Add pipeline tag and improve model card

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+pipeline_tag: other
 tags:
 - neuroscience
 - brain-to-text
@@ -9,24 +10,49 @@ tags:
 - brain foundation models
 ---
 
-# MEG-XL
+# MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
 
-Model weights for the paper "MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training".
+MEG-XL is a brain-to-text foundation model pre-trained with 2.5 minutes of MEG context per sample (equivalent to 191k tokens). It is designed to capture extended neural context, enabling high data efficiency for decoding words from brain activity.
 
-Use the checkpoint file alongside the code. Instructions for usage are in the GitHub repository.
+- **Paper:** [MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training](https://huggingface.co/papers/2602.02494)
+- **Repository:** [GitHub - neural-processing-lab/MEG-XL](https://github.com/neural-processing-lab/MEG-XL)
+- **Weights/Checkpoint:** [meg-xl-med.ckpt](https://huggingface.co/pnpl/MEG-XL/blob/main/meg-xl-med.ckpt)
 
-Weights/Checkpoint: [[HuggingFace]](https://huggingface.co/pnpl/MEG-XL/blob/main/meg-xl-med.ckpt)
+## Usage
 
-Code: [[GitHub Repository]](https://github.com/neural-processing-lab/MEG-XL)
+Instructions for environment setup, tokenizer (BioCodec) requirements, and data preparation are available in the [official GitHub repository](https://github.com/neural-processing-lab/MEG-XL).
 
-Paper: [[arXiv]](https://arxiv.org/abs/2602.02494)
+### Fine-tuning MEG-XL for Brain-to-Text
+You can fine-tune or evaluate the model on word decoding tasks using the following command structure:
 
-If you find this work helpful in your research, please cite:
+```bash
+python -m brainstorm.evaluate_criss_cross_word_classification \
+    --config-name=eval_criss_cross_word_classification_{armeni, gwilliams, libribrain} \
+    model.criss_cross_checkpoint=/path/to/your/checkpoint.ckpt
 ```
+
+### Linear Probing
+To perform linear probing, use:
+
+```bash
+python -m brainstorm.evaluate_criss_cross_word_classification \
+    --config-name=eval_criss_cross_word_classification_linear_probe_{armeni, gwilliams, libribrain} \
+    model.criss_cross_checkpoint=/path/to/your/checkpoint.ckpt
+```
+
+## Requirements
+- Python >= 3.12
+- High-VRAM GPU (>= 40-80GiB depending on the task).
+- Access to the [BioCodec](https://arxiv.org/abs/2510.09095) tokenizer code and weights.
+
+## Citation
+
+If you find this work helpful in your research, please cite:
+```bibtex
 @article{jayalath2026megxl,
   title={{MEG-XL}: Data-Efficient Brain-to-Text via Long-Context Pre-Training},
   author={Jayalath, Dulhan and Jones, Oiwi Parker},
   journal={arXiv preprint arXiv:2602.02494},
   year={2026}
 }
-```
+```