Spaces:
Sleeping
Sleeping
update
Browse files
README.md
CHANGED
|
@@ -12,9 +12,21 @@ short_description: Streamlit template space
|
|
| 12 |
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
-
|
|
|
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
+
Demo for Number Token Loss (ICML 2025)
|
| 16 |
|
| 17 |
+
See full paper at: https://arxiv.org/abs/2411.02083
|
| 18 |
+
See project landing page at: https://ibm.biz/ntl-main
|
| 19 |
|
| 20 |
+
```bibtex
|
| 21 |
+
@inproceedings{zausinger2025regress,
|
| 22 |
+
title = {Regress, Don't Guess – A Regression-like Loss on Number Tokens for Language Models},
|
| 23 |
+
author = {Jonas Zausinger and Lars Pennig and Anamarija Kozina and Sean Sdahl
|
| 24 |
+
and Julian Sikora and Adrian Dendorfer and Timofey Kuznetsov
|
| 25 |
+
and Mohamad Hagog and Nina Wiedemann and Kacper Chlodny
|
| 26 |
+
and Vincent Limbach and Anna Ketteler and Thorben Prein
|
| 27 |
+
and Vishwa Mohan Singh and Michael Danziger and Jannis Born},
|
| 28 |
+
booktitle = {Proc. of the 42nd International Conference on Machine Learning (ICML)},
|
| 29 |
+
year = {2025},
|
| 30 |
+
url = {https://ibm.biz/ntl-main}
|
| 31 |
+
}
|
| 32 |
+
```
|