Zobrazeno 1 - 10
of 116
pro vyhledávání: '"KOLLIAS, GEORGIOS"'
Autor:
Ko, Ching-Yun, Chen, Pin-Yu, Das, Payel, Mroueh, Youssef, Dan, Soham, Kollias, Georgios, Chaudhury, Subhajit, Pedapati, Tejaswini, Daniel, Luca
Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning the LLM us
Externí odkaz:
http://arxiv.org/abs/2410.03818
Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit memory mecha
Externí odkaz:
http://arxiv.org/abs/2407.16908
Current large language models (LLMs) often perform poorly on simple fact retrieval tasks. Here we investigate if coupling a dynamically adaptable external memory to a LLM can alleviate this problem. For this purpose, we test Larimar, a recently propo
Externí odkaz:
http://arxiv.org/abs/2407.01437
Autor:
Das, Payel, Chaudhury, Subhajit, Nelson, Elliot, Melnyk, Igor, Swaminathan, Sarath, Dai, Sihui, Lozano, Aurélie, Kollias, Georgios, Chenthamarakshan, Vijil, Jiří, Navrátil, Dan, Soham, Chen, Pin-Yu
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episod
Externí odkaz:
http://arxiv.org/abs/2403.11901
Autor:
Dhurandhar, Amit, Pedapati, Tejaswini, Luss, Ronny, Dan, Soham, Lozano, Aurelie, Das, Payel, Kollias, Georgios
Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their widespread
Externí odkaz:
http://arxiv.org/abs/2404.01306
Autor:
Wu, Dongxia, Idé, Tsuyoshi, Lozano, Aurélie, Kollias, Georgios, Navrátil, Jiří, Abe, Naoki, Ma, Yi-An, Yu, Rose
We address the problem of learning Granger causality from asynchronous, interdependent, multi-type event sequences. In particular, we are interested in discovering instance-level causal structures in an unsupervised manner. Instance-level causality i
Externí odkaz:
http://arxiv.org/abs/2402.03726
Is Conduction System Pacing Going to Be the New Gold Standard for Cardiac Resynchronization Therapy?
Autor:
Derndorfer, Michael1 (AUTHOR) martin.martinek@ordensklinikum.at, Kollias, Georgios1 (AUTHOR), Martinek, Martin1 (AUTHOR), Pürerfellner, Helmut1 (AUTHOR)
Publikováno v:
Journal of Clinical Medicine. Aug2024, Vol. 13 Issue 15, p4320. 19p.
We propose a new sparse Granger-causal learning framework for temporal event data. We focus on a specific class of point processes called the Hawkes process. We begin by pointing out that most of the existing sparse causal learning algorithms for the
Externí odkaz:
http://arxiv.org/abs/2208.10671
We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representations for the nodes of directe
Externí odkaz:
http://arxiv.org/abs/2202.12449
Autor:
Kalantzis, Vassilis, Kollias, Georgios, Ubaru, Shashanka, Nikolakopoulos, Athanasios N., Horesh, Lior, Clarkson, Kenneth L.
This paper considers the problem of updating the rank-k truncated Singular Value Decomposition (SVD) of matrices subject to the addition of new rows and/or columns over time. Such matrix problems represent an important computational kernel in applica
Externí odkaz:
http://arxiv.org/abs/2010.06392