Human Cognition in Machines: A Unified Perspective of World Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917417689546752 |
|---|---|
| author | Rupprecht, Timothy Zhao, Pu Taherin, Amir Akbari, Arash Akbari, Arman He, Yumei Duffy, Sean Lin, Juyi Chen, Yixiao Chowdhury, Rahul Nan, Enfu Shen, Yixin Cao, Yifan Zeng, Haochen Chen, Weiwei Yuan, Geng Dy, Jennifer Ostadabbas, Sarah Zhang, Silvia Kaeli, David Yeh, Edmund Wang, Yanzhi |
| author_facet | Rupprecht, Timothy Zhao, Pu Taherin, Amir Akbari, Arash Akbari, Arman He, Yumei Duffy, Sean Lin, Juyi Chen, Yixiao Chowdhury, Rahul Nan, Enfu Shen, Yixin Cao, Yifan Zeng, Haochen Chen, Weiwei Yuan, Geng Dy, Jennifer Ostadabbas, Sarah Zhang, Silvia Kaeli, David Yeh, Edmund Wang, Yanzhi |
| contents | This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost "human-like" cognitive capability in their world models. To evaluate these claims requires a proper grounding in first principles in Cognitive Architecture Theory (CAT). We present a conceptual unified framework for world models that fully incorporates all the cognitive functions associated with CAT (i.e. memory, perception, language, reasoning, imagining, motivation, and meta-cognition) and identify gaps in the research as a guide for future states of the art. In particular, we find that motivation (especially intrinsic motivation) and meta-cognition remain drastically under-researched, and we propose concrete directions informed by active inference and global workspace theory to address them. We further introduce Epistemic World Models, a new category encompassing agent frameworks for scientific discovery that operate over structured knowledge. Our taxonomy, applied across video, embodied, and epistemic world models, suggests research directions where prior taxonomies have not. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16592 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Human Cognition in Machines: A Unified Perspective of World Models Rupprecht, Timothy Zhao, Pu Taherin, Amir Akbari, Arash Akbari, Arman He, Yumei Duffy, Sean Lin, Juyi Chen, Yixiao Chowdhury, Rahul Nan, Enfu Shen, Yixin Cao, Yifan Zeng, Haochen Chen, Weiwei Yuan, Geng Dy, Jennifer Ostadabbas, Sarah Zhang, Silvia Kaeli, David Yeh, Edmund Wang, Yanzhi Robotics Artificial Intelligence Computer Vision and Pattern Recognition Emerging Technologies This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost "human-like" cognitive capability in their world models. To evaluate these claims requires a proper grounding in first principles in Cognitive Architecture Theory (CAT). We present a conceptual unified framework for world models that fully incorporates all the cognitive functions associated with CAT (i.e. memory, perception, language, reasoning, imagining, motivation, and meta-cognition) and identify gaps in the research as a guide for future states of the art. In particular, we find that motivation (especially intrinsic motivation) and meta-cognition remain drastically under-researched, and we propose concrete directions informed by active inference and global workspace theory to address them. We further introduce Epistemic World Models, a new category encompassing agent frameworks for scientific discovery that operate over structured knowledge. Our taxonomy, applied across video, embodied, and epistemic world models, suggests research directions where prior taxonomies have not. |
| title | Human Cognition in Machines: A Unified Perspective of World Models |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Emerging Technologies |
| url | https://arxiv.org/abs/2604.16592 |