thorir commited on
Commit
295dbf6
·
verified ·
1 Parent(s): 3b77d98

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +72 -2
README.md CHANGED
@@ -2,11 +2,74 @@
2
  license: cc-by-nd-4.0
3
  language:
4
  - en
 
5
  tags:
6
- - foundation-model
7
- - neuroscience
8
  - eeg
 
9
  - mamba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
  <div align="center">
12
  <img src="https://raw.githubusercontent.com/danaebroustail/BioFoundation_Danae/refs/heads/lumamba/docs/model/logo/LuMamba_logo.png" alt="LuMamba Logo" width="800"/>
@@ -192,7 +255,14 @@ If you use LuMamba, please cite:
192
  - **Issues & support:** please open a GitHub issue in the BioFoundation repository.
193
 
194
  ---
 
 
 
195
 
 
 
 
 
196
  ## 🗒️ Changelog
197
 
198
  - **v1.0:** Initial release of LuMamba model card with task-specific checkpoints and instructions.
 
2
  license: cc-by-nd-4.0
3
  language:
4
  - en
5
+ library_name: pytorch
6
  tags:
 
 
7
  - eeg
8
+ - biosignal
9
  - mamba
10
+ - state-space-model
11
+ - cross-attention
12
+ - foundation-model
13
+ - self-supervised
14
+ - masked-modeling
15
+ - lejepa
16
+ - topology-invariant
17
+ - neuroscience
18
+ datasets:
19
+ - TUEG
20
+ - TUAB
21
+ - APAVA
22
+ - TDBrain
23
+ metrics:
24
+ - balanced_accuracy
25
+ - roc_auc
26
+ - pr_auc
27
+ thumbnail: https://raw.githubusercontent.com/pulp-bio/BioFoundation/refs/heads/main/docs/model/logo/LuMamba_logo.png
28
+ model-index:
29
+ - name: LuMamba-Tiny
30
+ results:
31
+ - task:
32
+ type: time-series-classification
33
+ name: EEG Abnormality Detection
34
+ dataset:
35
+ type: TUAB
36
+ name: TUH EEG Abnormal Corpus (TUAB)
37
+ metrics:
38
+ - type: balanced_accuracy
39
+ value: 80.99
40
+ name: Balanced Accuracy (%)
41
+ - type: roc_auc
42
+ value: 0.883
43
+ name: AUROC
44
+ - type: pr_auc
45
+ value: 0.892
46
+ name: AUC-PR
47
+ - task:
48
+ type: time-series-classification
49
+ name: Alzheimer's Disease Detection
50
+ dataset:
51
+ type: APAVA
52
+ name: APAVA
53
+ metrics:
54
+ - type: roc_auc
55
+ value: 0.955
56
+ name: AUROC
57
+ - type: pr_auc
58
+ value: 0.970
59
+ name: AUC-PR
60
+ - task:
61
+ type: time-series-classification
62
+ name: Parkinson's Disease Detection
63
+ dataset:
64
+ type: TDBrain
65
+ name: TDBrain
66
+ metrics:
67
+ - type: roc_auc
68
+ value: 0.961
69
+ name: AUROC
70
+ - type: pr_auc
71
+ value: 0.960
72
+ name: AUC-PR
73
  ---
74
  <div align="center">
75
  <img src="https://raw.githubusercontent.com/danaebroustail/BioFoundation_Danae/refs/heads/lumamba/docs/model/logo/LuMamba_logo.png" alt="LuMamba Logo" width="800"/>
 
255
  - **Issues & support:** please open a GitHub issue in the BioFoundation repository.
256
 
257
  ---
258
+ ---
259
+
260
+ ## 🔗 Related Models
261
 
262
+ - **[LUNA](https://huggingface.co/PulpBio/LUNA)** — Transformer-based topology-agnostic EEG foundation model (NeurIPS 2025). Source of the channel-unification cross-attention module that LuMamba reuses.
263
+ - **[FEMBA](https://huggingface.co/PulpBio/FEMBA)** — Bidirectional Mamba foundation model for EEG. Source of the linear-complexity temporal backbone that LuMamba reuses.
264
+ - **[TinyMyo](https://huggingface.co/PulpBio/TinyMyo)** — Tiny foundation model for flexible EMG signal processing at the edge.
265
+ -
266
  ## 🗒️ Changelog
267
 
268
  - **v1.0:** Initial release of LuMamba model card with task-specific checkpoints and instructions.