Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Qian, Zhaozhi"'
Large Language Models (LLMs) are the cornerstones of modern artificial intelligence systems. This paper introduces Juhaina, a Arabic-English bilingual LLM specifically designed to align with the values and preferences of Arabic speakers. Juhaina inhe
Externí odkaz:
http://arxiv.org/abs/2409.12623
Autor:
Kacprzyk, Krzysztof, Holt, Samuel, Berrevoets, Jeroen, Qian, Zhaozhi, van der Schaar, Mihaela
Inferring unbiased treatment effects has received widespread attention in the machine learning community. In recent years, our community has proposed numerous solutions in standard settings, high-dimensional treatment settings, and even longitudinal
Externí odkaz:
http://arxiv.org/abs/2403.10766
Autor:
Huynh, Nicolas, Berrevoets, Jeroen, Seedat, Nabeel, Crabbé, Jonathan, Qian, Zhaozhi, van der Schaar, Mihaela
Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models. While recent data-centric methods are able to identify such inconsistencies with respect to the training set, th
Externí odkaz:
http://arxiv.org/abs/2402.17599
Clinical trials are typically run in order to understand the effects of a new treatment on a given population of patients. However, patients in large populations rarely respond the same way to the same treatment. This heterogeneity in patient respons
Externí odkaz:
http://arxiv.org/abs/2401.17205
Publikováno v:
International Conference on Learning Representations (ICLR), 2023
Symbolic regression (SR) aims to discover concise closed-form mathematical equations from data, a task fundamental to scientific discovery. However, the problem is highly challenging because closed-form equations lie in a complex combinatorial search
Externí odkaz:
http://arxiv.org/abs/2401.00282
Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization. However, current data characterization methods are largely focused on classifica
Externí odkaz:
http://arxiv.org/abs/2310.18970
Autor:
Jarrett, Daniel, Yoon, Jinsung, Bica, Ioana, Qian, Zhaozhi, Ercole, Ari, van der Schaar, Mihaela
Publikováno v:
In Proc. 9th International Conference on Learning Representations (ICLR 2021)
Time-series learning is the bread and butter of data-driven *clinical decision support*, and the recent explosion in ML research has demonstrated great potential in various healthcare settings. At the same time, medical time-series problems in the wi
Externí odkaz:
http://arxiv.org/abs/2310.18688
This paper addresses unsupervised representation learning on tabular data containing multiple views generated by distinct sources of measurement. Traditional methods, which tackle this problem using the multi-view framework, are constrained by predef
Externí odkaz:
http://arxiv.org/abs/2305.19726
Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs. Unfortunately, synthetic data is usually not perfect, resulting in potentia
Externí odkaz:
http://arxiv.org/abs/2305.09235
Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential largely remains to be unlocked as causality often requires crucial assumptions which cannot be tested in practice. To ad
Externí odkaz:
http://arxiv.org/abs/2303.02186