% Key papers for Pretraining and data augmentation for VLN (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2018_vision_13707,
  title = {{Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Anderson_Vision-and-Language_Navigation_Interpreting_CVPR_2018_paper.html},
}

@inproceedings{cvpr2019_reinforced_14724,
  title = {{Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2019_touchdown_14893,
  title = {{TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_reverie_16081,
  title = {{REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2020_towards_16363,
  title = {{Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2018_speaker_57640,
  title = {{Speaker-Follower Models for Vision-and-Language Navigation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11334},
}

@inproceedings{cvpr2020_neural_15947,
  title = {{Neural Topological SLAM for Visual Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2024_navgpt_6743,
  title = {{NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28597},
}

@inproceedings{cvpr2022_think_20021,
  title = {{Think Global, Act Local: Dual-Scale Graph Transformer for Vision-and-Language Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_simple_19883,
  title = {{Simple but Effective: CLIP Embeddings for Embodied AI}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2019_tactical_14894,
  title = {{Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{aaai2018_gated_102565,
  title = {{Gated-Attention Architectures for Task-Oriented Language Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11832},
}

@inproceedings{cvpr2019_vision_15007,
  title = {{Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2021_topological_18010,
  title = {{Topological Planning With Transformers for Vision-and-Language Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2021_room_17779,
  title = {{Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2022_cross_18550,
  title = {{Cross-Modal Map Learning for Vision and Language Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_zero_20238,
  title = {{Zero Experience Required: Plug \& Play Modular Transfer Learning for Semantic Visual Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2019_chasing_57993,
  title = {{Chasing Ghosts: Instruction Following as Bayesian State Tracking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13276},
}

@inproceedings{cvpr2022_less_19245,
  title = {{Less Is More: Generating Grounded Navigation Instructions From Landmarks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2021_scene_17830,
  title = {{Scene-Intuitive Agent for Remote Embodied Visual Grounding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{cvpr2024_vision_25242,
  title = {{Vision-and-Language Navigation via Causal Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30864},
}

@inproceedings{aaai2025_affordances_8068,
  title = {{Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34526},
}

@inproceedings{cvpr2024_goat_23553,
  title = {{GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31869},
}

@inproceedings{cvpr2024_over_24320,
  title = {{OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31340},
}

@inproceedings{aaai2025_enhancing_8975,
  title = {{Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33607},
}

@inproceedings{icml2024_voronav_44544,
  title = {{VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33908},
}

@inproceedings{cvpr2024_rila_24566,
  title = {{RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29730},
}

@inproceedings{cvpr2024_dialoc_23170,
  title = {{DiaLoc: An Iterative Approach to Embodied Dialog Localization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31198},
}

@inproceedings{cvpr2025_do_25981,
  title = {{Do Visual Imaginations Improve Vision-and-Language Navigation Agents?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33224},
}

@inproceedings{cvpr2024_dual_23286,
  title = {{Dual-View Visual Contextualization for Web Navigation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31252},
}

@inproceedings{neurips2025_beliefmapnav_75352,
  title = {{BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=7AMriz7I3K},
}

@inproceedings{aaai2024_angle_5191,
  title = {{Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28906},
}

@inproceedings{aaai2025_flona_9209,
  title = {{FloNa: Floor Plan Guided Embodied Visual Navigation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33601},
}

@inproceedings{iclr2024_selective_35086,
  title = {{Selective Visual Representations Improve Convergence and Generalization for Embodied AI}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17987},
}

@inproceedings{aaai2026_monodream_104670,
  title = {{MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37974},
}

@inproceedings{aaai2026_panonav_106592,
  title = {{PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38899},
}

@inproceedings{cvpr2025_let_26773,
  title = {{Let Humanoids Hike! Integrative Skill Development on Complex Trails}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34565},
}

@inproceedings{iclr2024_end_34792,
  title = {{End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18282},
}

@inproceedings{neurips2025_aux_80032,
  title = {{Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=vNmWbINtwH},
}