Search papers, labs, and topics across Lattice.
5
0
4
5
AirflowAttack reveals that adversarial perturbations can not only deceive infrared VLMs but also enhance their false confidence in erroneous classifications.
Infrared data, often overlooked, can dramatically enhance vision-language models, as shown by FusionRS's ability to improve dual-modal understanding and captioning performance.
Even with robust training techniques like EOT, a carefully crafted adversarial patch can reliably fool VIS-IR VLMs and transfer across tasks like classification, captioning, and VQA.
VLMs can be easily fooled in the real world by strategically manipulating lighting, causing them to misinterpret scenes and hallucinate nonsensical captions.
Medical vision-language models are surprisingly brittle: clinically plausible image manipulations, like those introduced during routine acquisition and delivery, can drastically degrade their performance.
