AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data

Roger Ferrod, Maël Lecene, Krishna Sapkota, George Leifman, Vered Silverman, Genady Beryozkin, Sylvain Lobry

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 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
fine-tune LLaVA-1.6 on GroundSet instructionsLLaVA-1.6 7B · GroundSet test, Classificationacc@0.8: 29.20 -> 94.18Improved
fine-tune LLaVA-1.6 on GroundSet instructionsLLaVA-1.6 7B · GroundSet test, DetectionF1@0.5: 0.92 -> 49.47Improved
fine-tune LLaVA-1.6 on GroundSet instructionsLLaVA-1.6 7B · GroundSet test, CaptioningCIDEr: 17.93 -> 104.48Improved
RS-specific fine-tuning on legacy data (GeoChat) vs general modelLLaVA-1.5 base · GroundSet test, Classificationacc@0.8: 28.62 -> 7.59Hurt
RS-specific fine-tuning (SkySenseGPT) vs general LLaVA on VQALLaVA base · GroundSet test, VQAF1: 86.36 -> 89.69Mixed
use grounding-specialized architecture (Ferret) vs RS specialistsFerret · GroundSet test, DetectionF1@0.5: 5.52 -> 18.08Improved
add text-only polygon reasoning augmentation (ablation)GroundSet LLaVA-1.6 · 100k subset, SegmentationF1@0.5: 12.62 -> 14.52Improved
add exhaustive segmentation queries (ablation)GroundSet LLaVA-1.6 · 100k subset, SegmentationF1@0.5: 12.62 -> 14.54Improved
add text-only geometric augmentation (ablation)GroundSet LLaVA-1.6 · 100k subset, Classificationacc@0.8: 90.47 -> 90.06No clear effect
unfreeze vision encoder (ablation)GroundSet LLaVA-1.6 · 100k subset, SegmentationF1@0.5: 12.62 -> 11.52Hurt
filter occluded invisible instances (ablation)GroundSet LLaVA-1.6 · 100k subset, SegmentationF1@0.5: 12.62 -> 15.31Mixed
train on GroundSet, evaluate zero-shot on VRSBench detectionGroundSet LLaVA-1.6 · VRSBench, DetectionF1@0.5: 12.81 -> 15.47Improved

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