mlsanityData to 14 Oct 2026

MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation

arXiv 2610.18478 ↗First posted 13 Oct 2026cs.RO cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models also fits: Visual token pruning and efficiency

Abstract (arXiv)

Large vision-language models (LVLMs) have shown strong potential for embodied vision-language navigation (VLN), yet their performance degrades on long-horizon trajectories due to context-length limits, redundant historical observations, and unstable spatial alignment across time. These issues make it difficult to both compress long navigation histories and reliably reuse past spatial experience. To address these limitations, we propose MemoryVLN, a unified memory-driven navigation system built around memory construction and management. During memory construction, Long Sequence Compression employs forgetting-curve-inspired temporal sampling to preserve dense recent evidence and sparse yet representative distant observations under a limited token budget. Ego-Aware Memory Representation further integrates 2D semantic tokens, 3D geometric tokens, and 6D agent poses, allowing each memory to encode both what was observed and where it was observed. During memory management, Hierarchical Memory Bank maintains in-episode and context-level memories through cross-context warm-start and confidence-controlled write-back. Memory Enhancement then retrieves the Top-K relevant memories according to the current navigation state and fuses them with the current visual tokens. Together, these mechanisms transform raw navigation history into compact, spatially grounded, selectively retrievable, and reusable navigation experience. Extensive experiments on R2R-CE and RxR-CE demonstrate consistent improvements over the state-of-the-art baselines by a substantial margin (i.e., 2% and 6.5% in successful rate).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 44 of its 49 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

44 of 49 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  7. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  8. 2018On Evaluation of Embodied Navigation Agentscited by 547
  9. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  10. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  11. 2014Memory Networkscited by 363
  12. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 340
32 more
  1. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  2. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 302
  3. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  4. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  5. 2019Vision-and-Dialog Navigationcited by 250
  6. 2019Learning to Navigate Unseen Environments: Back Translation with Environmental Dropoutcited by 244
  7. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 233
  8. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 211
  9. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  10. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  11. 2021Episodic Transformer for Vision-and-Language Navigationcited by 156
  12. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 156
  13. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  14. 2019Stay on the Path: Instruction Fidelity in Vision-and-Language Navigationcited by 130
  15. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 129
  16. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 124
  17. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 122
  18. 2021Pathdreamer: A World Model for Indoor Navigationcited by 118
  19. 2025StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modelingcited by 118
  20. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 94
  21. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 89
  22. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  23. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  24. 2025MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigationcited by 60
  25. 2025NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environmentscited by 45
  26. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 43
  27. 2024Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigationcited by 39
  28. 2022Iterative Vision-and-Language Navigationcited by 35
  29. 2024g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Taskscited by 22
  30. 2025COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigationcited by 15
  31. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 7
  32. 2026CMMR-VLN: Vision-and-Language Navigation via Continual Multimodal Memory Retrievalcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System
  2. 2025Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
  3. 2026AdaGeoVLN: Selective Geometry Across Representation Depth and Navigation Time for Vision-Language Navigation ↗
  4. 2026HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
  5. 2026BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation
  6. 2026Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation
  7. 2026VTM-Nav: Harnessing Cross-Episode Experience for Object-Goal Navigation with Hierarchical Visual-Topological Memory
  8. 2026Nipping the Drift in the Bud: Retrospective Rectification for Robust Vision-Language Navigation