mlsanityData to 14 Oct 2026

FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation

arXiv 2606.22424 ↗First posted 21 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes. While Large Models (LMs) have advanced VLN-CE, their performance remains severely degraded by real-world visual corruptions, a critical yet underexplored domain constraint. We introduce Temporal Conditional Flow Decorruptor (FlowDec), a novel image restoration framework tailored for LM-based VLN-CE. FlowDec integrates a hybrid temporal conditioning strategy to align the generative flow path with historical context and employs action-centroid guided filtering to dynamically assess and integrate outputs. Extensive experiments demonstrate that FlowDec outperforms state-of-the-art decorruption methods in both navigation accuracy and generation latency. Our approach establishes a robust, efficient paradigm for resilient embodied navigation in unpredictable real-world conditions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 56 references that are in the map. First posted on arXiv 21 Jun 2026.

Builds on

45 of 56 references.

References · 45

  1. 2022Flow Matching for Generative Modelingcited by 5,702
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  6. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  7. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  8. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  9. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  10. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  11. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 611
  12. 2018On Evaluation of Embodied Navigation Agentscited by 547
33 more
  1. 2022Continual Test-Time Domain Adaptationcited by 525
  2. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  3. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  4. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  5. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  6. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  7. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  8. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  9. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  10. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  11. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 233
  12. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 211
  13. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 193
  14. 2023Flow Matching in Latent Spacecited by 160
  15. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  16. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 156
  17. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  18. 2019Variational Denoising Network: Toward Blind Noise Modeling and Removalcited by 117
  19. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Modelscited by 98
  20. 2020Sim-to-Real Transfer for Vision-and-Language Navigationcited by 89
  21. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 89
  22. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 86
  23. 2024MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigationcited by 86
  24. 2024Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Modelscited by 79
  25. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  26. 2022A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learningcited by 60
  27. 2023Learning Vision-and-Language Navigation from YouTube Videoscited by 47
  28. 2023LangNav: Language as a Perceptual Representation for Navigationcited by 47
  29. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
  30. 2025General Scene Adaptation for Vision-and-Language Navigationcited by 17
  31. 2024GDA: Generalized Diffusion for Robust Test-time Adaptationcited by 14
  32. 2024Analytic Continual Test-Time Adaptation for Multi-Modality Corruptioncited by 5
  33. 2024Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptationcited by 4

Built on by

Not cited yet.