Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
Paper
•
2505.22943
•
Published
•
4
•
4
Jaewoo Ahn
ahnpersie
·
AI & ML interests
None yet
Recent Activity
authored
a paper
6 days ago
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on
Diverse Video Games
updated
a model
8 days ago
ahnpersie/llama3.1-8b-lora-coco-deceptive-clip
Organizations
None yet
ahnpersie's activity
Fix pipeline tag, add project page
#1 opened 8 days ago
by
nielsr
commented
3
papers
12 days ago
Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
Paper
•
2505.22943
•
Published
•
4
•
4
Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
Paper
•
2505.22943
•
Published
•
4
•
4