Spaces:
Running
Running
Update README.md
Browse filesadd year subsections
README.md
CHANGED
@@ -11,7 +11,12 @@ pinned: false
|
|
11 |
|
12 |
## Projects
|
13 |
|
|
|
|
|
14 |
- [Large Language Models as Markov Chains](https://huggingface.co/papers/2410.02724): theoretical insights on their generalization and convergence properties.
|
|
|
|
|
|
|
15 |
- *(NeurIPS'24)* [MANO: Unsupervised Accuracy Estimation Under Distribution Shifts](https://huggingface.co/papers/2405.18979): when logits are enough to estimate generalization of a pre-trained model.
|
16 |
- *(NeurIPS'24, **Spotlight**)* [Analysing Multi-Task Regression via Random Matrix Theory](https://arxiv.org/pdf/2406.10327): insights on a classical approach and its potentiality for time series forecasting.
|
17 |
- *(ICML'24, **Oral**)* [SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting](https://huggingface.co/papers/2402.10198): sharpness-aware minimization and channel-wise attention is all you need.
|
|
|
11 |
|
12 |
## Projects
|
13 |
|
14 |
+
### Preprints
|
15 |
+
|
16 |
- [Large Language Models as Markov Chains](https://huggingface.co/papers/2410.02724): theoretical insights on their generalization and convergence properties.
|
17 |
+
|
18 |
+
### 2024
|
19 |
+
|
20 |
- *(NeurIPS'24)* [MANO: Unsupervised Accuracy Estimation Under Distribution Shifts](https://huggingface.co/papers/2405.18979): when logits are enough to estimate generalization of a pre-trained model.
|
21 |
- *(NeurIPS'24, **Spotlight**)* [Analysing Multi-Task Regression via Random Matrix Theory](https://arxiv.org/pdf/2406.10327): insights on a classical approach and its potentiality for time series forecasting.
|
22 |
- *(ICML'24, **Oral**)* [SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting](https://huggingface.co/papers/2402.10198): sharpness-aware minimization and channel-wise attention is all you need.
|