mlsanityData to 7 Oct 2026

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

arXiv 2507.05240 ↗First posted 7 Jul 2025cs.RO cs.CVcited by 107

On the map: Efficient LLM inference and serving → Visual token pruning in multimodal models

Abstract (arXiv)

Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, language and action inputs. The fast-streaming dialogue context facilitates responsive action generation through a sliding-window of multi-turn dialogues, while the slow-updating memory context compresses historical visual states using a 3D-aware token pruning strategy. With this slow-fast design, StreamVLN achieves real-time dialogues through KV cache reuse, supporting long video streams with bounded context size and inference cost. Experiments on VLN-CE benchmarks show state-of-the-art performance with low latency, ensuring robustness and efficiency in real-world deployment. The project page is: https://streamvln.github.io/.

Key facts. Cited by 107 papers in the map (data through 7 Oct 2026). Placed in Visual token pruning in multimodal models, one of 12 directions in Efficient LLM inference and serving. Builds on 46 of its 50 references that are in the map. First posted on arXiv 7 Jul 2025.

Builds on

46 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024PruneVid: Visual Token Pruning for Efficient Video Large Language Models20 Dec

Other references · 45

  1. 2024Qwen2.5 Technical Reportcited by 4,713
  2. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  3. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  4. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  5. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  6. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Modelscited by 539
  7. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 429
  8. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 401
  9. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  10. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 340
  11. 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 338
  12. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 274
33 more
  1. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 268
  2. 2019Learning to Navigate Unseen Environments: Back Translation with Environmental Dropoutcited by 241
  3. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 222
  4. 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Textcited by 208
  5. 20233D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignmentcited by 201
  6. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigationcited by 201
  7. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  8. 2022Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigationcited by 187
  9. 2023Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifierscited by 170
  10. 2024Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoningcited by 170
  11. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 165
  12. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 150
  13. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 146
  14. 2023Towards Learning a Generalist Model for Embodied Navigationcited by 135
  15. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 127
  16. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 126
  17. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 125
  18. 2023GridMM: Grid Memory Map for Vision-and-Language Navigationcited by 117
  19. 2020Topological Planning with Transformers for Vision-and-Language Navigationcited by 115
  20. 2023Scaling Data Generation in Vision-and-Language Navigationcited by 115
  21. 2023Discuss Before Moving: Visual Language Navigation via Multi-expert Discussionscited by 108
  22. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  23. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  24. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 87
  25. 2022Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigationcited by 86
  26. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 82
  27. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 80
  28. 2023Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skillcited by 75
  29. 2024Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigationcited by 63
  30. 2023A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Modelscited by 61
  31. 2024VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Modelcited by 55
  32. 2025MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigationcited by 55
  33. 2024Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigationcited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 89.

107 papers.

Sort:

By area:

  1. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 80
  2. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 42
  3. 2025StreamingTOM: Streaming Token Compression for Efficient Video Understandingcited by 41
  4. 2025CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Modelcited by 26
  5. 2026ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigationcited by 23
  6. 2025A Survey of Token Compression for Efficient Multimodal Large Language Modelscited by 22
  7. 2025AstraNav-World: World Model for Foresight Control and Consistencycited by 17
  8. 2025Towards Physically Executable 3D Gaussian for Embodied Navigationcited by 16
  9. 2025MonoDream: Monocular Vision-Language Navigation with Panoramic Dreamingcited by 15
  10. 2025MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robotscited by 15
  11. 2025NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Predictioncited by 15
  12. 2025ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigationcited by 11
38 more
  1. 2026VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memorycited by 10
  2. 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigationcited by 10
  3. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 10
  4. 2026Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation Systemcited by 10
  5. 2025Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Modelscited by 8
  6. 2026SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigationcited by 8
  7. 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environmentscited by 8
  8. 2026AgentVLN: Towards Agentic Vision-and-Language Navigationcited by 8
  9. 2026Dual-Anchoring: Addressing State Drift in Vision-Language Navigationcited by 7
  10. 2025VISTAv2: World Imagination for Indoor Vision-and-Language Navigationcited by 6
  11. 2026MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Drivingcited by 6
  12. 2026AwareVLN: Reasoning with Self-awareness for Vision-Language Navigationcited by 6
  13. 2026AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harnesscited by 6
  14. 2025D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigationcited by 5
  15. 2026textscNaVIDA: Vision-Language Navigation with Inverse Dynamics Augmentationcited by 5
  16. 2026LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigationcited by 5
  17. 2026PanoWorld: Towards Spatial Supersensing in 360^circ Panorama Worldcited by 5
  18. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 5
  19. 2026ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AIcited by 5
  20. 2026ABot-N1: Toward a General Visual Language Navigation Foundation Modelcited by 5
  21. 2026MapDream: Task-Driven Map Learning for Vision-Language Navigationcited by 4
  22. 2026FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigationcited by 4
  23. 2025MetricNet: Recovering Metric Scale in Generative Navigation Policiescited by 3
  24. 2025Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generationcited by 3
  25. 2026SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planningcited by 3
  26. 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Modelscited by 3
  27. 2026OpenFrontier: General Navigation with Visual-Language Grounded Frontierscited by 3
  28. 2026Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environmentscited by 3
  29. 2026Structured Observation Language for Efficient and Generalizable Vision-Language Navigationcited by 3
  30. 2026Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulationcited by 3
  31. 2026Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigationcited by 3
  32. 2026Robostral Navigatecited by 3
  33. 2026HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harnesscited by 3
  34. 2025NavSpace: How Navigation Agents Follow Spatial Intelligence Instructionscited by 2
  35. 2025UrbanVLA: A Vision-Language-Action Model for Urban Micromobilitycited by 2
  36. 2026PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representationcited by 2
  37. 2026Does Peer Observation Help? Vision-Sharing Collaboration for Vision-Language Navigationcited by 2
  38. 2026STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understandingcited by 2

50 most cited of 107 All 107 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning
  2. 2026NavJev: Efficient Vision-Language Navigation via Action-Centric Visual Compression and Discriminative Action-Semantic Memory
  3. 2026VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness
  4. 2026StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation
  5. 2025A Navigation Framework Utilizing Vision-Language Models
  6. 2026Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation ↗
  7. 2026SFCo-Nav: Efficient Zero-Shot Visual Language Navigation via Collaboration of Slow LLM and Fast Attributed Graph Alignment
  8. 2025VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents