AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

Tianyu Xu, Jiawei Chen, Jiazhao Zhang, Wenyao Zhang, Zekun Qi, Minghan Li, Jiahang Liu, Lu Yue, Zhizheng Zhang, HE WANG

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 8 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
co-train with large-scale real-world VQA data (ablation)MM-Nav · InternVLA-N1 S1 benchmarkSR: Commercial 73.9 -> 86.7; Home 76.4 -> 79.9 (text: >20% drop without VQA)Improved
co-train with VQA data in real-world trials (ablation)MM-Nav · real-world thin/irregular obstaclesSRImproved
increase VQA ratio from 0% to 100% (ablation)MM-Nav latent space · sim vs real hidden-state alignmentgap-axis distance: 1.86 -> 0.38Improved
use 360 multi-view input instead of front view only (ablation)MM-Nav · InternVLA-N1 S1 benchmarkSR: Home 79.9 -> 86.3; Commercial 86.7 -> 89.9Improved
train VLA on mixed data from all three RL experts instead of one expert (ablation)MM-Nav VLA · IsaacLab capability scenesSR: Squeezing 64 -> 71; Avoiding 62 -> 68; Reaching 70 -> 80Improved
VLA student distilled from RL experts vs the expertsMixed-VLA · IsaacLab capability scenesSR: Reaching 65 -> 80, Avoiding 58 -> 68, Squeezing 73 -> 71Mixed
single mixed-scene RL expert instead of specialized experts (ablation)RL expert · IsaacLab capability scenesSR: Squeezing 73 -> 58; Reaching 65 -> 45; Avoiding 58 -> 42Hurt
capability-balanced data aggregation instead of unbalanced (ablation)MM-Nav iterative training · IsaacLab capability scenesSRMixed
MM-Nav vs NavDP on IsaacLabMM-Nav · IsaacLab squeezing sceneSR: 18 -> 71Improved
MM-Nav vs strongest baseline SIDP on InternVLA-N1 S1MM-Nav · InternVLA-N1 S1 benchmarkSR: Home 63.2 -> 86.3; Commercial 81.2 -> 89.9Improved

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