Zobrazeno 1 - 10
of 20 567
pro vyhledávání: '"Caglar, A"'
The emergence of beyond 5G (B5G) and 6G networks underscores the critical role of advanced computer-aided tools, such as network digital twins (DTs), in fostering autonomous networks and ubiquitous intelligence. Existing solutions in the DT domain pr
Externí odkaz:
http://arxiv.org/abs/2409.01136
Autor:
Terekhov, Mikhail, Gulcehre, Caglar
Multi-objective reinforcement learning (MORL) is essential for addressing the intricacies of real-world RL problems, which often require trade-offs between multiple utility functions. However, MORL is challenging due to unstable learning dynamics wit
Externí odkaz:
http://arxiv.org/abs/2407.16807
Machine translation is indispensable in healthcare for enabling the global dissemination of medical knowledge across languages. However, complex medical terminology poses unique challenges to achieving adequate translation quality and accuracy. This
Externí odkaz:
http://arxiv.org/abs/2407.12126
State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs, specifically a
Externí odkaz:
http://arxiv.org/abs/2407.09835
This work explores the in-context learning capabilities of State Space Models (SSMs) and presents, to the best of our knowledge, the first theoretical explanation of a possible underlying mechanism. We introduce a novel weight construction for SSMs,
Externí odkaz:
http://arxiv.org/abs/2407.09375
Knowledge Graph Embedding (KGE) transforms a discrete Knowledge Graph (KG) into a continuous vector space facilitating its use in various AI-driven applications like Semantic Search, Question Answering, or Recommenders. While KGE approaches are effec
Externí odkaz:
http://arxiv.org/abs/2407.06855
Autor:
Davidson, Tim R., Surkov, Viacheslav, Veselovsky, Veniamin, Russo, Giuseppe, West, Robert, Gulcehre, Caglar
A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification methods, w
Externí odkaz:
http://arxiv.org/abs/2407.06946
Autor:
Ozturk, Caglar, Pak, Daniel H., Rosalia, Luca, Goswami, Debkalpa, Robakowski, Mary E., McKay, Raymond, Nguyen, Christopher T., Duncan, James S., Roche, Ellen T.
Aortic stenosis (AS) is the most common valvular heart disease in developed countries. High-fidelity preclinical models can improve AS management by enabling therapeutic innovation, early diagnosis, and tailored treatment planning. However, their use
Externí odkaz:
http://arxiv.org/abs/2407.00535
Ensemble models often improve generalization performances in challenging tasks. Yet, traditional techniques based on prediction averaging incur three well-known disadvantages: the computational overhead of training multiple models, increased latency,
Externí odkaz:
http://arxiv.org/abs/2406.19092
State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter count and computational costs without significantly impacting
Externí odkaz:
http://arxiv.org/abs/2406.16450