nielsr HF Staff commited on
Commit
78c394c
·
verified ·
1 Parent(s): 25ba3ad

Add robotics pipeline tag and improve metadata

Browse files

Hi! I'm Niels, part of the community science team at Hugging Face.

This pull request improves the model card for FAINT-Sim by:
- Adding the `pipeline_tag: robotics` to the metadata to improve discoverability.
- Adding relevant tags such as `visual-navigation` and `sim-to-real`.
- Including a direct link to the research paper on the Hugging Face Hub.
- Correcting the code block language identifiers for the usage examples.

These changes help researchers and developers find and use your work more effectively.

Files changed (1) hide show
  1. README.md +11 -4
README.md CHANGED
@@ -1,12 +1,19 @@
1
  ---
2
  license: cc-by-4.0
 
 
 
 
 
3
  ---
4
 
5
  # FAINT
6
 
7
  Fast, Appearance-Invariant Navigation Transformer (FAINT) is a learned policy for vision-based topological navigation.
8
 
9
- Please see the [Project Page](https://lasuomela.github.io/faint/) for more information.
 
 
10
 
11
  ## Model Details
12
 
@@ -25,7 +32,7 @@ See the main Github [repo](https://github.com/lasuomela/FAINT) for details, inpu
25
 
26
  Only dependency is Pytorch.
27
 
28
- ```bash
29
  import torch
30
  ckpt_path = 'FAINT-Sim/model_torchscript.pt'
31
  model = torch.jit.load(ckpt_path)
@@ -35,7 +42,7 @@ model = torch.jit.load(ckpt_path)
35
 
36
  Need to have the Faint library installed.
37
 
38
- ```bash
39
  import torch
40
  from faint.common.models.faint import FAINT
41
 
@@ -52,7 +59,7 @@ If you use FAINT in your research, please use the following BibTeX entry:
52
  ```bibtex
53
  @article{suomela2025synthetic,
54
  title={Synthetic vs. Real Training Data for Visual Navigation},
55
- author={Suomela, Lauri and Kuruppu Arachchige, Sasanka and Torres, German F. and Edelman, Harry and Kämäräinen, Joni-Kristian}
56
  journal={arXiv:2509.11791},
57
  year={2025}
58
  }
 
1
  ---
2
  license: cc-by-4.0
3
+ pipeline_tag: robotics
4
+ tags:
5
+ - visual-navigation
6
+ - sim-to-real
7
+ - topological-navigation
8
  ---
9
 
10
  # FAINT
11
 
12
  Fast, Appearance-Invariant Navigation Transformer (FAINT) is a learned policy for vision-based topological navigation.
13
 
14
+ This model is presented in the paper [Synthetic vs. Real Training Data for Visual Navigation](https://huggingface.co/papers/2509.11791).
15
+
16
+ [**Project Page**](https://lasuomela.github.io/faint/) | [**Code**](https://github.com/lasuomela/faint)
17
 
18
  ## Model Details
19
 
 
32
 
33
  Only dependency is Pytorch.
34
 
35
+ ```python
36
  import torch
37
  ckpt_path = 'FAINT-Sim/model_torchscript.pt'
38
  model = torch.jit.load(ckpt_path)
 
42
 
43
  Need to have the Faint library installed.
44
 
45
+ ```python
46
  import torch
47
  from faint.common.models.faint import FAINT
48
 
 
59
  ```bibtex
60
  @article{suomela2025synthetic,
61
  title={Synthetic vs. Real Training Data for Visual Navigation},
62
+ author={Suomela, Lauri and Kuruppu Arachchige, Sasanka and Torres, German F. and Edelman, Harry and Kämäräinen, Joni-Kristian},
63
  journal={arXiv:2509.11791},
64
  year={2025}
65
  }