AI Paper Atlas

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

Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigation

Yunzhe Xu, Yiyuan Pan, Zhe Liu

TPAMI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 5 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 multi-step overshooting objective to world model training (ablation)Memoir world model (GRU and Transformer) · Future observation predictionprediction accuracyImproved
use multi-step bound instead of single-step variational bound (ablation)Memoir world model · Future observation predictionprediction accuracyImproved
replace GR-DUET persistent memory with imagination-guided retrievalGR-DUET · IR2R-CE Val UnseenSR: 23.7 -> 45.6Improved
compare Memoir against single-episode DUETMemoir · IR2R-CE Val UnseennDTW: 58.2 -> 49.2Hurt
compare Memoir against single-episode DUETMemoir · IR2R-CE Val UnseenSR: 44.1 -> 45.6Improved
add Memoir to GR-DUET*GR-DUET* · GSA-R2R Test-Non-Residential-SceneSR: 47.1 -> 50.2Improved
add Memoir to GR-DUET*GR-DUET* · GSA-R2R Test-Residential-BasicSR: 67.6 -> 69.8Improved
add Memoir to GR-DUET*GR-DUET* · GSA-R2R Test-Non-Residential-BasicSR: 55.3 -> 57.7Improved
add Memoir to GR-DUET*GR-DUET* · GSA-R2R user instructions (Child)SR: 64.9 -> 66.5Improved
add back-translation augmentation (+BT) to DUETDUET · GSA-R2R Test-Non-Residential-SceneSPL: 30.1 -> 38.2Improved
add test-time adaptation TENT to DUETDUET · GSA-R2R Test-Non-Residential-SceneSPL: 30.1 -> 28.9Hurt

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