From Representation to Reasoning: Toward General-Purpose Visual Intelligence
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39836-39837
DOI: 10.1609/aaai.v40i47.41357 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chen Wei.
Abstract (Originalsprache)
This talk surveys my research agenda on advancing general-purpose visual intelligence, moving AI beyond static recognition toward active reasoning and embodied action. A central challenge is enabling AI systems to generalize reliably in low-data and long-tail regimes. I address this by combining multimodal representation learning with agentic reasoning frameworks such as PyVision, which equips vision models to dynamically generate tools for deliberate problem-solving, and ViGaL, which leverages gameplay to instill transferable cognitive skills for reasoning under scarcity. These efforts chart a trajectory from representation and generation to interactive, embodied agents, re-imagining AI as an active collaborator capable of tool use, imagination, and purposeful engagement across both digital and physical environments.
Zitieren
APA
Wei, C. (2026). From Representation to Reasoning: Toward General-Purpose Visual Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39836-39837. https://doi.org/10.1609/aaai.v40i47.41357
Vancouver
Wei C. From Representation to Reasoning: Toward General-Purpose Visual Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39836-39837. doi:10.1609/aaai.v40i47.41357
BibTeX
@article{Wei2026,
author = {Wei, Chen},
title = {From Representation to Reasoning: Toward General-Purpose Visual Intelligence},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {47},
pages = {39836--39837},
doi = {10.1609/aaai.v40i47.41357}
}
EUVIMED