Hossein Shakibania

Hossshakiba

6 1

·

https://hossshakiba.github.io/

AI & ML interests

Generative Models, Multimodal AI

Recent Activity

upvoted a paper 4 days ago

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

upvoted a paper 4 days ago

Obliviate: Erasing Concepts from Autoregressive Image Generation Models

upvoted a paper 4 days ago

VETO: Towards Protecting Images From Frontier AI Editing

View all activity

Organizations

upvoted 3 papers 4 days ago

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

Paper • 2605.19227 • Published May 19 • 1

Obliviate: Erasing Concepts from Autoregressive Image Generation Models

Paper • 2606.28643 • Published Jun 26 • 1

VETO: Towards Protecting Images From Frontier AI Editing

Paper • 2607.27292 • Published 11 days ago • 2

upvoted a paper 3 months ago

When Do Diffusion Models learn to Generate Multiple Objects?

Paper • 2605.00273 • Published Apr 30 • 9

upvoted a paper 7 months ago

Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy

Paper • 2601.02989 • Published Jan 6 • 6

upvoted a paper about 1 year ago

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Paper • 2505.17955 • Published May 23, 2025 • 22