AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors

Zhengshen Zhang, Hao Li, Yalun Dai, Zhengbang Zhu, Lei Zhou, Chenchen Liu, Dong Wang, Francis E. H. Tay, Sijin Chen, Ziwei Liu, Yuxiao Liu, Xinghang Li and 1 more

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 21 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
inject spatial tokens into the action head instead of the VLM (ablation)FALCON · CALVIN ABC->DAvg. Len.: 3.79 -> 3.91Improved
inject spatial tokens into the action head instead of the VLM (ablation)FALCON · CALVIN ABCD->DAvg. Len.: 4.00 -> 4.08Improved
use element-wise addition instead of cross-attention fusion (ablation)FALCON · CALVIN ABC->DAvg. Len.: 3.68 -> 3.91Improved
use element-wise addition instead of FiLM-gated fusion (ablation)FALCON · CALVIN ABC->DAvg. Len.: 3.76 -> 3.91Improved
add test-time depth to RGB-trained FALCONFALCON · CALVIN ABC->DAvg. Len.: 3.91 -> 3.95Improved
add test-time depth to RGB-trained FALCONFALCON · CALVIN ABCD->DAvg. Len.: 4.08 -> 4.09No clear effect
remove depth at test time for RGB-D trained FALCONFALCON · CALVIN ABCD->DAvg. Len.: 4.09 -> 4.07No clear effect
replace point cloud encoder with ESM (RGB-only) over Kosmos-VLA RGBFALCON · CALVIN ABC->DAvg. Len.: 3.48 -> 3.91Improved
add wrist camera images to ESM (ablation)FALCON · CALVIN ABCD->DAvg. Len.: 4.08 -> 4.10Improved
increase loss weight lambda from 0.01 to 0.05 (ablation)FALCON · CALVIN ABC->DAvg. Len.: 3.91 -> 3.87Hurt
increase LSTM history length from 8 to 16 (ablation)Kosmos-VLA (LSTM) · CALVIN ABC->DAvg. Len.: 3.90 -> 4.23Improved
increase LSTM chunk size from 5 to 10 (ablation)Kosmos-VLA (LSTM) · CALVIN ABC->DAvg. Len.: 3.99 -> 4.23Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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