AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors

Hanxun Yu, Xuan Qu, Lei Ke, Boqiang Zhang, YUXIN WANG, Jianke Zhu, Dong Yu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 1 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 geometry priors (camera + geometry tokens) via cross-attention fusion (ablation)Stream3D-VLM-7B visual baseline · Stream3D-BenchNA: 46.0 -> 59.8Improved
add geometry priors to visual baseline (ablation)Stream3D-VLM · VSI-Bench NAaccuracy: 42.9 -> 65.7Improved
use cross-attention fusion instead of addition (ablation)Stream3D-VLM · Stream3D-Bench NAaccuracy: 57.6 -> 59.8Improved
use cross-attention fusion instead of addition (MCA) (ablation)Stream3D-VLM · Stream3D-Bench MCAaccuracy: 65.8 -> 65.4No clear effect
use cross-attention instead of concat + MLP (ablation)Stream3D-VLM · Stream3D-Bench NAaccuracy: 53.5 -> 59.8Improved
use GAVC instead of average pooling at 50% retention (ablation)Stream3D-VLM · Stream3D-Bench NAaccuracy: 47.8 -> 59.8Improved
use GAVC instead of VisionZip at 50% retention (ablation)Stream3D-VLM · ScanQACIDEr: 87.2 -> 104.5Improved
replace standard CE with focal loss for streaming tokens (ablation)Stream3D-VLM · Stream3D-BenchAnswer-Timing Accuracy: 86.7% -> 77.4%Hurt
raise streaming loss weight lambda from 2.0 to 3.0 (ablation)Stream3D-VLM · Stream3D-BenchNA: 59.8 -> 57.0 NA; timing 86.7% -> 89.2%Mixed
lower streaming loss weight lambda from 2.0 to 1.0 (ablation)Stream3D-VLM · Stream3D-BenchAnswer-Timing Accuracy: 86.7% -> 80.3%Hurt
online streaming model vs best offline spatial reasoning model on Relative DirectionStream3D-VLM-8B · VSI-Bench Rel. Dir.accuracy: 80.5 -> 73.3Hurt
use Stream3D-VLM-8B instead of VLM-3R-8BStream3D-VLM · VSI-Benchaverage accuracy: 60.9 -> 65.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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