Project AURIONAI Use-Cases Research & Innovation
Ant Group
geospatial

SkySense V2

Successor of SkySense (ICCV 2025); beats SkySense by 1.8 points on average over 16 datasets.

Figure from the SkySense V2 paper: SkySense V2 has achieved superior performance on 16 datasets over 7 distinct tasks compared with its predecessor SkySense and supports a board range of tasks.
Levelmodel
Classgeospatial
Parametersnot in the notes
Contextnot in the notes
Released18 Jul 2025
Opennessunknown
Runs onsingle datacentre GPU
Statusactive

Lineage

successor
SkySense to SkySense V2: successor, high confidenceSkySenseSkySenseAnt Group, Dec 2023SkySense V2SkySense V2Ant Group, Jul 2025
Ant GroupSkySense is the parent (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Identity

Developer
Ant Group
Family
not in the notes
Released
18 Jul 2025 sourcesannouncement page
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
MoE Single unified transformer backbone for multiple modalities; adaptive patch merging; modality prompt tokens; MoE
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
single datacentre GPU
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing arxiv.org https://arxiv.org/abs/2507.13812

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SkySense V2", https://aurion.semai.id/models/ant-group-skysense-v2/, records of October 2026.