Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Noroozizadeh, Shahriar"'
Autor:
Moayedpour, Saeed, Corrochano-Navarro, Alejandro, Sahneh, Faryad, Noroozizadeh, Shahriar, Koetter, Alexander, Vymetal, Jiri, Kogler-Anele, Lorenzo, Mas, Pablo, Jangjou, Yasser, Li, Sizhen, Bailey, Michael, Bianciotto, Marc, Matter, Hans, Grebner, Christoph, Hessler, Gerhard, Bar-Joseph, Ziv, Jager, Sven
Large Language Models (LLMs) have demonstrated great performance in few-shot In-Context Learning (ICL) for a variety of generative and discriminative chemical design tasks. The newly expanded context windows of LLMs can further improve ICL capabiliti
Externí odkaz:
http://arxiv.org/abs/2407.19089
Publikováno v:
Conference on Computer Vision and Pattern Recognition (CVPR 2022) - Embodied AI Workshop
We introduce a simple method that employs pre-trained CLIP encoders to enhance model generalization in the ALFRED task. In contrast to previous literature where CLIP replaces the visual encoder, we suggest using CLIP as an additional module through a
Externí odkaz:
http://arxiv.org/abs/2406.17876
Publikováno v:
In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 507-516, Mexico City, Mexico. Association for Computational Linguistics
This paper introduces novel methodologies for the Natural Language Inference for Clinical Trials (NLI4CT) task. We present TLDR (T5-generated clinical-Language summaries for DeBERTa Report Analysis) which incorporates T5-model generated premise summa
Externí odkaz:
http://arxiv.org/abs/2404.09136
Publikováno v:
In Machine Learning for Health (ML4H), pages 403-427. PMLR, 2023
We consider the problem of predicting how the likelihood of an outcome of interest for a patient changes over time as we observe more of the patient data. To solve this problem, we propose a supervised contrastive learning framework that learns an em
Externí odkaz:
http://arxiv.org/abs/2312.05933
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Noroozizadeh S; Carnegie Mellon University, Pittsburgh, PA, USA., Weiss JC; National Library of Medicine, Bethesda, MD, USA., Chen GH; Carnegie Mellon University, Pittsburgh, PA, USA.
Publikováno v:
Proceedings of machine learning research [Proc Mach Learn Res] 2023; Vol. 225, pp. 403-427.
