一作ECCV 2026Poster
UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models
Ioannis Maniadis Metaxas · Adrian Bulat · Alberto Baldrati · Anestis Zaganidis · Yassine Ouali · Hyeonuk Kim · Georgios Tzimiropoulos
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Ioannis Maniadis Metaxas · Adrian Bulat · Alberto Baldrati · Anestis Zaganidis · Yassine Ouali · Hyeonuk Kim · Georgios Tzimiropoulos
Adrian Bulat · Alberto Baldrati · Ioannis Maniadis Metaxas · Yassine Ouali · Georgios Tzimiropoulos
Anurag Das · Adrian Bulat · Alberto Baldrati · Ioannis Maniadis Metaxas · Bernt Schiele · Georgios Tzimiropoulos · Brais Martinez
Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored. While existing benchmarks have initiated the evaluation of multi-image models, a comprehensive analysis of their co...