AI Pangaea: Unifying Intelligence Islands for Adapting Myriad Tasks
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_ | 1866915506460557312 |
|---|---|
| author | Chang, Jianlong Wang, Haixin Dang, Zhiyuan Huang, Li Wang, Zhiyu Cao, Ruoqi Piao, Shihao Li, Dongzhe Gao, Dianyu Wang, Dongsheng Li, Yin Sun, Jinan Fang, Lu Lin, Zhouchen |
| author_facet | Chang, Jianlong Wang, Haixin Dang, Zhiyuan Huang, Li Wang, Zhiyu Cao, Ruoqi Piao, Shihao Li, Dongzhe Gao, Dianyu Wang, Dongsheng Li, Yin Sun, Jinan Fang, Lu Lin, Zhouchen |
| contents | The pursuit of artificial general intelligence continuously demands generalization in one model across myriad tasks, even those not seen before. However, current AI models are isolated from each other for being limited to specific tasks, now first defined as Intelligence Islands. To unify Intelligence Islands into one, we propose Pangaea, the first AI supercontinent akin to the geological Pangaea. Pangaea encodes any data into a unified format and accumulates universal knowledge through pre-training on 296 datasets across diverse modalities. Eventually, it demonstrates remarkable generalization across 45 general tasks and 15 scientific tasks encompassing a wide range of scientific subjects. By investigating Pangaea deeper, the scaling effect of modality is revealed, quantifying the universal knowledge accumulation across modalities as the cumulative distribution function of a geometric distribution. On the whole, Pangaea shows strong potential to handle myriad tasks, indicating a new direction toward artificial general intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17460 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI Pangaea: Unifying Intelligence Islands for Adapting Myriad Tasks Chang, Jianlong Wang, Haixin Dang, Zhiyuan Huang, Li Wang, Zhiyu Cao, Ruoqi Piao, Shihao Li, Dongzhe Gao, Dianyu Wang, Dongsheng Li, Yin Sun, Jinan Fang, Lu Lin, Zhouchen Artificial Intelligence Machine Learning The pursuit of artificial general intelligence continuously demands generalization in one model across myriad tasks, even those not seen before. However, current AI models are isolated from each other for being limited to specific tasks, now first defined as Intelligence Islands. To unify Intelligence Islands into one, we propose Pangaea, the first AI supercontinent akin to the geological Pangaea. Pangaea encodes any data into a unified format and accumulates universal knowledge through pre-training on 296 datasets across diverse modalities. Eventually, it demonstrates remarkable generalization across 45 general tasks and 15 scientific tasks encompassing a wide range of scientific subjects. By investigating Pangaea deeper, the scaling effect of modality is revealed, quantifying the universal knowledge accumulation across modalities as the cumulative distribution function of a geometric distribution. On the whole, Pangaea shows strong potential to handle myriad tasks, indicating a new direction toward artificial general intelligence. |
| title | AI Pangaea: Unifying Intelligence Islands for Adapting Myriad Tasks |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.17460 |