AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

VGMamba: Attribute-to-Location Clue Reasoning for Quantity-Agnostic 3D Visual Grounding

Yihang Zhu, Jinhao Zhang, Yuxuan Wang, Aming Wu, Cheng Deng

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 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
add SVD-based Attribute Mamba (SAM) (ablation)baseline · Multi3DRefer valF1@0.5 All: 38.4 -> 45.2Improved
add SVD-based Attribute Mamba (SAM) (ablation)baseline · Multi3DRefer valF1@0.5 ST w/o D: 47.8 -> 67.6Improved
add Location Mamba (LM) (ablation)baseline + SAM · Multi3DRefer valF1@0.5 All: 45.2 -> 52.5Improved
add Location Mamba (LM) (ablation)baseline + SAM · Multi3DRefer valF1@0.5 MT: 47.8 -> 53.1Improved
add Instructive Dual-Mamba (IDM) (ablation)SAM + LM · Multi3DRefer valF1@0.5 All: 52.5 -> 54.9Improved
add Instructive Dual-Mamba (IDM) (ablation)SAM + LM · Multi3DRefer valF1@0.5 ZT w/D: 45.3 -> 45.2No clear effect
reason attribute first then location instead of location first (ablation)VGMamba · Multi3DRefer valF1@0.5 All: 53.1 -> 54.9Improved
VGMamba vs previous best PQ3DVGMamba · ScanRefer valAcc@0.5 overall: 51.2 -> 53.9Improved
VGMamba vs second best D-LISAVGMamba · Multi3DRefer valF1@0.5 MT: 51.0 -> 55.1Improved

Later papers that compared with this method

1 later accepted paper reports VGMamba as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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