mlsanityData to 14 Oct 2026

Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation

arXiv 2512.08186 ↗First posted 9 Dec 2025cs.ROcited by 62

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

While recent large vision-language models (VLMs) have improved generalization in vision-language navigation (VLN), existing methods typically rely on end-to-end pipelines that map vision-language inputs directly to short-horizon discrete actions. Such designs often produce fragmented motions, incur high latency, and struggle with real-world challenges like dynamic obstacle avoidance. We propose DualVLN, the first dual-system VLN foundation model that synergistically integrates high-level reasoning with low-level action execution. System 2, a VLM-based global planner, "grounds slowly" by predicting mid-term waypoint goals via image-grounded reasoning. System 1, a lightweight, multi-modal conditioning Diffusion Transformer policy, "moves fast" by leveraging both explicit pixel goals and latent features from System 2 to generate smooth and accurate trajectories. The dual-system design enables robust real-time control and adaptive local decision-making in complex, dynamic environments. By decoupling training, the VLM retains its generalization, while System 1 achieves interpretable and effective local navigation. DualVLN outperforms prior methods across all VLN benchmarks and real-world experiments demonstrate robust long-horizon planning and real-time adaptability in dynamic environments.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. First posted on arXiv 9 Dec 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 60.

62 papers.

Sort:

By area:

  1. 2026ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigationcited by 25
  2. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 11
  3. 2026Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation Systemcited by 11
  4. 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environmentscited by 10
  5. 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigationcited by 10
  6. 2026AgentVLN: Towards Agentic Vision-and-Language Navigationcited by 9
  7. 2026Hy-Embodied-VLM-1.0: Efficient Physical-World Agentscited by 8
  8. 2026Dual-Anchoring: Addressing State Drift in Vision-Language Navigationcited by 7
  9. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 7
  10. 2025LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometrycited by 6
  11. 2026ABot-N1: Toward a General Visual Language Navigation Foundation Modelcited by 6
  12. 2026World-Action Models for Robot Learning and Control: A Surveycited by 6
38 more
  1. 2026Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulationcited by 5
  2. 2026Structured Observation Language for Efficient and Generalizable Vision-Language Navigationcited by 3
  3. 2026Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigationcited by 3
  4. 2026Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigationcited by 3
  5. 2026SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoningcited by 3
  6. 2026Robostral Navigatecited by 3
  7. 2026HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harnesscited by 3
  8. 2025Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigationcited by 2
  9. 2026WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Modelscited by 2
  10. 2026POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigationcited by 2
  11. 2026Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigationcited by 2
  12. 2026LIME: Learning Intent-aware Camera Motion from Egocentric Videocited by 2
  13. 2026HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigationcited by 2
  14. 2026OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agentscited by 2
  15. 2026What Limits Vision-and-Language Navigation ?cited by 1
  16. 2026Image2Sim: Scaling Embodied Navigation via Generative Neural Simulatorcited by 1
  17. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
  18. 2026X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matchingcited by 1
  19. 2026SC2-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environmentscited by 1
  20. 2026Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigationcited by 1
  21. 2026LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigationcited by 1
  22. 2026TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Modelcited by 1
  23. 2026HaltNav: Reactive Visual Halting over Lightweight Topological Priors for Robust Vision-Language Navigationcited by 0
  24. 2026LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoningcited by 0
  25. 2026From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigationcited by 0
  26. 2026TopoExplore: Homology as an Exploration Signalcited by 0
  27. 2026Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generationcited by 0
  28. 2026Learning to Navigate with Minimal Parameters: Decomposing Visual Navigation Through Closed-Form Geometric Interfacescited by 0
  29. 2026ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoningcited by 0
  30. 2026Goal-oriented Navigation Instruction Generation with Tour Video Priorscited by 0
  31. 2026Decoupling Planning and Control for Instructable Agentscited by 0
  32. 2026One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypointscited by 0
  33. 2026AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigationcited by 0
  34. 2026Visual Cue Guided Video Planning for Generalizable Robot Navigationcited by 0
  35. 2026What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behaviorcited by 0
  36. 2026Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigationcited by 0
  37. 2026RECAST: Recasting Vision-Language Semantics into an Actionable Cost Map for Robot Navigationcited by 0
  38. 2026FINE: Future-Informed Navigation Encoding for Data-Efficient Vision-Language Navigationcited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
  2. 2026GroundingVLN: Reasoning and Acting with Grounding for Vision-Language Navigation
  3. 2026OpenFrontier: General Navigation with Visual-Language Grounded Frontiers
  4. 2026Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies
  5. 2020Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learning
  6. 2026FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation
  7. 2025VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation
  8. 2025CLASH: Collaborative Large-Small Hierarchical Framework for Continuous Vision-and-Language Navigation