mlsanityData to 7 Oct 2026

MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming

arXiv 2508.02549 ↗First posted 4 Aug 2025cs.CV cs.ROcited by 15

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Vision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results with monocular input, yet they still lag behind methods using panoramic RGB-D information. We present MonoDream, a lightweight VLA framework that enables monocular agents to learn a Unified Navigation Representation (UNR). This shared feature representation jointly aligns navigation-relevant visual semantics (e.g., global layout, depth, and future cues) and language-grounded action intent, enabling more reliable action prediction. MonoDream further introduces Latent Panoramic Dreaming (LPD) tasks to supervise the UNR, which train the model to predict latent features of panoramic RGB and depth observations at both current and future steps based on only monocular input. Experiments on multiple VLN benchmarks show that MonoDream consistently improves monocular navigation performance and significantly narrows the gap with panoramic-based agents.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 25 of its 36 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

25 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024NaVILA: Legged Robot Vision-Language-Action Model for Navigation5 Dec

Other references · 24

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  4. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  5. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 429
  6. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 401
  7. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  8. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  9. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 300
  10. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 268
  11. 2024NVILA: Efficient Frontier Visual Language Modelscited by 206
  12. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
12 more
  1. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 159
  2. 2025StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modelingcited by 107
  3. 2021Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environmentscited by 87
  4. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  5. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  6. 2023VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street Viewcited by 67
  7. 2025NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environmentscited by 41
  8. 2024Vision-Language Navigation with Energy-Based Policycited by 19
  9. 2025Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigationcited by 19
  10. 2020Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learningcited by 14
  11. 2024Reinforcement Learning with Generalizable Gaussian Splattingcited by 11
  12. 2024UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 12.

15 papers.

Sort:

By area:

  1. 2026DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variationcited by 9
  2. 2025Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoningcited by 7
  3. 2025D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigationcited by 5
  4. 2026textscNaVIDA: Vision-Language Navigation with Inverse Dynamics Augmentationcited by 5
  5. 2026FutureNav: Unified World-Action Modeling for Vision-and-Language Navigationcited by 5
  6. 2026MapDream: Task-Driven Map Learning for Vision-Language Navigationcited by 4
  7. 2025Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigationcited by 3
  8. 2026Structured Observation Language for Efficient and Generalizable Vision-Language Navigationcited by 3
  9. 2026Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigationcited by 1
  10. 2026HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memorycited by 1
  11. 2026World-Action Models for Robot Learning and Control: A Surveycited by 1
  12. 2026GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigationcited by 0
3 more
  1. 2026Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigationcited by 0
  2. 2026LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestrationcited by 0
  3. 2026PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation
  2. 2026AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness
  3. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
  4. 2026PGN: Design and Implementation of a Vision-Language Navigation System Based on Pangu Multimodal Foundation Model
  5. 2026WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
  6. 2025A Navigation Framework Utilizing Vision-Language Models
  7. 2025VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
  8. 2026AgentVLN: Towards Agentic Vision-and-Language Navigation