Zobrazeno 1 - 10
of 304
pro vyhledávání: '"Buntine, P"'
Logical reasoning is a fundamental task in natural language processing that presents significant challenges to Large Language Models (LLMs). The inherent characteristics of logical reasoning makes it well-suited for symbolic representations such as f
Externí odkaz:
http://arxiv.org/abs/2409.16461
Autor:
Ho, Gia-Bao Dinh, Tan, Chang Wei, Darban, Zahra Zamanzadeh, Salehi, Mahsa, Haffari, Gholamreza, Buntine, Wray
Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences. Our work introduces a novel problem setting focusing on these moments
Externí odkaz:
http://arxiv.org/abs/2409.14801
Autor:
Zhou, Xin, Wang, Weiqing, Buntine, Wray, Qu, Shilin, Sriramulu, Abishek, Tan, Weicong, Bergmeir, Christoph
Deep models for Multivariate Time Series (MTS) forecasting have recently demonstrated significant success. Channel-dependent models capture complex dependencies that channel-independent models cannot capture. However, the number of channels in real-w
Externí odkaz:
http://arxiv.org/abs/2408.04245
While diffusion models excel at conditional generating high-quality images, prior works in discrete diffusion models were not evaluated on conditional long-text generation. In this work, we address the limitations of prior discrete diffusion models f
Externí odkaz:
http://arxiv.org/abs/2407.10998
Topic modeling has been a widely used tool for unsupervised text analysis. However, comprehensive evaluations of a topic model remain challenging. Existing evaluation methods are either less comparable across different models (e.g., perplexity) or fo
Externí odkaz:
http://arxiv.org/abs/2406.09008
Resolving conflicts is essential to make the decisions of multi-view classification more reliable. Much research has been conducted on learning consistent informative representations among different views, assuming that all views are identically impo
Externí odkaz:
http://arxiv.org/abs/2406.00958
Autor:
Liu, Ming, Liu, Ran, Zhu, Ye, Wang, Hua, Qu, Youyang, Li, Rongsheng, Sheng, Yongpan, Buntine, Wray
ChatGPT has changed the AI community and an active research line is the performance evaluation of ChatGPT. A key challenge for the evaluation is that ChatGPT is still closed-source and traditional benchmark datasets may have been used by ChatGPT as t
Externí odkaz:
http://arxiv.org/abs/2405.00704
Machine translation for Vietnamese-English in the medical domain is still an under-explored research area. In this paper, we introduce MedEV -- a high-quality Vietnamese-English parallel dataset constructed specifically for the medical domain, compri
Externí odkaz:
http://arxiv.org/abs/2403.19161
Most existing medication recommendation models learn representations for medical concepts based on electronic health records (EHRs) and make recommendations with learnt representations. However, most medications appear in the dataset for limited time
Externí odkaz:
http://arxiv.org/abs/2401.15814
While Language Agents have achieved promising success by placing Large Language Models at the core of a more versatile design that dynamically interacts with the external world, the existing approaches neglect the notion of uncertainty during these i
Externí odkaz:
http://arxiv.org/abs/2401.14016