EUVIMEDEUVIMED entdecken
Crossref

Efficient Model Specialization via Training-time and Test-time Adaptation

Huanrui Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39839-39840

DOI: 10.1609/aaai.v40i47.41359 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Huanrui Yang.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this talk, we discuss efficient model specialization algorithm to adapt the pretrained model towards downstream tasks while improving its efficiency, efficiently generalizing to multiple tasks via dynamic architectures, and improving inference-time efficiency utilizing the diversity within model block functionalities. These research directions serve as the foundation towards co-designing models, tasks, systems, and hardware for a reconfigurable efficient intelligence future.

Zitieren

APA

Yang, H. (2026). Efficient Model Specialization via Training-time and Test-time Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39839-39840. https://doi.org/10.1609/aaai.v40i47.41359

Vancouver

Yang H. Efficient Model Specialization via Training-time and Test-time Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39839-39840. doi:10.1609/aaai.v40i47.41359

BibTeX
@article{Yang2026,
  author = {Yang, Huanrui},
  title = {Efficient Model Specialization via Training-time and Test-time Adaptation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {39839--39840},
  doi = {10.1609/aaai.v40i47.41359}
}
Kostenlos starten →