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

• URL: http://arxiv.org/abs/2607.23181v1
• Date: Sat, 25 Jul 2026 12:26:47 GMT
• Title: Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation
• Abstract summary: BrainNav is a navigation framework grounded in the Principle of Minimal Sufficiency.<n>BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception, a Minimalist Constraint Alignment module, and a Compression World Model.<n> 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.
• Score: 32.00869718735648
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation [68.02899606570223]
  We propose TAMP-Nav, a unified framework for efficient embodied navigation.<n>First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual coordinates.<n>Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize)
  arXiv  Detail & Related papers  (2026-08-18T08:37:08Z)
• Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation [15.851694572297612]
  Vision-Language Navigation in Continuous Environments (VLN-CE) poses a formidable challenge for autonomous agents.<n>Existing approaches often falter in long-horizon tasks due to limited scene understanding, inefficient planning, and lack of robust decision-making frameworks.<n>We introduce the textbfHierarchical Semantic-Augmented Navigation (HSAN) framework, a groundbreaking approach that redefines VLN-CE through three synergistic innovations.
  arXiv  Detail & Related papers  (2026-06-01T02:11:01Z)
• What Limits Vision-and-Language Navigation ? [18.423144111320592]
  StereoNav is a robust Vision-Language-Action framework designed to enhance real-world navigation consistency.<n>Experiments on R2R-CE and RxR-CE demonstrate that StereoNav achieves state-of-the-art egocentric RGB performance.
  arXiv  Detail & Related papers  (2026-05-13T10:41:24Z)
• FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation [20.13280678867453]
  FineCog-Nav organizes navigation into fine-grained modules for language processing, perception, attention, memory, imagination, reasoning, and decision-making.<n>FineCog-Nav consistently outperforms zero-shot baselines in instruction adherence, long-horizon planning, and generalization to unseen environments.
  arXiv  Detail & Related papers  (2026-04-17T17:59:48Z)
• AgentVLN: Towards Agentic Vision-and-Language Navigation [78.739525400071]
  Vision-and-Language Navigation (VLN) requires an embodied agent to ground complex natural-language instructions into long-horizon navigation in unseen environments.<n>In this paper, we propose AgentVLN, a novel and efficient embodied navigation framework that can be deployed on edge computing platforms.
  arXiv  Detail & Related papers  (2026-03-18T12:43:47Z)
• AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control [20.1849703990752]
  Vision-Language Navigation (VLN) for Unmanned Aerial Vehicles (UAVs) demands complex visual interpretation and continuous control in 3D environments.<n>We propose AerialVLA, a minimalist end-to-end Vision-Language-Action framework mapping raw visual observations and fuzzy linguistic instructions directly to continuous physical control signals.
  arXiv  Detail & Related papers  (2026-03-15T13:02:13Z)
• One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation [18.529673835965745]
  A navigable agent needs to understand both high-level semantic instructions and precise spatial perceptions.<n>We propose a decoupled design that separates low-level spatial state estimation from high-level semantic planning.<n>We conduct comprehensive experiments in both simulated and real-world environments.
  arXiv  Detail & Related papers  (2026-02-17T07:13:48Z)
• AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild [62.47761809929869]
  Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations.<n>Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes.<n>We propose AutoFly, an end-to-end Vision-Language-Action model for autonomous UAV navigation.
  arXiv  Detail & Related papers  (2026-02-10T11:08:07Z)
• VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation [52.00474922315126]
  We present VLN-Zero, a vision-language navigation framework for unseen environments.<n>We use vision-language models to efficiently construct symbolic scene graphs and enable zero-shot neurosymbolic navigation.<n>VLN-Zero achieves 2x higher success rate compared to state-of-the-art zero-shot models, outperforms most fine-tuned baselines, and reaches goal locations in half the time.
  arXiv  Detail & Related papers  (2025-09-23T03:23:03Z)
• NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning [97.88246428240872]
  Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions.<n>Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability.<n>This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision.
  arXiv  Detail & Related papers  (2024-03-12T07:27:02Z)
• CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation [73.78984332354636]
  CorNav is a novel zero-shot framework for vision-and-language navigation. It incorporates environmental feedback for refining future plans and adjusting its actions. It consistently outperforms all baselines in a zero-shot multi-task setting.
  arXiv  Detail & Related papers  (2023-06-17T11:44:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.