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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-step overshooting objective to world model training (ablation) | Memoir world model (GRU and Transformer) · Future observation prediction | prediction accuracy | Improved |
| use multi-step bound instead of single-step variational bound (ablation) | Memoir world model · Future observation prediction | prediction accuracy | Improved |
| replace GR-DUET persistent memory with imagination-guided retrieval | GR-DUET · IR2R-CE Val Unseen | SR: 23.7 -> 45.6 | Improved |
| compare Memoir against single-episode DUET | Memoir · IR2R-CE Val Unseen | nDTW: 58.2 -> 49.2 | Hurt |
| compare Memoir against single-episode DUET | Memoir · IR2R-CE Val Unseen | SR: 44.1 -> 45.6 | Improved |
| add Memoir to GR-DUET* | GR-DUET* · GSA-R2R Test-Non-Residential-Scene | SR: 47.1 -> 50.2 | Improved |
| add Memoir to GR-DUET* | GR-DUET* · GSA-R2R Test-Residential-Basic | SR: 67.6 -> 69.8 | Improved |
| add Memoir to GR-DUET* | GR-DUET* · GSA-R2R Test-Non-Residential-Basic | SR: 55.3 -> 57.7 | Improved |
| add Memoir to GR-DUET* | GR-DUET* · GSA-R2R user instructions (Child) | SR: 64.9 -> 66.5 | Improved |
| add back-translation augmentation (+BT) to DUET | DUET · GSA-R2R Test-Non-Residential-Scene | SPL: 30.1 -> 38.2 | Improved |
| add test-time adaptation TENT to DUET | DUET · GSA-R2R Test-Non-Residential-Scene | SPL: 30.1 -> 28.9 | Hurt |
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.
- DUET — DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning (AAAI 2023) · better on 4 of 6 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
- Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation (AAAI 2025 · similarity 0.91)
- Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight (ECCV 2026 · similarity 0.89)
- ESceme: Vision-and-Language Navigation with Episodic Scene Memory (IJCV 2024 · similarity 0.89)
- Do Visual Imaginations Improve Vision-and-Language Navigation Agents? (CVPR 2025 · similarity 0.88)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025 · similarity 0.87)
- WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction (NeurIPS 2026 · similarity 0.87)
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.
