Towards Physics-Guided Foundation Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915254534930432 |
|---|---|
| author | Farhadloo, Majid Sharma, Arun Yang, Mingzhou Jayaprakash, Bharat Northrop, William Shekhar, Shashi |
| author_facet | Farhadloo, Majid Sharma, Arun Yang, Mingzhou Jayaprakash, Bharat Northrop, William Shekhar, Shashi |
| contents | Traditional foundation models are pre-trained on broad datasets to reduce the training resources (e.g., time, energy, labeled samples) needed for fine-tuning a wide range of downstream tasks. However, traditional foundation models struggle with out-of-distribution prediction and can produce outputs that are unrealistic and physically infeasible. We propose the notation of physics-guided foundation models (PGFM), that is, foundation models integrated with broad or general domain (e.g., scientific) physical knowledge applicable to a wide range of downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Physics-Guided Foundation Models Farhadloo, Majid Sharma, Arun Yang, Mingzhou Jayaprakash, Bharat Northrop, William Shekhar, Shashi Machine Learning Artificial Intelligence Traditional foundation models are pre-trained on broad datasets to reduce the training resources (e.g., time, energy, labeled samples) needed for fine-tuning a wide range of downstream tasks. However, traditional foundation models struggle with out-of-distribution prediction and can produce outputs that are unrealistic and physically infeasible. We propose the notation of physics-guided foundation models (PGFM), that is, foundation models integrated with broad or general domain (e.g., scientific) physical knowledge applicable to a wide range of downstream tasks. |
| title | Towards Physics-Guided Foundation Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.15013 |