mlsanityData to 14 Oct 2026

DialNav: Multi-turn Dialog Navigation with a Remote Guide

arXiv 2509.12894 ↗First posted 16 Sep 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce DialNav, a novel collaborative embodied dialog task, where a navigation agent (Navigator) and a remote guide (Guide) engage in multi-turn dialog to reach a goal location. Unlike prior work, DialNav aims for holistic evaluation and requires the Guide to infer the Navigator's location, making communication essential for task success. To support this task, we collect and release the Remote Assistance in Navigation (RAIN) dataset, human-human dialog paired with navigation trajectories in photorealistic environments. We design a comprehensive benchmark to evaluate both navigation and dialog, and conduct extensive experiments analyzing the impact of different Navigator and Guide models. We highlight key challenges and publicly release the dataset, code, and evaluation framework to foster future research in embodied dialog.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

34 of 49 references.

References · 34

  1. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  2. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  3. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 340
  4. 2017Embodied Question Answeringcited by 336
  5. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  6. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  7. 2019Vision-and-Dialog Navigationcited by 250
  8. 2020Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingcited by 231
  9. 2021TEACh: Task-driven Embodied Agents that Chatcited by 197
  10. 2019Stay on the Path: Instruction Fidelity in Vision-and-Language Navigationcited by 130
  11. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  12. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 117
22 more
  1. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  2. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  3. 2019Executing Instructions in Situated Collaborative Interactionscited by 69
  4. 2021Less is More: Generating Grounded Navigation Instructions from Landmarkscited by 64
  5. 2022DialFRED: Dialogue-Enabled Agents for Embodied Instruction Followingcited by 63
  6. 2019Just Ask:An Interactive Learning Framework for Vision and Language Navigationcited by 53
  7. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 51
  8. 2022Learning from Unlabeled 3D Environments for Vision-and-Language Navigationcited by 50
  9. 2022Aerial Vision-and-Dialog Navigationcited by 49
  10. 2024TopViewRS: Vision-Language Models as Top-View Spatial Reasonerscited by 49
  11. 2018Talk the Walk: Navigating New York City through Grounded Dialoguecited by 44
  12. 2023Lana: A Language-Capable Navigator for Instruction Following and Generationcited by 40
  13. 2020RMM: A Recursive Mental Model for Dialog Navigationcited by 32
  14. 2020The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigationcited by 26
  15. 2020Where Are You? Localization from Embodied Dialogcited by 24
  16. 2020Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigationcited by 22
  17. 2022Ask4Help: Learning to Leverage an Expert for Embodied Taskscited by 18
  18. 2024InstruGen: Automatic Instruction Generation for Vision-and-Language Navigation Via Large Multimodal Modelscited by 6
  19. 2022Transformer-based Localization from Embodied Dialog with Large-scale Pre-trainingcited by 5
  20. 2023R2H: Building Multimodal Navigation Helpers that Respond to Help Requestscited by 5
  21. 2024DiaLoc: An Iterative Approach to Embodied Dialog Localizationcited by 4
  22. 2024The Wallpaper is Ugly: Indoor Localization using Vision and Languagecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigationcited by 3
  2. 2026Listen, Look, Drive: Coupling Audio Instructions for User-aware VLA-based Autonomous Drivingcited by 2
  3. 2026Goal-oriented Navigation Instruction Generation with Tour Video Priorscited by 0