AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards Spatial Supersensing in the Wild

Tianjun Gu, Tianyu Xin, Kuan Zhang, Bowen Yang, Yinan Han, Peize Li, Yucheng Lu, Jianhang Liu, Xinran Zhang, KOK CHUNG CHUA, Qiyue Zhao, Qinlei Xie and 3 more

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
rotate query frame viewpoint in VPOGPT-5.4 · VSI-Super-Wild VPOaccuracy (%): 26.0% -> 24.9%Hurt
rotate query frame viewpoint in VPOQwen3-VL-8B · VSI-Super-Wild VPOaccuracy (%): 25.7% -> 24.4%Hurt
rotate query frame viewpoint in VPOCambrian-S-7B · VSI-Super-Wild VPOaccuracy (%): 26.2% -> 25.6%Hurt
ask last-occurrence instead of first-occurrence ordering in VOOGPT-5.4 · VSI-Super-Wild VOOaccuracy (%): 31.3% -> 22.1%Hurt
ask last-occurrence instead of first-occurrence ordering in VOOQwen3-VL-8B · VSI-Super-Wild VOOaccuracy (%): 50.2% -> 30.5%Hurt
ask last-occurrence instead of first-occurrence ordering in VOOCambrian-S-7B · VSI-Super-Wild VOOaccuracy (%): 50.7% -> 30.0%Hurt
lengthen video duration from 0-10 to 120+ minutesopen-source models average · VSI-Super-Wildoverall score: 35.0 -> 26.3Hurt
probe object state (VOO) instead of agent (VMR) or place (VPO) stateCambrian-S-7B · VSI-Super-Wildaccuracy (%): 26.91 -> 40.36Improved
use streaming input instead of 128 sampled framesCambrian-S-7B-LFP · VSI-Super-Wildoverall score: 32.86 -> 33.35No clear effect
scale Cambrian-S from 0.5B to 3BCambrian-S · VSI-Super-Wildoverall score: 21.46 -> 33.18Improved
scale Cambrian-S from 3B to 7BCambrian-S · VSI-Super-Wildoverall score: 33.18 -> 34.22No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy