Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
Paper • 2605.19227 • Published • 1
Hossein Shakibania
Hossshakiba
AI & ML interests
Generative Models, Multimodal AI
Recent Activity
upvoted a paper 1 day ago
Obliviate: Erasing Concepts from Autoregressive Image Generation Models upvoted a paper 1 day ago
VETO: Towards Protecting Images From Frontier AI EditingOrganizations
upvoted 3
papers 1 day ago
authored a
paper 5 days ago
updated a
Space 5 days ago
liked a
dataset 6 days ago
authored a
paper 7 days ago
published a
Space 7 days ago
authored a
paper 27 days ago
upvoted a paper 3 months ago
upvoted a paper 7 months ago
authored 3
papers 7 months ago
CDAN: Convolutional dense attention-guided network for low-light image enhancement
Paper • 2308.12902 • Published
Dual Branch Deep Learning Network for Detection and Stage Grading of Diabetic Retinopathy
Paper • 2308.09945 • Published
No Trust Issues Here: A Technical Report on the Winning Solutions for the Rayan AI Contest
Paper • 2512.01498 • Published • 2
upvoted a paper about 1 year ago
updated a
Space over 1 year ago
published a
Space over 1 year ago
published a
model over 1 year ago
updated a
model over 1 year ago