2 papers
cs.CV2025
MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
Changho Choi, Minho Kim, Jinkyu Kim
Despite decades of progress, a truly input-size agnostic visual encoder-a fundamental characteristic of human vision-has remained elusive. We address this limitation by proposing \…
cs.CV2025
Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
Kyungryul Back, Seongbeom Park, Milim Kim +6
Large Vision-Language Models (LVLMs) have recently shown promising results on various multimodal tasks, even achieving human-comparable performance in certain cases. Nevertheless,…