Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the multimodal processing needed for localization. Adapting these representations to box geometry offers a route t...
Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially...
Zhangxuan Gu, Hao-Xin Chen, Qiujieli Qin et al.· 0 citations
Experiments on standard referring-expression grounding benchmarks show consistent region-level improvements over strong coordinate-generating baselines, demonstrating that ground-truth boxes can provide useful privileged guidance beyond serving as coordinate labels.
Xiuyuan Zhu, Ke Lu, Hao Wu et al.· arXiv.org· 0 citations
The results show that structured coordinate generation provides an effective approach to generative visual grounding and Hi-Token encodes each coordinate with axis-specific tokens for the hundreds, tens, and ones digits, which adds coarse-to-fine structure and increases token reuse while retaining the existing VLM arch...
Xiuyuan Zhu, Ke Lu, Kun Dong et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
