AI Paper Atlas

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

LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning

HAIHONG HAO, Lei Chen, Mingfei Han, Changlin Li, Dong An, Yuqiang Yang, Zhihui Li, Xiaojun Chang

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 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
supervise Pilot Token with future visual latents instead of no extra supervision (ablation)LatentPilot · R2R Val-UnseenSR: 51.7 -> 62.0Improved
supervise Pilot Token with future visual latents instead of 3D features (ablation)LatentPilot · R2R Val-UnseenSR: 50.3 -> 62.0Improved
supervise Pilot Token with future visual latents instead of text (ablation)LatentPilot · R2R Val-UnseenSR: 53.2 -> 62.0Improved
add 3D (VGGT) supervision to Pilot Token (ablation)LatentPilot · R2R Val-UnseenSR: 51.7 -> 50.3Hurt
add text supervision to Pilot Token (ablation)LatentPilot · R2R Val-UnseenSR: 51.7 -> 53.2No clear effect
add future vision supervision to Pilot Token (ablation)LatentPilot · R2R Val-SeenSR: 53.1 -> 65.1Improved
internalize future supervision instead of plug-in Wan2.1 world model (ablation)LatentPilot · R2R Val-SeenSR: 56.6 -> 65.1Improved
internalize future supervision instead of plug-in CogVideoX1.5 world model (ablation)LatentPilot · R2R Val-SeenSR: 59.3 -> 65.1Improved
internalize future supervision instead of plug-in Wan2.1 world model (ablation)LatentPilot · R2R Val-Seentime per action (ms): 2040 -> 130Improved
add more PilotLoop flywheel rounds (ablation)LatentPilot · R2R Val-UnseenSR and SPLImproved
LatentPilot vs JanusVLNLatentPilot · R2R-CE Val-UnseenSR: 60.5 -> 62.0Improved
LatentPilot vs JanusVLNLatentPilot · RxR-CE Val-UnseenSR: 56.2 -> 58.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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