Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -79,18 +79,6 @@ model-index:
|
|
| 79 |
> Guifeng Deng, Pan Wang, Jiquan Wang, Tao Li, Haiteng Jiang. "SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model." *In preparation.*
|
| 80 |
> This repository will be made public upon release of the preprint.
|
| 81 |
|
| 82 |
-
## Authors
|
| 83 |
-
|
| 84 |
-
| Name | Affiliation | ORCID |
|
| 85 |
-
|------|------------|-------|
|
| 86 |
-
| Guifeng Deng | Zhejiang University | [0009-0001-1940-7797](https://orcid.org/0009-0001-1940-7797) |
|
| 87 |
-
| Pan Wang | Wenzhou Medical University | [0009-0001-6664-6934](https://orcid.org/0009-0001-6664-6934) |
|
| 88 |
-
| Jiquan Wang | Zhejiang University | |
|
| 89 |
-
| Tao Li ✉ | Zhejiang University | [0000-0003-3831-901X](https://orcid.org/0000-0003-3831-901X) |
|
| 90 |
-
| Haiteng Jiang ✉ | Zhejiang University | [0000-0003-0739-8413](https://orcid.org/0000-0003-0739-8413) |
|
| 91 |
-
|
| 92 |
-
**Correspondence:** Tao Li (litaozjusc@zju.edu.cn) and Haiteng Jiang (h.jiang@zju.edu.cn)
|
| 93 |
-
|
| 94 |
## Overview
|
| 95 |
|
| 96 |
**SleepVLM-3B** is a rule-grounded vision-language model for explainable automated sleep staging from polysomnography (PSG) recordings. Unlike conventional black-box classifiers that output only a stage label, SleepVLM generates clinician-readable natural-language rationales citing specific AASM scoring rules for every 30-second epoch, making each staging decision auditable against the clinical standard.
|
|
|
|
| 79 |
> Guifeng Deng, Pan Wang, Jiquan Wang, Tao Li, Haiteng Jiang. "SleepVLM: Explainable and Rule-Grounded Sleep Staging via a Vision-Language Model." *In preparation.*
|
| 80 |
> This repository will be made public upon release of the preprint.
|
| 81 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
## Overview
|
| 83 |
|
| 84 |
**SleepVLM-3B** is a rule-grounded vision-language model for explainable automated sleep staging from polysomnography (PSG) recordings. Unlike conventional black-box classifiers that output only a stage label, SleepVLM generates clinician-readable natural-language rationales citing specific AASM scoring rules for every 30-second epoch, making each staging decision auditable against the clinical standard.
|