AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

Byungwoo Jeon, Dongyoung Kim, Huiwon Jang, Insoo Kim, Jinwoo Shin

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 2 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
use LLM-based decoder supervision instead of SAM decoder (ablation)DINOv2 ViT-L/14 · ADE20K segmentationmIoU: 50.1 -> 51.5Improved
use LLM-based decoder supervision instead of VGGT decoder (ablation)DINOv2 ViT-L/14 · ADE20K segmentationmIoU: 45.6 -> 51.5Improved
use LLM-based decoder supervision instead of linear depth head (ablation)DINOv2 ViT-L/14 · ImageNet-1K classificationaccuracy: 85.7 -> 88.3Improved
use LLM-based decoder supervision instead of linear segmentation head (ablation)DINOv2 ViT-L/14 · NYUd depth estimationRMSE: 0.45 -> 0.32Improved
use LLM-based decoder instead of SAM decoder (ablation)DINOv2 ViT-L/14 · ScanQABLEU-1: 37.6 -> 40.0Improved
use forward (pixel->object->scene) turn order instead of reverse (ablation)SpatialBoost on DINOv2 · ADE20K segmentationmIoU: 48.4 -> 48.9Improved
use forward turn order instead of random order (ablation)SpatialBoost on DINOv2 · NYUd depth estimationRMSE: 0.36 -> 0.34Improved
combine 50K single-view and 50K multi-view data instead of 100K single-view only (ablation)SpatialBoost on DINOv2 · ADE20K segmentationmIoU: 48.9 -> 49.2Improved
combine single-view and multi-view data instead of multi-view only (ablation)SpatialBoost on DINOv2 · NYUd depth estimationRMSE: 0.36 -> 0.32Improved
replace simple fine-tuning with SpatialBoost (ablation)DINOv3 · ADE20K segmentationmIoU: 56.4 -> 59.7Improved
replace simple fine-tuning with SpatialBoost (ablation)DINOv3 · CortexBench robot learningaverage score: 75.5 -> 80.8Improved
replace simple fine-tuning with SpatialBoost (ablation)OpenCLIP · NYUd depth estimationRMSE: 0.56 -> 0.40Improved

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