AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning

Tin Stribor Sohn, Maximilian Dillitzer, Jason Corso, Johannes Bach, Eric Sax

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 6 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 training-free 4DSG with STEP tokens (ablation)Gemma3-4B-IT · VLM4D (200-question subset)overall accuracy: 49.25% (A1) to 77.5% (A3)Improved
add 2D temporal tracking to VLM-only baseline (ablation)Gemma3-4B-IT · VLM4D (200-question subset)egocentric/exocentric accuracy: +18% ego, +20% exoImproved
add 3D STEP tokens on top of 2D tracking (ablation)Gemma3-4B-IT · VLM4D (200-question subset)egocentric/exocentric accuracy: +22% ego, +20% exoImproved
add 4D STEP tokens (ablation)Gemma3-4B-IT · VLM4D (200-question subset)false-positive accuracy: 74.0 -> 74.0No clear effect
add 2D temporal tracking (ablation)Gemma3-4B-IT · VLM4D (200-question subset)false-positive accuracy: 74.0 -> 72.0Hurt
add SNOW 4DSG to Gemma3-4B-ITSNOW · NuScenes-QAStatus accuracy: +23.5%Improved
add SNOW 4DSGSNOW · NuScenes-QAoverall accuracy: 58.5 -> 60.1Improved
use SNOW instead of best prior on ComparisonSNOW · NuScenes-QAComparison accuracy: 68.8 -> 61.0Hurt
use training-free SNOW vs RS-finetuned modelsSNOW · RoboSpatial-HomeContext accuracy: 31.1 -> 54.92Improved
use SNOW vs best priorSNOW · RoboSpatial-HomeCompatibility accuracy: 81.0 -> 78.10Hurt
use SNOW vs Gemini-2.5-ProSNOW · VLM4Doverall accuracy: 62.0 -> 73.75Improved
use training-free SNOW vs prior trained open-vocab methodsSNOW · NuScenes LiDAR segmentation (val)mIoU: 38.1 vs 44.6 (OV3D)Mixed

Later papers that compared with this method

1 later accepted paper reports SNOW as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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