AI Paper Atlas

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

Dual-Anchoring: Addressing State Drift in Vision-Language Navigation

Kangyi Wu, Pengna Li, Kailin Lyu, Xi Lin, Lin Zhao, Qingrong He, Jinjun Wang, Jianyi Liu

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 7 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 Instruction Progress Anchoring (progress text co-training) (ablation)StreamVLN · R2R-CE val unseen (R2R+RxR+EnvDrop)SR (%): 40.8 -> 45.4Improved
add Memory Landmark Anchoring (landmark world model) (ablation)StreamVLN · R2R-CE val unseen (R2R+RxR+EnvDrop)NE: 6.49 -> 6.01Improved
add Memory Landmark Anchoring (landmark world model) (ablation)StreamVLN · R2R-CE val unseen (R2R+RxR+EnvDrop)SPL (%): 37.4 -> 43.3Improved
add both IPA and MLA (ablation)StreamVLN · R2R-CE val unseen (R2R+RxR+EnvDrop)SR (%): 40.8 -> 49.5Improved
add Instruction Progress Anchoring (ablation)StreamVLN · R2R-CE val unseen (all datasets)SR (%): 56.9 -> 60.8Improved
add Memory Landmark Anchoring (ablation)StreamVLN · R2R-CE val unseen (all datasets)SR (%): 56.9 -> 62.5Improved
add both IPA and MLA (ablation)StreamVLN · R2R-CE val unseen (all datasets)SPL (%): 51.9 -> 62.1Improved
add Dual-Anchoring frameworkStreamVLN · RxR-CE val unseenSR (%): 52.9 -> 61.7Improved
add Dual-Anchoring framework on long trajectoriesStreamVLN · R2R-CE val unseen by trajectory lengthSPL relative improvement: +12.6% -> +33.2%Improved
use Visual Kinematics Prompting (frame index and action overlay) for progress annotation (ablation)Qwen3-VL annotator · Progress description dataHallucination rate (%): 8.13 -> 6.04Improved
use Visual Kinematics Prompting for progress annotation (ablation)Qwen3-VL annotator · Progress description dataLogical consistency score: 1.71 -> 4.26Improved
mine landmark frames with ordered temporal grounding instead of random sampling (ablation)Qwen3-VL · Grounded landmark dataLandmark presence rate (%): 13.9 -> 75.6Improved

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