AI Paper Atlas

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

Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action

Pengteng Li, Weiyu Guo, He Zhang, Tiefu Cai, Xiao He, Yandong Guo, Hui Xiong

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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
add persistent spatial memory with construction, refinement and retrieval (full SOMA) over scan-then-reactive policy (ablation)GR00T N1.5 on real-world OOV tasks · real-world OOV tasks (avg of 5)success rate (%): 18.5 -> 28.3Improved
add multi-view head scanning to build the initial memory (ablation)SOMA · real-world OOV tasks (avg)success rate (%): 19.8 -> 24.1Improved
add dynamic memory refinement during manipulation (ablation)SOMA with scan-built memory · real-world OOV tasks (avg)success rate (%): 24.1 -> 28.3Improved
scanning alone with a reactive policy (no persistent memory) (ablation)GR00T N1.5 · real-world OOV tasks (avg)success rate (%): 18.5 vs 19.8 for No-Scan SOMANo clear effect
use spatial memory instead of GR00T-N1.5 reactive controlOOV Task 5 · time-to-graspseconds: 36.5 -> 14.6Improved
add geometric cues to memory (ablation)SOMA · RoboCasa GR1 (Full)overall success (%): 45.1 -> 49.3Improved
add object semantics to memory (ablation)SOMA · RoboCasa GR1 (Full)overall success (%): 43.7 -> 49.3Improved
add dynamic update mechanism (ablation)SOMA · RoboCasa GR1 (Full)overall success (%): 41.5 -> 49.3Improved
use a fixed head camera instead of an active head camera (ablation)SOMA · real-world OOV taskssuccess rateHurt
add SOMA memory in fully observable simulation with more demosGR00T N1.5 on RoboCasa GR1 · RoboCasa GR1 (Full data)average success (%): SOMA 52.0 at 300 demos but 49.3 at Full; GR00T 44.3 -> 45.9Mixed
SOMA memory on SimplerEnv Open/Close DrawerSOMA vs OpenVLA-OFT · SimplerEnv Visual Matching, Open/Close Drawersuccess rate (%): 47.2 (OpenVLA-OFT) vs 31.5 (SOMA)Hurt

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