AI Research

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Medium Severity Global
Date Occurred May 26, 2026 17:59 UTC
Event Type AI Research
Source arXiv
Recorded May 27, 2026
Full Description

arXiv: LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding and detection framework based on Parallel Box Decoding (

AI Intelligence Layer

AI Categories

performance
Event Metadata
  • ID #4008
  • Type AI Research
  • Region Global
  • Severity Medium
  • Indexed May 27, 2026