arXiv 2609.39600 · cs.CV · 2026-09-30
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
Qize Yu, Lianrui Fan, Bowen Ping, Xini Ding, Zetian Song, Junbo Niu, Kaixuan Wang, Tianxing Chen 等 22 人
XPENG AI
在最新榜 #58 本站收录于 2026-10-21
一句话要点
GroundAnything 用双向扩散并行解码目标位置，在保持精准的同时大幅加快视觉定位。
GroundAnything decodes grounding outputs in parallel with bidirectional diffusion, keeping precision while being much faster.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：视觉理解与 3D
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲170
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲156
- EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling ▲60
- All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts ▲56
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。