@article{metaxas2026ultravit, title={UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models}, author={Metaxas, Ioannis Maniadis and Bulat, Adrian and Baldrati, Alberto and Zaganidis, Anestis and Ouali, Yassine and Kim, Hyeonuk and Tzimiropoulos, Georgios}, journal={arXiv preprint arXiv:2607.23373}, year={2026} }