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 and 3 more
MirroS
In latest · #33 2026-W42 #10 Added on 2026-10-21
One-line takeaway
Finds S-Space, a linear subspace inside MLLMs where object tokens encode continuous coordinates, acting as an internal spatial workspace.
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。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Multimodal
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.