Update README.md
Browse files
README.md
CHANGED
|
@@ -284,7 +284,6 @@ Please reason step-by-step, and put your final answer within \\boxed{}.
|
|
| 284 |
### Known Issues
|
| 285 |
* Model is sensitive to system prompt. We recommend using the default one.
|
| 286 |
* The model is finetuned for multiple-choice VQA. The model may follow instructions for other tasks but is not extensively tested or post-trained to do so.
|
| 287 |
-
* The model occasionally states that it cannot see the image even when the image is provided. Some of our text-only reasoning traces describe an image in words, and the expected reasoning trace indicates that the image is missing. Despite this, we observe high benchmark performance and the model can still reliably use visual information.
|
| 288 |
|
| 289 |
We hope to address these concerns moving forward in future iterations!
|
| 290 |
|
|
@@ -293,7 +292,7 @@ We hope to address these concerns moving forward in future iterations!
|
|
| 293 |
If you find our work helpful, feel free to give us a cite.
|
| 294 |
|
| 295 |
```
|
| 296 |
-
@article{
|
| 297 |
title={OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning},
|
| 298 |
author={Ossowski, Timothy and Zhang, Sheng and Liu, Qianchu and Qin, Guanghui and Tan, Reuben and Naumann, Tristan and Hu, Junjie and Poon, Hoifung},
|
| 299 |
journal={arXiv preprint arXiv:2511.23269},
|
|
|
|
| 284 |
### Known Issues
|
| 285 |
* Model is sensitive to system prompt. We recommend using the default one.
|
| 286 |
* The model is finetuned for multiple-choice VQA. The model may follow instructions for other tasks but is not extensively tested or post-trained to do so.
|
|
|
|
| 287 |
|
| 288 |
We hope to address these concerns moving forward in future iterations!
|
| 289 |
|
|
|
|
| 292 |
If you find our work helpful, feel free to give us a cite.
|
| 293 |
|
| 294 |
```
|
| 295 |
+
@article{ossowski2025octomed,
|
| 296 |
title={OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning},
|
| 297 |
author={Ossowski, Timothy and Zhang, Sheng and Liu, Qianchu and Qin, Guanghui and Tan, Reuben and Naumann, Tristan and Hu, Junjie and Poon, Hoifung},
|
| 298 |
journal={arXiv preprint arXiv:2511.23269},
|