AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

NaVLA$^2$: A Vision-Language-Audio-Action Model for Multimodal Instruction Navigation

Jugang Fan, Peihao Chen, Changhao Li, Qing Du, Jian Chen, Mingkui Tan

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 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 spatial audio branch to audio encoder (no audio branches baseline) (ablation)NaVLA2 · MINav-bench (test-mini)SR: 0.206 -> 0.258Improved
add semantic audio branch to audio encoder (no audio branches baseline) (ablation)NaVLA2 · MINav-bench (test-mini)SR: 0.206 -> 0.219Improved
add semantic branch on top of spatial branch (ablation)NaVLA2 · MINav-bench (test-mini)SR: 0.258 -> 0.272Improved
add semantic branch on top of spatial branch (ablation)NaVLA2 · MINav-bench (test-mini)SPL: 0.201 -> 0.196No clear effect
add spatial branch on top of semantic branch (ablation)NaVLA2 · MINav-bench (test-mini)SPL: 0.168 -> 0.196Improved
decode actions from [NAV] embedding with action head instead of LLM text actions (ablation)NaVLA2 · MINav-bench (test-mini)SPL: 0.165 -> 0.196Improved
decode actions from [NAV] embedding with action head instead of LLM text actions (ablation)NaVLA2 · MINav-bench (test-mini)SR: 0.256 -> 0.272Improved
add chain-of-thought before [NAV] token (ablation)NaVLA2 · MINav-bench (test-mini)SR: 0.261 -> 0.272Improved
add chain-of-thought before [NAV] token (ablation)NaVLA2 · MINav-bench (test-mini)SPL: 0.192 -> 0.196Improved
give full multimodal instruction with landmarks instead of goal object onlyRL baseline · MINav-bench (test-mini)SR: 0.064 -> 0.156Improved
use VLA with spatial audio and CoThinkAct instead of NavidNaVLA2 vs Navid · MINav-bench (test-mini)SR: 0.131 -> 0.272Improved
use more modality types in an episode's references instead of a single modalityNaVLA2 · MINav-bench (test-mini)SRImproved

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