mlsanityData to 14 Oct 2026

Query, Align, and Distill: Navigation-Aware Cross-Modal Interaction for Efficient Vision-and-Language Navigation

arXiv 2609.33097 ↗First posted 27 Sep 2026cs.CV cs.AI cs.ROcited by 0

On the map: Knowledge distillation → Multimodal distillation

Abstract (arXiv)

Recent large-scale Vision-and-Language Navigation (VLN) models deliver strong accuracy but remain costly to deploy due to their large parameter counts and computational requirements. We tackle efficient VLN in two steps. First, we build a high-performing teacher that makes navigation evidence selection explicit and compressible. The teacher introduces a small set of learnable query slots to extract global and local action-sufficient navigable evidence from panoramic observations via a Navigable Query Generator, then progressively grounds these evidence tokens to the instruction with an Instruction-Query Aligner for policy prediction. Second, using this explicit query bottleneck as a distillation interface, we train a compact student by transferring both where to attend and what to do. We distill the teacher's global and local navigable queries with a navigation-aware token-adaptive objective, then further match action distributions during fine-tuning. Experiments on standard VLN benchmarks demonstrate that our student nearly matches the teacher's navigation performance while reducing the number of parameters by 93.65% compared to the teacher.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal distillation, one of 12 directions in Knowledge distillation. Builds on 48 of its 63 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

48 of 63 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation27 Sep
  2. 2024MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation25 Jun

Other references · 46

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  4. 2020Object-Centric Learning with Slot Attentioncited by 876
  5. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  6. 2019Selective Kernel Networkscited by 403
  7. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 340
  8. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  9. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 305
  10. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 302
  11. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  12. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
34 more
  1. 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
  2. 2020Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingcited by 231
  3. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  4. 2019Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Taskscited by 179
  5. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 130
  6. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 124
  7. 2022BEVBert: Multimodal Map Pre-training for Language-guided Navigationcited by 122
  8. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  9. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 117
  10. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Modelscited by 98
  11. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  12. 2022EnvEdit: Environment Editing for Vision-and-Language Navigationcited by 83
  13. 2021Less is More: Generating Grounded Navigation Instructions from Landmarkscited by 64
  14. 2024Volumetric Environment Representation for Vision-Language Navigationcited by 63
  15. 2022A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learningcited by 60
  16. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  17. 2021Scene-Intuitive Agent for Remote Embodied Visual Groundingcited by 49
  18. 2022ADAPT: Vision-Language Navigation with Modality-Aligned Action Promptscited by 45
  19. 2023KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigationcited by 39
  20. 2021Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Informationcited by 31
  21. 2023GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigationcited by 24
  22. 2023VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigationcited by 23
  23. 2020Language-guided Navigation via Cross-Modal Grounding and Alternate Adversarial Learningcited by 22
  24. 2021Distilled Dual-Encoder Model for Vision-Language Understandingcited by 22
  25. 2023A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigationcited by 18
  26. 2024Correctable Landmark Discovery via Large Models for Vision-Language Navigationcited by 17
  27. 2025Do Visual Imaginations Improve Vision-and-Language Navigation Agents?cited by 14
  28. 2025FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graphcited by 11
  29. 2022CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representationscited by 10
  30. 2024DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learningcited by 7
  31. 2025NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigationcited by 6
  32. 2025NavComposer: Composing Language Instructions for Navigation Trajectories through Action-Scene-Object Modularizationcited by 5
  33. 2025Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigationcited by 4
  34. 2022Local Slot Attention for Vision-and-Language Navigationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
  2. 2025Harnessing Input-Adaptive Inference for Efficient VLN
  3. 2026Learning to Retrieve Navigable Candidates for Efficient Vision-and-Language Navigation
  4. 2023Discuss Before Moving: Visual Language Navigation via Multi-expert Discussions
  5. 2025Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning
  6. 2026VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions
  7. 2024MC-GPT: Empowering Vision-and-Language Navigation with Memory Map and Reasoning Chains
  8. 2025A Navigation Framework Utilizing Vision-Language Models