arXiv 2610.13527 · cs.CV · 2026-10-09
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Zhiyuan Shi, Xiang Li, Xingzhuo Guo, Shangchen Miao, Weiliang Chen, Qiyu Dai, Jinshan Ren, Jiangran Lyu 等 11 人
MirroS
在最新榜 #33 2026-W42 第 10 名 本站收录于 2026-10-21
一句话要点
发现多模态模型内部存在线性“空间工作区”S-Space，用连续坐标编码物体位置。
Finds S-Space, a linear subspace inside MLLMs where object tokens encode continuous coordinates, acting as an internal spatial workspace.
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：多模态
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲560
- LoopVL: Recurrent Visual Intelligence ▲417
- VideoJev: System One Model for Video Understanding and Interaction ▲375
- UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement ▲266
- OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction ▲238
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。