Link model card to arXiv paper

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +15 -6
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
- license: apache-2.0
3
  base_model: Qwen/Qwen3-VL-4B-Instruct
4
- library_name: peft
5
- pipeline_tag: image-text-to-text
6
  language:
7
  - en
 
 
 
8
  tags:
9
  - remote-sensing
10
  - temporal-understanding
@@ -18,8 +18,9 @@ tags:
18
 
19
  **GeoChrono** is a multimodal large language model (MLLM) tailored for long-term remote sensing interpretation. Given an image sequence spanning multiple years and a text prompt, GeoChrono generates a response through spatio-temporal reasoning β€” tracing, memorizing, and reasoning about the long-term evolution of geographic entities.
20
 
21
- GeoChrono is introduced in the paper *GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing* (**accepted at ACM MM 2026** πŸ”₯), together with the **ChronoBench** benchmark and the **ChronoInstruct** instruction-tuning dataset.
22
 
 
23
  - πŸ“¦ **Code**: https://github.com/IntelliSensing/GeoChrono
24
  - πŸ“Š **Data (ChronoBench & ChronoInstruct)**: https://huggingface.co/datasets/Davidup1/GeoChrono-Data
25
 
@@ -76,8 +77,16 @@ This model is released under the **Apache License 2.0**. The base model Qwen3-VL
76
 
77
  ## Citation
78
 
79
- If you find GeoChrono useful, please cite our paper *GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing*. The BibTeX entry will be provided here once the arXiv preprint is released β€” stay tuned.
 
 
 
 
 
 
 
 
80
 
81
  ## Contact
82
 
83
- For questions or feedback, please open a discussion or contact **liyujie2003@bupt.edu.cn**.
 
1
  ---
 
2
  base_model: Qwen/Qwen3-VL-4B-Instruct
 
 
3
  language:
4
  - en
5
+ library_name: peft
6
+ license: apache-2.0
7
+ pipeline_tag: image-text-to-text
8
  tags:
9
  - remote-sensing
10
  - temporal-understanding
 
18
 
19
  **GeoChrono** is a multimodal large language model (MLLM) tailored for long-term remote sensing interpretation. Given an image sequence spanning multiple years and a text prompt, GeoChrono generates a response through spatio-temporal reasoning β€” tracing, memorizing, and reasoning about the long-term evolution of geographic entities.
20
 
21
+ GeoChrono is introduced in the paper [GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing](https://huggingface.co/papers/2607.15768) (**accepted at ACM MM 2026** πŸ”₯), together with the **ChronoBench** benchmark and the **ChronoInstruct** instruction-tuning dataset.
22
 
23
+ - πŸ“„ **Paper**: https://arxiv.org/abs/2607.15768
24
  - πŸ“¦ **Code**: https://github.com/IntelliSensing/GeoChrono
25
  - πŸ“Š **Data (ChronoBench & ChronoInstruct)**: https://huggingface.co/datasets/Davidup1/GeoChrono-Data
26
 
 
77
 
78
  ## Citation
79
 
80
+ If you find GeoChrono useful, please cite our paper:
81
+ ```bibtex
82
+ @article{geochrono2026,
83
+ title={GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing},
84
+ author={Yujie Li and others},
85
+ journal={arXiv preprint arXiv:2607.15768},
86
+ year={2026}
87
+ }
88
+ ```
89
 
90
  ## Contact
91
 
92
+ For questions or feedback, please open a discussion or contact **liyujie2003@bupt.edu.cn**.