Constarium
← Search

Data · dataset · 2026

VSI-Super-Wild

Listed in Hugging Face Datasets

[ECCV 2026] Towards Spatial Supersensing in the Wild Tsinghua University, NVIDIA, Stanford University Humans make sense of continuous sensory streams by maintaining implicit world states that support spatial reasoning and prediction.

Description

VSI-Super-Wild studies whether multimodal models can develop similar spatial supersensing capabilities in genuinely long-form, in-the-wild videos. The benchmark moves beyond short indoor clips and object-centric settings.

It evaluates world… See the full description on the dataset page: huggingface.co/datasets/THUSI-Lab/VSI-Super-Wild.

Links

Where it is published

Documentation and papers

Catalogue records · 1

Topics

Provenance · 1 source records, 9 field assertions
SourceKeyLast seenRaw
Hugging Face DatasetsTHUSI-Lab/VSI-Super-Wild8 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[task].hf_task:multiple-choicesource · Hugging Faceconnector:huggingface@1.0.0/tags[task_categories:*]
concepts[task].hf_task:visual-question-answeringsource · Hugging Faceconnector:huggingface@1.0.0/tags[task_categories:*]
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0