LocateAnything：基于并行框解码的快速高质量视觉-语言定位

摘要

视觉-语言模型（VLMs）通常将视觉定位与检测形式化为坐标令牌生成问题，即将每个二维框序列化为多个一维令牌，这些令牌在很大程度上是独立学习与解码的。这种逐令牌解码方式与边界框几何结构的耦合性不匹配，并且由于严格顺序生成而造成了实际推理瓶颈。我们提出LocateAnything，一种基于并行框解码（PBD）的统一生成式定位与检测框架。通过将边界框和关键点等几何元素作为原子单元进行单步解码，LocateAnything保持了框内几何一致性，并实现了显著的并行性。我们证明PBD在解码吞吐量和定位精度上均有所提升。此外，我们开发了可扩展的数据引擎，并构建了包含超过1.38亿训练样本的大规模数据集LocateAnything-Data，大幅增加了高精度定位的数据多样性。大量评估表明，LocateAnything推动了速度-精度前沿，在显著提高解码吞吐量的同时，在多个基准测试中提升了高IoU定位质量。这些结果凸显了并行框解码与大规模训练数据在实现高效、精确的统一视觉定位与检测方面的互补优势。

English

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 (PBD). By decoding geometric elements such as bounding boxes and points as atomic units in a single step, LocateAnything preserves intra-box geometric coherence and unlocks substantial parallelism. We show that PBD improves both decoding throughput and localization accuracy. We further develop a scalable data engine and curate LocateAnything-Data, a large-scale dataset with more than 138 million training samples, substantially increasing data diversity for high-precision localization. Extensive evaluations show that LocateAnything advances the speed-accuracy frontier, achieving significantly higher decoding throughput while improving high-IoU localization quality across diverse benchmarks. The results highlight the complementary benefits of Parallel Box Decoding and large-scale training data in enabling efficient and precise unified visual grounding and detection.