AI Paper Atlas

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

Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision

Keji He, Yan Huang, Qi Wu, Jianhua Yang, Dong An, Shuanglin Sima, Liang Wang

NeurIPS 2021 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 18 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
replace nDTW fidelity reward with soft focal-oriented reward (ablation)RL agent · en-RxR val unseenSR (%): 29.3 -> 33.7Improved
replace nDTW fidelity reward with soft focal-oriented reward (ablation)RL agent · Landmark-RxR val unseenLoss Number: 5500 -> 5173Improved
replace nDTW fidelity reward with soft focal-oriented reward (ablation)RL agent · en-RxR val unseennDTW: 43.2 -> 41.0Hurt
replace goal-oriented SR reward with hard focal-oriented reward (ablation)RL agent · en-RxR val unseenSR (%): 32.7 -> 34.9Improved
replace fidelity+SR reward with hard focal-oriented reward (ablation)RL agent · en-RxR val unseenSR (%): 33.6 -> 34.9Improved
replace fidelity+SR reward with soft focal-oriented reward (ablation)RL agent · Landmark-RxR val unseenSSA: 52.5 -> 53.3Improved
replace complete en-RxR pairs with Landmark-RxR sub pairs in training (ablation)IL agent · R2R val unseenSR (%): 33.1 -> 40.1Improved
add complete en-RxR pairs to R2R training (ablation)IL agent · R2R val unseenSR (%): 33.0 -> 33.1No clear effect
add sub pairs to complete pairs in training (ablation)IL agent · en-RxR val unseenSR (%): 20.7 -> 26.2Improved
train on joint sub, synthesized and complete pairs (ablation)IL agent · en-RxR val unseenSR (%): 26.2 -> 28.4Improved
train on synthesized pairs instead of complete pairs (ablation)IL agent · en-RxR val unseenSR (%): 20.7 -> 24.2Improved

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