Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.16844 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913955135356928 |
|---|---|
| author | He, Jie Kenbeek, Vincent Theo Willem Yang, Zhantao Qu, Meixun Bartocci, Ezio Ničković, Dejan Grosu, Radu |
| author_facet | He, Jie Kenbeek, Vincent Theo Willem Yang, Zhantao Qu, Meixun Bartocci, Ezio Ničković, Dejan Grosu, Radu |
| contents | We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual question-answer environment which allows engineers to input a set of TDs and ask design and verification queries regarding these TDs. We implemented TD-Interpreter with multimodal learning by fine-tuning LLaVA, a lightweight 7B Multimodal Large Language Model (MLLM). To address limited training data availability, we developed a synthetic data generation workflow that aligns visual information with its textual interpretation. Our experimental evaluation demonstrates the usefulness of TD-Interpreter which outperformed untuned GPT-4o by a large margin on the evaluated benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16844 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TD-Interpreter: Enhancing the Understanding of Timing Diagrams with Visual-Language Learning He, Jie Kenbeek, Vincent Theo Willem Yang, Zhantao Qu, Meixun Bartocci, Ezio Ničković, Dejan Grosu, Radu Machine Learning We introduce TD-Interpreter, a specialized ML tool that assists engineers in understanding complex timing diagrams (TDs), originating from a third party, during their design and verification process. TD-Interpreter is a visual question-answer environment which allows engineers to input a set of TDs and ask design and verification queries regarding these TDs. We implemented TD-Interpreter with multimodal learning by fine-tuning LLaVA, a lightweight 7B Multimodal Large Language Model (MLLM). To address limited training data availability, we developed a synthetic data generation workflow that aligns visual information with its textual interpretation. Our experimental evaluation demonstrates the usefulness of TD-Interpreter which outperformed untuned GPT-4o by a large margin on the evaluated benchmarks. |
| title | TD-Interpreter: Enhancing the Understanding of Timing Diagrams with Visual-Language Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.16844 |