Update README.md

README.md

@@ -1,4 +1,12 @@
 # T³: Test-Time Model Merging for Medical Vision-Language Models
+[Raza Imam](https://razaimam45.github.io/), Hu Wang, Dwarikanath Mahapatra, Mohammad Yaqub \
+Mohamed bin Zayed University of Artificial Intelligence
+
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+[![Paper](https://img.shields.io/badge/Paper-PDF-blue)](https://arxiv.org/abs/2510.27265)
+[![Weights](https://img.shields.io/badge/Model-MediMeta--C-yellow)](https://huggingface.co/razaimam45/TCube_Merging)
+
+This repository provides the official PyTorch implementation of our T³ Medical Model-Merging paper:    
 
 ![T³ Workflow](figures/method.png)  
 *Figure 1: Dynamic test-time merging workflow of T³*
@@ -22,13 +30,14 @@ Official implementation of **T³: Test-Time Model Merging in Vision-Language Mod
 - [Folder Structure](#folder-structure)
 - [Reproducing Results](#reproducing-results)
 - [Pretrained Weights](#pretrained-weights)
+- [Datasets](#datasets)
 - [Citation](#citation)
 
 ## Installation
 
 1. Clone repository:
 ```bash
-git clone https://github.com/yourusername/T3.git
+git clone https://github.com/Razaimam45/TCube.git
 cd T3
 ```
 
@@ -91,12 +100,14 @@ Empirically, \(I(x)\) correlates positively with \(R(x)\), but better distinguis
 ---
 
 ## Folder Structure
-
+Do check our [HuggingFace page](https://huggingface.co/razaimam45/TCube_Merging) for Expert Models and Evaluation Datasets.
 ```
 T3/
 ├── clip/              # CLIP model adaptations
 ├── data/              # Data Utilities
 ├── utils/             # Helper functions
+├── models/            # Put your finetuned models HERE
+├── dataset/           # Put your medimeta/medmnist-c eval data HERE
 ├── baselines.py       # Comparison methods
 ├── t_cube.py          # Core T³ implementation
 ├── BetaMixture.py     # Auxiliary models
@@ -109,7 +120,7 @@ T3/
 
 To reproduce the results from the paper, you can run the `t_cube.py` script. This script handles the evaluation of T³ and its baselines across multiple datasets and severity levels. Additional baselines are available in `baselines.py`.
 
-To understand the script better:
+To understand the script better; in `t_cube.py`:
 - Refer to the `compute_samplewise_tcube_weights` and `compute_samplewise_tcube_weights_MI` functions for entropy (DaWiN baseline) and Our mutual information-based merging.
 - Check the `evaluate_on_test_set` function for how datasets and severities are processed.
 - Explore the `evaluate_tcube` function for the merging and evaluation logic.
@@ -126,12 +137,38 @@ We provide pretrained weights for the following models:
    - Cell Microscopy
    - Retinal OCT
 
-If you would like access to these weights, please contact us directly at [Raza Imam](mailto:[email protected]).
+<!-- If you would like access to these weights, please contact us directly at [Raza Imam](mailto:[email protected]). -->
+If you would like to access these weights, please find them at model card at [https://huggingface.co/razaimam45/TCube_Merging](https://huggingface.co/razaimam45/TCube_Merging) under `models/finetuned` subfolder. 
 
 ---
 
+## Datasets
+
+We provided `Breast Imaging` evaluation sets on [HuggingFace page](https://huggingface.co/razaimam45/TCube_Merging). Please download from there.
+
+If you need to run multiple modalities datasets, just pass `--testset` arg with `'bloodmnist/breastmnist/'`. This will evaluate medmnist-c and medimeta from each modality, resulting in 4 datasets evaluation.
+
+If you need all modality datasets, you can find them as follows:
+* [MedMNIST datasets](https://zenodo.org/records/10519652) | In-Domain _Fine-Tune_ Datasets
+* [MediMeta datasets](https://zenodo.org/records/7884735) | OOD-B2N _Eval_ Datasets
+* [MedMNIST-C datasets](https://github.com/francescodisalvo05/medmnistc-api) | OOD-Corruptions _Eval_ Datasets
+
 ## License
 This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
 
+### Citation
+If you find this work useful, please cite the arXiv version below:
+```
+@misc{imam2025t3testtimemodelmerging,
+      title={T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis}, 
+      author={Raza Imam and Hu Wang and Dwarikanath Mahapatra and Mohammad Yaqub},
+      year={2025},
+      eprint={2510.27265},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2510.27265}, 
+}
+```
+
 ## Contact
-For questions or collaborations, contact [Raza Imam](mailto:[email protected]).
+For questions or collaborations, contact [Raza Imam](mailto:[email protected]). Please feel free to raise an issue in facing error in reproducing the results.