mlsanityData to 14 Oct 2026

VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning

arXiv 2506.17221 ↗First posted 20 Jun 2025cs.CVcited by 63

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions. Current language model-based navigation systems operate on discrete topological graphs, limiting path planning to predefined node connections. We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions, adopting GRPO-based training inspired by DeepSeek-R1. To enable effective training, we first construct the VLN-Ego dataset using a 3D simulator, Habitat, and propose Long-Short Memory Sampling to balance historical and current observations. While large language models can supervise complete textual instructions, they lack fine-grained action-level control. Our framework employs a two-stage training approach: a) Supervised fine-tuning (SFT) to align the model's action sequence text predictions with expert demonstrations, followed by b) Reinforcement fine-tuning (RFT) enhanced with a Time-Decayed Reward (TDR) mechanism that strategically weights multi-step future actions. Experimental results show VLN-R1 achieves strong performance on VLN-CE benchmark. VLN-R1 proves LVLMs can drive embodied navigation and enhance task-specific reasoning through data-efficient, reward-driven post-training.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). Builds on 58 of its 63 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

58 of 63 references.

References · 58

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  8. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  10. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  11. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  12. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
38 more
  1. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  2. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  3. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  4. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  5. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  6. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  7. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  8. 2018On Evaluation of Embodied Navigation Agentscited by 547
  9. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  10. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  11. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  12. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 412
  13. 2022Visual Language Maps for Robot Navigationcited by 365
  14. 2024Skywork-Reward: Bag of Tricks for Reward Modeling in LLMscited by 327
  15. 2023NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Modelscited by 280
  16. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  17. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigationcited by 233
  18. 2020Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-trainingcited by 231
  19. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 228
  20. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 225
  21. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 198
  22. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  23. 2020Improving Vision-and-Language Navigation with Image-Text Pairs from the Webcited by 177
  24. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  25. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Taskscited by 156
  26. 2023Towards Learning a Generalist Model for Embodied Navigationcited by 138
  27. 2022Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigationcited by 132
  28. 2021Airbert: In-domain Pretraining for Vision-and-Language Navigationcited by 130
  29. 2021Waypoint Models for Instruction-guided Navigation in Continuous Environmentscited by 129
  30. 2020Topological Planning with Transformers for Vision-and-Language Navigationcited by 116
  31. 2023Discuss Before Moving: Visual Language Navigation via Multi-expert Discussionscited by 110
  32. 2021Core Challenges of Social Robot Navigation: A Surveycited by 106
  33. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Modelscited by 98
  34. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 94
  35. 2022Cross-modal Map Learning for Vision and Language Navigationcited by 91
  36. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 86
  37. 2022Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigationcited by 86
  38. 2024o1-Coder: an o1 Replication for Codingcited by 78

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 22; 2026: 41.

63 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecyclecited by 35
  3. 2025Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Modelscited by 33
  4. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  5. 2025DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigationcited by 17
  6. 2025Towards Physically Executable 3D Gaussian for Embodied Navigationcited by 17
  7. 2025MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robotscited by 15
  8. 2025Thinking in 360deg: Humanoid Visual Search in the Wildcited by 15
  9. 2025LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integrationcited by 14
  10. 2026WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigationcited by 14
  11. 2025ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigationcited by 13
  12. 2026Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Explorationcited by 13
38 more
  1. 2025STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligencecited by 11
  2. 2026VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memorycited by 10
  3. 2026AwareVLN: Reasoning with Self-awareness for Vision-Language Navigationcited by 10
  4. 2025Reinforcement Learning for Large Model: A Surveycited by 9
  5. 2025Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Modelscited by 8
  6. 2025Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoningcited by 8
  7. 2026PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learningcited by 7
  8. 2026SeeUPO: Sequence-Level Agentic-RL with Convergence Guaranteescited by 6
  9. 2026Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigationcited by 6
  10. 2025SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuningcited by 5
  11. 2026Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsingcited by 5
  12. 2026CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Modelscited by 5
  13. 2026Watch, Remember, Reason: Human-View Video Understanding with MLLMscited by 4
  14. 2025UrbanVLA: A Vision-Language-Action Model for Urban Micromobilitycited by 3
  15. 2025SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimizationcited by 3
  16. 2026Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environmentscited by 3
  17. 2026World Models as Group Actionscited by 3
  18. 2025P3: Toward Versatile Embodied Agentscited by 2
  19. 2025Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical Worldcited by 2
  20. 2025IRPO: Boosting Image Restoration via Post-training GRPOcited by 2
  21. 2026Think before Go: Hierarchical Reasoning for Image-goal Navigationcited by 2
  22. 2026SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigationcited by 2
  23. 2026Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigationcited by 2
  24. 2026OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agentscited by 2
  25. 2025MUVLA: Learning to Explore Object Navigation via Map Understandingcited by 1
  26. 2025PIGEON: VLM-Driven Object Navigation via Points of Interest Selectioncited by 1
  27. 2026MA-CoNav: A Master-Slave Multi-Agent Framework with Hierarchical Collaboration and Dual-Level Reflection for Long-Horizon Embodied VLNcited by 1
  28. 20263D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understandingcited by 1
  29. 2026FreeFly-Thinking : Aligning Chain-of-Thought Reasoning with Continuous UAV Navigationcited by 1
  30. 2026Mind over Space: Can Multimodal Large Language Models Mentally Navigate?cited by 1
  31. 2026Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigationcited by 1
  32. 2026Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoningcited by 1
  33. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
  34. 2026VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Methodcited by 1
  35. 2026Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigationcited by 1
  36. 2026LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigationcited by 1
  37. 2026VerNav: Verifier-First Low-Latency Vision-and-Language Navigationcited by 1
  38. 2026MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Controlcited by 1

50 most cited of 63 All 63 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
  2. 2025A Navigation Framework Utilizing Vision-Language Models
  3. 2025Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
  4. 2026AgentVLN: Towards Agentic Vision-and-Language Navigation
  5. 2025Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigation
  6. 2025FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks
  7. 2026PGN: Design and Implementation of a Vision-Language Navigation System Based on Pangu Multimodal Foundation Model
  8. 2026Nipping the Drift in the Bud: Retrospective Rectification for Robust Vision-Language Navigation