AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Mamba-3VL: Taming State Space Model for 3D Vision Language Learning

Yuan Wang, Yuxin Chen, Zhongang Qi, Lijun Liu, Jile Jiao, Xuetao Feng, Yujia Liang, Ying Shan, Zhipeng Zhang

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 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
add IDPA to spatial+channel scanning (ablation)Mamba-3VL · ScanReferaccuracy (%): 52.4 -> 53.5Improved
add IDPA to spatial+channel scanning (ablation)Mamba-3VL · SQA3Daccuracy (%): 51.0 -> 52.4Improved
add relation-prioritized spatial scanning to channel only (ablation)Mamba-3VL · SQA3Daccuracy (%): 47.0 -> 51.0Improved
add relation-prioritized spatial scanning to channel only (ablation)Mamba-3VL · Multi3DReferaccuracy (%): 49.7 -> 52.0Improved
add channel twisting to spatial scanning (ablation)Mamba-3VL · ScanReferaccuracy (%): 50.1 -> 52.4Improved
add spatial scanning to IDPA-only (ablation)Mamba-3VL · ScanReferaccuracy (%): 49.5 -> 52.1Improved
use relation twisting instead of random-order scanning (ablation)Mamba-3VL · Scan2CapCIDEr: 80.8 -> 84.0Improved
use relation twisting instead of random-order scanning (ablation)Mamba-3VL · Nr3D Hardaccuracy (%): 58.3 -> 62.9Improved
add FIS component to scanning (ablation)Mamba-3VL · Nr3D Hardaccuracy (%): 60.5 -> 62.9Improved
add NIS component to scanning (ablation)Mamba-3VL · Nr3D Hardaccuracy (%): 61.7 -> 62.9Improved
use relation twisting instead of relation AdaIN (ablation)Mamba-3VL · Scan2CapCIDEr: 83.1 -> 84.0Improved
replace Mamba-3VL instance-specific PE with linear PE (ablation)Mamba-3VL · ScanRefer, Multi3DRefer, SQA3D, Scan2Cap, Nr3DaccuracyHurt

Earlier methods this paper compares with

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