Image-Text-to-Text
PEFT
Safetensors
English
remote-sensing
temporal-understanding
multimodal
lora
earth-observation
qwen3-vl
conversational
Instructions to use Davidup1/GeoChrono with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Davidup1/GeoChrono with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") model = PeftModel.from_pretrained(base_model, "Davidup1/GeoChrono") - Notebooks
- Google Colab
- Kaggle
Link model card to arXiv paper
#1
by nielsr HF Staff - opened
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
|
| 22 |
|
|
|
|
| 23 |
- π¦ **Code**: https://github.com/IntelliSensing/GeoChrono
|
| 24 |
- π **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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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** π₯), together with the **ChronoBench** benchmark and the **ChronoInstruct** instruction-tuning dataset.
|
| 22 |
|
| 23 |
+
- π **Paper**: https://arxiv.org/abs/2607.15768
|
| 24 |
- π¦ **Code**: https://github.com/IntelliSensing/GeoChrono
|
| 25 |
- π **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**.
|