VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation (VLN) which requires visual and natural language understanding as well as spatial and temporal reasoning capabilities. The embodied agent needs to ground its understanding of navigation instructions in observations of a real-world environment like Street View. Despite the impressive results of LLMs in other research areas, it is an ongoing problem of how to best connect them with an interactive visual environment. In this work, we propose VELMA, an embodied LLM agent that uses a verbalization of the trajectory and of visual environment observations as contextual prompt for the next action. Visual information is verbalized by a pipeline that extracts landmarks from the human written navigation instructions and uses CLIP to determine their visibility in the current panorama view. We show that VELMA is able to successfully follow navigation instructions in Street View with only two in-context examples. We further finetune the LLM agent on a few thousand examples and achieve around 25% relative improvement in task completion over the previous state-of-the-art for two datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
Ross, S., Gordon, G. J., & Bagnell, J. A. (2018) · Carnegie Mellon University · doi:10.1184/r1/6550949 · Cited by 1,941
Anderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., Sunderhauf, N., Reid, I., Gould, S., & van den Hengel, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00387 · Cited by 1,187
LAION-5B: An open large-scale dataset for training next generation image-text models
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.08402 · Cited by 1,022
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
Shridhar, M., Thomason, J., Gordon, D., Bisk, Y., Han, W., Mottaghi, R., Zettlemoyer, L., & Fox, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01075 · Cited by 540
Wang, X., Huang, Q., Celikyilmaz, A., Gao, J., Shen, D., Wang, Y.-F., Wang, W. Y., & Zhang, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00679 · Cited by 522
Self-citationREVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
Qi, Y., Wu, Q., Anderson, P., Wang, X., Wang, W. Y., Shen, C., & van den Hengel, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01000 · Cited by 331
Self-citationLearning to Navigate Unseen Environments: Back Translation with Environmental Dropout
Tan, H., Yu, L., & Bansal, M. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1268 · Cited by 293
Cited by
Liu, Y., Lo, S. K., Lu, Q., Zhu, L., Zhao, D., Xu, X., Harrer, S., & Whittle, J. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2024.112278 · Cited by 51
Evaluating the World Model Implicit in a Generative Model
Vafa, K., Chen, J., Rambachan, A., Kleinberg, J., & Mullainathan, S. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-0846 · Cited by 22
V-IRL: Grounding Virtual Intelligence in Real Life
Yang, J., Ding, R., Brown, E., Qi, X., & Xie, S. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72995-9_3 · Cited by 20
A knowledge-driven framework for Robotic Odor Source Localization using large language models
Mahmud, K. R., Wang, L., Hassan, S., & Zhang, Z. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.104915 · Cited by 10
Metadata
- Authors
- Schumann, R., Zhu, W., Feng, W., Fu, T.-J., Riezler, S., & Wang, W. Y.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2024-03-24
- Volume
- 38
- Issue
- 17
- Pages
- 18924-18933
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W4393160097
- Cited by
- 68
- References
- 18
- FWCI
- 14.19
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View. https://app.cochat.ai/papers/10.1609/aaai.v38i17.29858
- The paper
- Schumann, R., Zhu, W., Feng, W., Fu, T.-J., Riezler, S., & Wang, W. Y. (2024). VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.1609/aaai.v38i17.29858
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.