CC3M
PulseAugur coverage of CC3M — every cluster mentioning CC3M across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Recursive CLIP models explore parameter efficiency via recurrent blocks
Researchers have developed new vision-language models, rCLIP and r^2CLIP, that utilize recurrent transformer blocks instead of independently parameterized ones. This approach increases parameter sharing while maintainin…
-
New CASCADE framework enhances backdoor detection in multimodal learning
Researchers have developed a new framework called CASCADE to detect backdoor attacks in multimodal contrastive learning (MCL). Existing methods often rely on the CLIPScore metric, but this approach has limitations due t…
-
New research reveals privacy risks in vision-language models
New research indicates that multi-modal vision-language models (VLMs) are susceptible to privacy attacks, specifically membership inference attacks (MIAs), which can leak sensitive training data. One study proposes a ne…