mlsanityData to 14 Oct 2026

Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

arXiv 2607.23181 ↗First posted 25 Jul 2026cs.CVcited by 0

On the map: World models → World models for navigation

Abstract (arXiv)

Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening generalization and increasing computational burden. We propose BrainNav, a navigation framework grounded in the Principle of Minimal Sufficiency. BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception to suppress environmental noise, a Minimalist Constraint Alignment module that serves as a compact cross-modal bottleneck, efficiently synchronizing discrete linguistic intent with continuous latent dynamics while filtering out redundant information, and a Compression World Model that predicts action-conditioned states within a condensed, low-rank latent space. These modules align semantic intent with spatial perception, enhancing the agent's robustness and efficiency in complex tasks. Experiments show that BrainNav improves over prior SOTA by 2.0 % / 1.0 in SR/SPL on R2R-CE val-unseen and 0.94 % / 0.78 on RxR-CE val-unseen. These results indicate that minimally sufficient world representations provide an effective foundation for robust VLN.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for navigation, one of 11 directions in World models. Builds on 56 of its 62 references that are in the map. First posted on arXiv 25 Jul 2026.

Builds on

56 of 62 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction1 Dec
  2. 2025NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments30 Jun
  3. 2024Navigation World Models4 Dec
  4. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation14 Aug
  5. 2021Pathdreamer: A World Model for Indoor Navigation18 May

Other references · 51

  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. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  4. 2024Qwen2.5 Technical Reportcited by 4,942
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  6. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  7. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  8. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  9. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  10. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  11. 2016Deep Variational Information Bottleneckcited by 930
  12. 2020Object-Centric Learning with Slot Attentioncited by 876
38 more
  1. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 629
  2. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  3. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  4. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  5. 2015Tensorizing Neural Networkscited by 250
  6. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 233
  7. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  8. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
  9. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 156
  10. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  11. 2025AdaWorld: Learning Adaptable World Models with Latent Actionscited by 114
  12. 2019General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warpingcited by 105
  13. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 94
  14. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  15. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  16. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  17. 2024Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Methodcited by 67
  18. 2024Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigationcited by 65
  19. 2024Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigationcited by 65
  20. 2025VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuningcited by 63
  21. 2018Compressing Neural Networks using the Variational Information Bottleneckcited by 59
  22. 2024A Survey on Robotics with Foundation Models: toward Embodied AIcited by 56
  23. 2022Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Modelscited by 53
  24. 20221st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)cited by 34
  25. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
  26. 2024Learning Latent Dynamic Robust Representations for World Modelscited by 21
  27. 2025Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigationcited by 17
  28. 2025DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigationcited by 17
  29. 2025COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigationcited by 15
  30. 2025Do Visual Imaginations Improve Vision-and-Language Navigation Agents?cited by 14
  31. 2025Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulationcited by 10
  32. 2018Learning Sparse Latent Representations with the Deep Copula Information Bottleneckcited by 9
  33. 2026Factored Latent Action World Modelscited by 7
  34. 2021Hamiltonian latent operators for content and motion disentanglement in image sequencescited by 5
  35. 2026MapDream: Task-Driven Map Learning for Vision-Language Navigationcited by 4
  36. 20263D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigationcited by 4
  37. 2026Structured Observation Language for Efficient and Generalizable Vision-Language Navigationcited by 3
  38. 2018Attention-Based Guided Structured Sparsity of Deep Neural Networkscited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentVLN: Towards Agentic Vision-and-Language Navigation
  2. 2026What Limits Vision-and-Language Navigation ?
  3. 2026HaltNav: Reactive Visual Halting over Lightweight Topological Priors for Robust Vision-Language Navigation
  4. 2025MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation
  5. 2025A Navigation Framework Utilizing Vision-Language Models
  6. 2026SparseNav: Instruction-conditioned Sparse Semantic Perception for Training-Free Vision-Language Navigation
  7. 2026C2Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation
  8. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation