TS-HINT: Enhancing Semiconductor Time Series Regression Using Attention Hints From Large Language Model Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914181867896832 |
|---|---|
| author | Rico, Jonathan Adam Raghavan, Nagarajan Jayavelu, Senthilnath |
| author_facet | Rico, Jonathan Adam Raghavan, Nagarajan Jayavelu, Senthilnath |
| contents | Existing data-driven methods rely on the extraction of static features from time series to approximate the material removal rate (MRR) of semiconductor manufacturing processes such as chemical mechanical polishing (CMP). However, this leads to a loss of temporal dynamics. Moreover, these methods require a large amount of data for effective training. In this paper, we propose TS-Hint, a Time Series Foundation Model (TSFM) framework, integrated with chain-of-thought reasoning which provides attention hints during training based on attention mechanism data and saliency data. Experimental results demonstrate the effectiveness of our model in limited data settings via few-shot learning and can learn directly from multivariate time series features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05419 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TS-HINT: Enhancing Semiconductor Time Series Regression Using Attention Hints From Large Language Model Reasoning Rico, Jonathan Adam Raghavan, Nagarajan Jayavelu, Senthilnath Machine Learning Existing data-driven methods rely on the extraction of static features from time series to approximate the material removal rate (MRR) of semiconductor manufacturing processes such as chemical mechanical polishing (CMP). However, this leads to a loss of temporal dynamics. Moreover, these methods require a large amount of data for effective training. In this paper, we propose TS-Hint, a Time Series Foundation Model (TSFM) framework, integrated with chain-of-thought reasoning which provides attention hints during training based on attention mechanism data and saliency data. Experimental results demonstrate the effectiveness of our model in limited data settings via few-shot learning and can learn directly from multivariate time series features. |
| title | TS-HINT: Enhancing Semiconductor Time Series Regression Using Attention Hints From Large Language Model Reasoning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.05419 |