arXivShihao Wang, Shilong Liu, Yuanguo Kuang, Xinyu Wei, Yangzhou Liu, Zhiqi Li, Yunze Man, Guo Chen, Andrew Tao, Guilin Liu, Jan Kautz, Lei Zhang, Zhiding YuTue, May 26, 2026, 10:59 AM PDT
score 16.5
Parallel decoding speeds up visual localization without sacrificing accuracy
Original: LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Source: arxiv.org ↗
Writing ELI5 summary…