mlsanityData to 14 Oct 2026

NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments

arXiv 2506.23468 ↗First posted 30 Jun 2025cs.CVcited by 45

On the map: World models → World models for navigation

Abstract (arXiv)

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions. Current approaches often struggle with generalizing to novel environments and adapting to ongoing changes during navigation. Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks. NavMorph employs compact latent representations to model environmental dynamics, equipping agents with foresight for adaptive planning and policy refinement. By integrating a novel Contextual Evolution Memory, NavMorph leverages scene-contextual information to support effective navigation while maintaining online adaptability. Extensive experiments demonstrate that our method achieves notable performance improvements on popular VLN-CE benchmarks. Code is available at https://github.com/Feliciaxyao/NavMorph.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Placed in World models for navigation, one of 11 directions in World models. Builds on 65 of its 83 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

65 of 83 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Navigation World Models4 Dec
  2. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation14 Aug
  3. 2021Pathdreamer: A World Model for Indoor Navigation18 May
  4. 2019Habitat: A Platform for Embodied AI Research2 Apr

Other references · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  6. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  8. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  9. 2023Mastering Diverse Domains through World Modelscited by 1,253
  10. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  11. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  12. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
38 more
  1. 2018On Evaluation of Embodied Navigation Agentscited by 547
  2. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  3. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  4. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  5. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  6. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  7. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 319
  8. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 279
  9. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  10. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 233
  11. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  12. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  13. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 151
  14. 2022Model-Based Imitation Learning for Urban Drivingcited by 150
  15. 2023EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AIcited by 147
  16. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  17. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 129
  18. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 124
  19. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 117
  20. 2020Topological Planning with Transformers for Vision-and-Language Navigationcited by 116
  21. 2019General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warpingcited by 105
  22. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 94
  23. 2024DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Drivingcited by 93
  24. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  25. 2020Sim-to-Real Transfer for Vision-and-Language Navigationcited by 89
  26. 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learningcited by 89
  27. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  28. 2022Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigationcited by 86
  29. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  30. 2024Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigationcited by 65
  31. 2024Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigationcited by 65
  32. 2023A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Modelscited by 62
  33. 2022A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learningcited by 60
  34. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  35. 2021SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environmentscited by 48
  36. 2023Improving Vision-and-Language Navigation by Generating Future-View Image Semanticscited by 46
  37. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 43
  38. 2024Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigationcited by 39

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 36.

45 papers.

Sort:

By area:

  1. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 89
  2. 2025A Comprehensive Survey on World Models for Embodied AIcited by 68
  3. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  4. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 36
  5. 2026MobileDreamer: Generative Sketch World Model for GUI Agentcited by 23
  6. 2025AstraNav-World: World Model for Foresight Control and Consistencycited by 17
  7. 2025MonoDream: Monocular Vision-Language Navigation with Panoramic Dreamingcited by 16
  8. 2025NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Predictioncited by 16
  9. 2025Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresightcited by 14
  10. 2025Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Spacecited by 12
  11. 2026Language-Conditioned World Modeling for Visual Navigationcited by 10
  12. 2026Dual-Anchoring: Addressing State Drift in Vision-Language Navigationcited by 7
33 more
  1. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 7
  2. 2026Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Modelcited by 6
  3. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  4. 2026textscNaVIDA: Vision-Language Navigation with Inverse Dynamics Augmentationcited by 5
  5. 2026NavWM: A Unified Navigation World Model for Foresight-Driven Planningcited by 5
  6. 2026MapDream: Task-Driven Map Learning for Vision-Language Navigationcited by 4
  7. 2025Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigationcited by 3
  8. 2026Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Modelcited by 3
  9. 2026PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representationcited by 3
  10. 2026Self-evolving Embodied AIcited by 2
  11. 2026WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Modelscited by 2
  12. 2026SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigationcited by 2
  13. 2026Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigationcited by 2
  14. 2026SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigationcited by 1
  15. 2026What Limits Vision-and-Language Navigation ?cited by 1
  16. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
  17. 2026SeeSE3: Emergence of 3D Space in Vision Featurescited by 1
  18. 2026From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigationcited by 1
  19. 2026Predicting Consequences and Reinforcing Navigation Policies with Latent World Modelscited by 1
  20. 2026LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoningcited by 0
  21. 2026Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigationcited by 0
  22. 2026CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigationcited by 0
  23. 2026Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generationcited by 0
  24. 2026ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoningcited by 0
  25. 2026Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigationcited by 0
  26. 2026Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamicscited by 0
  27. 2026Skytopia: Monocular Drone Navigation with Action-Conditioned Latent World Modelscited by 0
  28. 2026Where Should I Join? Robot Group Joining via Language-Guided Goal Predictioncited by 0
  29. 2026Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigationcited by 0
  30. 2026GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigationcited by 0
  31. 2026StageVLN: Spatial and Trajectory Auxiliary Guidance for Efficient Vision-Language Navigationcited by 0
  32. 2026GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidancecited by 0
  33. 2026MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models
  2. 2026SC2-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
  3. 2026AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
  4. 2026NavHarness: Towards Lifelong Embodied Navigation
  5. 2020Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
  6. 2026Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
  7. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models
  8. 2025A Navigation Framework Utilizing Vision-Language Models