AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Spatial Amsan: A Benchmark for Perception-Grounded Spatial Reasoning and Action Evaluation in Egocentric Manipulation

Changsoo Jung, Jack Fitzgerald, Ethan Seefried, Mariah Bradford, Nathaniel Blanchard

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 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
go from Task 1 (7 colored blocks) to Task 2 (16 irregular blocks)GPT-5.2 / Gemini 3 Flash · Spatial AmsanQ3 contact accuracy (%): 74.9 -> 15.9 (GPT-5.2); 69.5 -> 12.2 (Gemini)Hurt
increase number of ground-truth contacts from 1 to 2+API VLMs · Spatial Amsan Task 2Q3 exact-match (%): 60.2 -> 0.0 (GPT-5.2)Hurt
increase turn position from 1 to 8API VLMs · Spatial Amsan Task 1Q4 accuracy (%): 81.3 -> 3.9 (GPT-5.2); 81.3 -> 15.8 (Gemini); 79.3 -> 10.5 (Claude)Hurt
increase turn position from 1 to 8API VLMs · Spatial Amsan Task 1Q1 accuracy (%): 90.7 -> 90.8 (GPT-5.2)No clear effect
insert a single hand-occlusion frame (ablation)API VLMs · Spatial Amsan Task 1Q2 temporal tracking (%): 95.1 -> 85.1 (GPT-5.2); 88.0 -> 80.2 (Claude)Hurt
insert a single hand-occlusion frame (ablation)API VLMs · Spatial Amsan Task 1Q1/Q3/Q4 accuracy: Q4 49.8 -> 51.2 (GPT-5.2)No clear effect
use newer InternVL3.5-8B instead of InternVL3-8Blocal VLM · Spatial Amsanoverall accuracy (%): 29.3 -> 17.6 (Task 1); 17.5 -> 5.8 (Task 2)Hurt
use Qwen3-VL-8B instead of Qwen2.5-VL-7Blocal VLM · Spatial Amsan Task 1overall accuracy (%): 16.8 -> 28.1Improved
use reasoning-tuned VideoChat-R1-7B over its Qwen2.5-VL baselocal VLM · Spatial AmsanQ4 accuracy (%): 0.7 -> 0.7 (Task 1)No clear effect
frontier API models vs local open-weight modelsVLMs · Spatial Amsan Task 1overall accuracy (%): 29.3 -> 77.0Improved

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