Robustness in Both Domains: CLIP Needs a Robust Text Encoder
Paper
•
2506.03355
•
Published
•
6
Christian Schlarmann
chs20
AI & ML interests
None yet
Organizations
authored
4
papers
7 months ago
On the Adversarial Robustness of Multi-Modal Foundation Models
Paper
•
2308.10741
•
Published
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
Paper
•
2402.12336
•
Published
FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens
Paper
•
2506.03096
•
Published
•
4