Itay Yona's picture

1 3 8

Itay Yona

tux

1tux

AI & ML interests

Explainable AI Neuroscience

Recent Activity

updated a model 2 days ago

tux/ablated-qwen-2.5-7b

published a model 2 days ago

tux/ablated-qwen-2.5-7b

updated a model 6 days ago

tux/Qwen3-1.7B_modified

View all activity

Organizations

None yet

authored a paper 20 days ago

In-Context Representation Hijacking

Paper • 2512.03771 • Published 21 days ago • 3

authored a paper 7 months ago

Lessons from Defending Gemini Against Indirect Prompt Injections

Paper • 2505.14534 • Published May 20 • 8

authored 2 papers over 1 year ago

Operationalizing Contextual Integrity in Privacy-Conscious Assistants

Paper • 2408.02373 • Published Aug 5, 2024 • 5

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

Paper • 2407.00106 • Published Jun 27, 2024 • 6