---
title: "The Sonar Moment — paper by Zhang et al. (2026)"
description: "Unlike image geo-localization, audio geo-localization has had no systematic benchmark, mainly because geo-tagged… 29 references."
authors: ["Ruixing Zhang", "Zihan Liu", "Leilei Sun", "Tongyu Zhu", "Weifeng Lv"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1297/"
doi: "10.18653/v1/2026.findings-acl.1297"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-sonar-moment-audio-geo-localization/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-sonar-moment-audio-geo-localization/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/) / The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models

# The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models

**Authors:** Ruixing Zhang, [Zihan Liu](https://md.research.elamur.ai/free/en/authors/zihan-liu/), Leilei Sun, Tongyu Zhu and [Weifeng Lv](https://md.research.elamur.ai/free/en/authors/weifeng-lv/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1297/) · [PDF](https://aclanthology.org/2026.findings-acl.1297.pdf) · [DOI 10.18653/v1/2026.findings-acl.1297](https://doi.org/10.18653/v1/2026.findings-acl.1297) · [OpenAlex](https://openalex.org/W7166820955)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Unlike image geo-localization, audio geo-localization has had no systematic benchmark, mainly because geo-tagged recordings are scarce and there has been no way to tell which clips carry geographic signal. The authors built AGL1K from user-uploaded, geo-tagged recordings on the crowd-sourced Aporee platform, obtained in cooperation with its maintainers. Four acoustic filters remove poor-quality audio first. A new Audio Localizability score then ranks the remaining clips. It sums the durations of sound categories, weighted by their learned contribution: categories that help localization add to the score, and categories that obscure clues subtract from it. The final set has 1,444 clips from 72 countries. The authors tested 16 audio-language models (ALMs). Some geo-localization ability is already present, but closed-source systems clearly beat open-source ones, and spoken language is often the main cue. Analyses of reasoning traces, continent-level bias and error types point to three needs: finer perception, less regional skew, and better integration of multiple weak clues.

## Key points
- **AGL1K** spans six continents, with 1,444 recordings covering 72 nations and territories. Scenes include nature, animals, music, human-made sounds and speech. Code is on GitHub (Rising0321/AGL1K), and an interactive human-play demo runs on a HuggingFace Space.
- **Pre-filtering** uses RMS Energy, Spectral Flatness, Clipping Ratio and Acoustic Complexity.
- **Localizability scoring** combines several components:
  - EfficientAT audio tagging;
  - chain-of-thought contribution labels produced with Gemini 2.5 Pro;
  - location-error splits judged by three LLMs;
  - human verification.
- **Model comparison:** Gemini 3 Pro gives the most stable continent-level predictions. GPT-4o Audio makes broader cross-continent mistakes. Qwen3-Omni disproportionately predicts North America.
- **Error analysis:** the authors annotated 300 country-level errors into seven categories, including Bird Bias, Language Ambiguity, Over-Commitment and Label Misidentification. Gemini 3 Pro errs mostly through language ambiguity, GPT-4o Audio through educated guesses, and Mimo-Audio through label misidentification.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) — Research institute, Shanghai, China · 152 works · 13,166 citations
- [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 86 works · 9,097 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 493 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works · [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 519 works

## Cite

Cite as: Ruixing Zhang, Zihan Liu, Leilei Sun, Tongyu Zhu and Weifeng Lv. 2026. The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026sonar,
  title = {{The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models}},
  author = {Ruixing Zhang, Zihan Liu, Leilei Sun, Tongyu Zhu and Weifeng Lv},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1297},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1297}
}
```

- [← previous The SignBeach Dataset of Dutch Sign Language (NGT) signs](https://md.research.elamur.ai/free/en/papers/schiefner-2026-signbeach-dataset-dutch-sign-language/)
- [next → The Spectrum of Sentiment: Optimistic, Pessimistic, and Neutral Voices in Online Depression Discourse](https://md.research.elamur.ai/free/en/papers/tabusca-2026-spectrum-sentiment-optimistic-pessimistic-neutral/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/)

## References

29 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdelrahman Abouelenin, Atabak Ashfaq, Adam Atkinson, Hany Awadalla, Nguyen Bach, Jianmin Bao, Alon Benhaim, Martin Cai, Vishrav Chaudhary, Congcong Chen, and 1 others. 2025. [Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras](https://md.research.elamur.ai/free/en/papers/microsoft-2025-phi-4-mini-technical-report/). arXiv preprint arXiv:2503.…
2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
3. Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Adam Coates, Greg Diamos, Erich Elsen, Jesse H. Engel, Linxi Fan, Christopher Fougner, Awni Y. Hannun, Billy Jun, Tony Han, and 20 othe… — [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://md.research.elamur.ai/free/en/papers/amodei-2015-deep-speech-2-end-end/)
4. Vicente Vivanco Cepeda, Gaurav Kumar Nayak, and Mubarak Shah. 2023. Geoclip: Clip-inspired alignment between locations and images for effective worldwide geo-localization. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIP… [find](https://scholar.google.com/scholar?q=Vicente+Vivanco+Cepeda%2C+Gaurav+Kumar+Nayak%2C+and+Mubarak+Shah%2E+2023%2E+Geoclip%3A+Clip%2Dinspired+alignment+between+locations+and+images+for+effective+worldwide+geo%2Dlocalization%2E+In+Advances+in+Neural+Inform)
5. Mustafa Chasmai, Wuao Liu, Subhransu Maji, and Grant Van Horn. 2025. Audio geolocation: A natural sounds benchmark. CoRR, abs/2505.18726. — [arXiv:2505.18726](https://arxiv.org/abs/2505.18726) [find](https://scholar.google.com/scholar?q=Mustafa+Chasmai%2C+Wuao+Liu%2C+Subhransu+Maji%2C+and+Grant+Van+Horn%2E+2025%2E+Audio+geolocation%3A+A+natural+sounds+benchmark%2E+CoRR%2C+abs%2F2505%2E18726%2E+%E2%80%94+%5BarXiv%3A2505%2E18726%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E18726%29)
6. Brandon Clark, Alec Kerrigan, Parth Parag Kulkarni, Vicente Vivanco Cepeda, and Mubarak Shah. 2023. Where we are and what we’re looking at: Query based worldwide image geo-localization using hierarchies and scenes. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouv… [find](https://scholar.google.com/scholar?q=Brandon+Clark%2C+Alec+Kerrigan%2C+Parth+Parag+Kulkarni%2C+Vicente+Vivanco+Cepeda%2C+and+Mubarak+Shah%2E+2023%2E+Where+we+are+and+what+we%E2%80%99re+looking+at%3A+Query+based+worldwide+image+geo%2Dlocalization+using+hierarchi)
7. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, 26053 9 Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilit…](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/)
8. Jort F. Gemmeke, Daniel P. W. Ellis, Dylan Freedman, Aren Jansen, Wade Lawrence, R. Channing Moore, Manoj Plakal, and Marvin Ritter. 2017. Audio set: An ontology and human-labeled dataset for audio events. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017,… [find](https://scholar.google.com/scholar?q=Jort+F%2E+Gemmeke%2C+Daniel+P%2E+W%2E+Ellis%2C+Dylan+Freedman%2C+Aren+Jansen%2C+Wade+Lawrence%2C+R%2E+Channing+Moore%2C+Manoj+Plakal%2C+and+Marvin+Ritter%2E+2017%2E+Audio+set%3A+An+ontology+and+human%2Dlabeled+dataset+for+audio+ev)
9. Yuan Gong, Jin Yu, and James R. Glass. 2022. Vocalsound: A dataset for improving human vocal sounds recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022, pages 151–155. IEEE. [find](https://scholar.google.com/scholar?q=Yuan+Gong%2C+Jin+Yu%2C+and+James+R%2E+Glass%2E+2022%2E+Vocalsound%3A+A+dataset+for+improving+human+vocal+sounds+recognition%2E+In+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing%2C+ICASSP+202)
10. Google. 2025. Gemini 2.0 Flash: Model Card. Model card (technical report), Google. Model card published April 15, 2025. [find](https://scholar.google.com/scholar?q=Google%2E+2025%2E+Gemini+2%2E0+Flash%3A+Model+Card%2E+Model+card+%28technical+report%29%2C+Google%2E+Model+card+published+April+15%2C+2025%2E)
11. Google DeepMind. 2025. Gemini 3 Pro: Model Card. Model card (technical report), Google DeepMind. Model card published November 2025. [find](https://scholar.google.com/scholar?q=Google+DeepMind%2E+2025%2E+Gemini+3+Pro%3A+Model+Card%2E+Model+card+%28technical+report%29%2C+Google+DeepMind%2E+Model+card+published+November+2025%2E)
12. Xiao Han, Chen Zhu, Hengshu Zhu, and Xiangyu Zhao. 2025. Swarm intelligence in geo-localization: A multi-agent large vision-language model collaborative framework. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, KDD 2025, Toronto ON, Canada, August 3-7,… [find](https://scholar.google.com/scholar?q=Xiao+Han%2C+Chen+Zhu%2C+Hengshu+Zhu%2C+and+Xiangyu+Zhao%2E+2025%2E+Swarm+intelligence+in+geo%2Dlocalization%3A+A+multi%2Dagent+large+vision%2Dlanguage+model+collaborative+framework%2E+In+Proceedings+of+the+31st+ACM+SIGKD)
13. KimiTeam, Ding Ding, Zeqian Ju, Yichong Leng, Songxiang Liu, Tong Liu, Zeyu Shang, Kai Shen, Wei Song, Xu Tan, Heyi Tang, Zhengtao Wang, Chu Wei, Yifei Xin, Xinran Xu, Jianwei Yu, Yutao Zhang, Xinyu Zhou, Y. Charles, and 21 others. 2025. [Kimi-audio technical report](https://md.research.elamur.ai/free/en/papers/kimiteam-2025-kimi-audio-technical-report/). Preprint, arXiv:2504.18425.
14. Ling Li, Yu Ye, Bingchuan Jiang, and Wei Zeng. 2024. Georeasoner: Geo-localization with reasoning in street views using a large vision-language model. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. [find](https://scholar.google.com/scholar?q=Ling+Li%2C+Yu+Ye%2C+Bingchuan+Jiang%2C+and+Wei+Zeng%2E+2024%2E+Georeasoner%3A+Geo%2Dlocalization+with+reasoning+in+street+views+using+a+large+vision%2Dlanguage+model%2E+In+Forty%2Dfirst+International+Conference+on+Machin)
15. Zihan Liu, Zhikang Niu, Qiuyang Xiao, Zhisheng Zheng, Ruoqi Yuan, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Jianze Liang, Xie Chen, Leilei Sun, Dahua Lin, and Jiaqi Wang. 2025. Star-bench: Probing deep spatio-temporal reasoning as audio 4d intelligence. CoRR, abs/2510.24693. — [arXiv:2510.24693](https://arxiv.org/abs/2510.24693) [find](https://scholar.google.com/scholar?q=Zihan+Liu%2C+Zhikang+Niu%2C+Qiuyang+Xiao%2C+Zhisheng+Zheng%2C+Ruoqi+Yuan%2C+Yuhang+Zang%2C+Yuhang+Cao%2C+Xiaoyi+Dong%2C+Jianze+Liang%2C+Xie+Chen%2C+Leilei+Sun%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2025%2E+Star%2Dbench%3A+Probing+deep+sp)
16. Eric Müller-Budack, Kader Pustu-Iren, and Ralph Ewerth. 2018. Geolocation estimation of photos using a hierarchical model and scene classification. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XII, volume 11216 of Lecture Notes i… [find](https://scholar.google.com/scholar?q=Eric+M%C3%BCller%2DBudack%2C+Kader+Pustu%2DIren%2C+and+Ralph+Ewerth%2E+2018%2E+Geolocation+estimation+of+photos+using+a+hierarchical+model+and+scene+classification%2E+In+Computer+Vision+%2D+ECCV+2018+%2D+15th+European+Confe)
17. Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Xunying Liu, Junbo Zhang, and Jian Luan. 2025. MECAT: A multi-experts constructed benchmark for fine-grained audio understanding tasks. CoRR, abs/2507.23511. — [arXiv:2507.23511](https://arxiv.org/abs/2507.23511) [find](https://scholar.google.com/scholar?q=Yadong+Niu%2C+Tianzi+Wang%2C+Heinrich+Dinkel%2C+Xingwei+Sun%2C+Jiahao+Zhou%2C+Gang+Li%2C+Jizhong+Liu%2C+Xunying+Liu%2C+Junbo+Zhang%2C+and+Jian+Luan%2E+2025%2E+MECAT%3A+A+multi%2Dexperts+constructed+benchmark+for+fine%2Dgrained+a)
18. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. [Robust speech recognition via large-scale weak supervision](https://md.research.elamur.ai/free/en/papers/radford-2022-robust-speech-recognition-large-scale/). In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learn…
19. Krishna Regmi and Mubarak Shah. 2019. Bridging the domain gap for ground-to-aerial image matching. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pages 470–479. IEEE. [find](https://scholar.google.com/scholar?q=Krishna+Regmi+and+Mubarak+Shah%2E+2019%2E+Bridging+the+domain+gap+for+ground%2Dto%2Daerial+image+matching%2E+In+2019+IEEE%2FCVF+International+Conference+on+Computer+Vision%2C+ICCV+2019%2C+Seoul%2C+Korea+%28South%29%2C+Octobe)
20. Florian Schmid, Khaled Koutini, and Gerhard Widmer. 2023. Efficient large-scale audio tagging via transformer-to-cnn knowledge distillation. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023, pages 1–5. IEEE. [find](https://scholar.google.com/scholar?q=Florian+Schmid%2C+Khaled+Koutini%2C+and+Gerhard+Widmer%2E+2023%2E+Efficient+large%2Dscale+audio+tagging+via+transformer%2Dto%2Dcnn+knowledge+distillation%2E+In+IEEE+International+Conference+on+Acoustics%2C+Speech+and+S)
21. Paul Hongsuck Seo, Tobias Weyand, Jack Sim, and Bohyung Han. 2018. Cplanet: Enhancing image geolocalization by combinatorial partitioning of maps. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part X, volume 11214 of Lecture Notes in C… [find](https://scholar.google.com/scholar?q=Paul+Hongsuck+Seo%2C+Tobias+Weyand%2C+Jack+Sim%2C+and+Bohyung+Han%2E+2018%2E+Cplanet%3A+Enhancing+image+geolocalization+by+combinatorial+partitioning+of+maps%2E+In+Computer+Vision+%2D+ECCV+2018+%2D+15th+European+Confer)
22. Yujiao Shi, Liu Liu, Xin Yu, and Hongdong Li. 2019. Spatial-aware feature aggregation for image based cross-view geo-localization. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, B… [find](https://scholar.google.com/scholar?q=Yujiao+Shi%2C+Liu+Liu%2C+Xin+Yu%2C+and+Hongdong+Li%2E+2019%2E+Spatial%2Daware+feature+aggregation+for+image+based+cross%2Dview+geo%2Dlocalization%2E+In+Advances+in+Neural+Information+Processing+Systems+32%3A+Annual+Confe)
23. Yujiao Shi, Xin Yu, Dylan Campbell, and Hongdong Li. 2020. Where am I looking at? joint location and orientation estimation by cross-view matching. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pages 4063–4071. Computer Vision… [find](https://scholar.google.com/scholar?q=Yujiao+Shi%2C+Xin+Yu%2C+Dylan+Campbell%2C+and+Hongdong+Li%2E+2020%2E+Where+am+I+looking+at%3F+joint+location+and+orientation+estimation+by+cross%2Dview+matching%2E+In+2020+IEEE%2FCVF+Conference+on+Computer+Vision+and+P)
24. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, and 1 others. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+and+1+others%2E+2025%2E+Gemma+3+technical+rep)
25. Bin Wang, Xunlong Zou, Geyu Lin, Shuo Sun, Zhuohan Liu, Wenyu Zhang, Zhengyuan Liu, AiTi Aw, and Nancy F. Chen. 2025a. [Audiobench: A universal benchmark for audio large language models](https://md.research.elamur.ai/free/en/papers/wang-2025-audiobench-universal-benchmark-audio-large/). In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for 26054 10
26. Computational Linguistics: Human Language Technologies, NAACL 2025 - Volume 1: Long Papers, Albuquerque, New Mexico, USA, April 29 - May 4, 2025, pages 4297–4316. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Computational+Linguistics%3A+Human+Language+Technologies%2C+NAACL+2025+%2D+Volume+1%3A+Long+Papers%2C+Albuquerque%2C+New+Mexico%2C+USA%2C+April+29+%2D+May+4%2C+2025%2C+pages+4297%E2%80%934316%2E+Association+for+Computational+Linguis)
27. Chun Wang, Xiaoran Pan, Zihao Pan, Haofan Wang, and Yiren Song. 2025b. GRE suite: Geolocalization inference via fine-tuned vision-language models and enhanced reasoning chains. CoRR, abs/2505.18700. — [arXiv:2505.18700](https://arxiv.org/abs/2505.18700) [find](https://scholar.google.com/scholar?q=Chun+Wang%2C+Xiaoran+Pan%2C+Zihao+Pan%2C+Haofan+Wang%2C+and+Yiren+Song%2E+2025b%2E+GRE+suite%3A+Geolocalization+inference+via+fine%2Dtuned+vision%2Dlanguage+models+and+enhanced+reasoning+chains%2E+CoRR%2C+abs%2F2505%2E18700%2E+%E2%80%94)
28. Tobias Weyand, Ilya Kostrikov, and James Philbin. 2016. Planet - photo geolocation with convolutional neural networks. In Computer Vision - ECCV 2016 -14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII, volume 9912 of Lecture Notes in Computer Science,… [find](https://scholar.google.com/scholar?q=Tobias+Weyand%2C+Ilya+Kostrikov%2C+and+James+Philbin%2E+2016%2E+Planet+%2D+photo+geolocation+with+convolutional+neural+networks%2E+In+Computer+Vision+%2D+ECCV+2016+%2D14th+European+Conference%2C+Amsterdam%2C+The+Netherla)
29. LLM-Core-Team Xiaomi. 2025. [Mimo-audio: Audio language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/team-2025-llm-mimo-audio-audio-language/).

*Updated 2 November 2026*