mlsanityData to 7 Oct 2026

Robust Navigation with Language Pretraining and Stochastic Sampling

arXiv 1909.02244 ↗First posted 5 Sep 2019cs.CL cs.CV cs.LGcited by 77

Not on the map. Why?

Abstract (arXiv)

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report two simple but highly effective methods to address these challenges and lead to a new state-of-the-art performance. First, we adapt large-scale pretrained language models to learn text representations that generalize better to previously unseen instructions. Second, we propose a stochastic sampling scheme to reduce the considerable gap between the expert actions in training and sampled actions in test, so that the agent can learn to correct its own mistakes during long sequential action decoding. Combining the two techniques, we achieve a new state of the art on the Room-to-Room benchmark with 6% absolute gain over the previous best result (47% -> 53%) on the Success Rate weighted by Path Length metric.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 19; 2023: 16; 2024: 11; 2025: 8; 2026: 4.

77 papers.

Sort:

By area:

  1. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  2. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  3. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 268
  4. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 222
  5. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 201
  6. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 187
  7. 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
  8. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 129
  9. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 127
  10. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devicescited by 120
  11. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 116
  12. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Modelscited by 96
38 more
  1. 2024Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Modelscited by 79
  2. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  3. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  4. 2021Vision-Language Navigation with Random Environmental Mixupcited by 70
  5. 2022HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigationcited by 69
  6. 2022A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learningcited by 60
  7. 2021SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigationcited by 53
  8. 2021Neighbor-view Enhanced Model for Vision and Language Navigationcited by 50
  9. 2022Learning from Unlabeled 3D Environments for Vision-and-Language Navigationcited by 49
  10. 2021On the Evaluation of Vision-and-Language Navigation Instructionscited by 45
  11. 2022ADAPT: Vision-Language Navigation with Modality-Aligned Action Promptscited by 45
  12. 2023Lana: A Language-Capable Navigator for Instruction Following and Generationcited by 39
  13. 2021Diagnosing Vision-and-Language Navigation: What Really Matterscited by 36
  14. 2022Reinforced Structured State-Evolution for Vision-Language Navigationcited by 36
  15. 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 35
  16. 2021Vision-Language Navigation: A Survey and Taxonomycited by 33
  17. 2021Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Informationcited by 31
  18. 2021Core Challenges in Embodied Vision-Language Planningcited by 30
  19. 2023Distilling Internet-Scale Vision-Language Models into Embodied Agentscited by 30
  20. 2022One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestonescited by 26
  21. 2022Visual-Language Navigation Pretraining via Prompt-based Environmental Self-explorationcited by 25
  22. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
  23. 2023GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigationcited by 24
  24. 2022FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigationcited by 22
  25. 2023VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigationcited by 22
  26. 2021Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigationcited by 20
  27. 2021Curriculum Learning for Vision-and-Language Navigationcited by 18
  28. 2023Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Groundingcited by 18
  29. 2021Contrastive Instruction-Trajectory Learning for Vision-Language Navigationcited by 16
  30. 2024Correctable Landmark Discovery via Large Models for Vision-Language Navigationcited by 16
  31. 2024SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Expertscited by 16
  32. 2021Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigationcited by 15
  33. 2023MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigationcited by 11
  34. 2022CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representationscited by 10
  35. 2025Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environmentscited by 10
  36. 2023ESceme: Vision-and-Language Navigation with Episodic Scene Memorycited by 9
  37. 2021CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigationcited by 8
  38. 2023LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Followingcited by 8

50 most cited of 77 All 77 (JSON)