ago

NL-Eye: Abductive NLI for Images

Paper • 2410.02613 • Published Oct 3, 2024 • 23

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Paper • 2410.02707 • Published Oct 3, 2024 • 47