Zobrazeno 1 - 10
of 8 531
pro vyhledávání: '"Färber, P."'
Autor:
Yuan, Shuzhou, Sun, Jingyi, Zhang, Ran, Färber, Michael, Eger, Steffen, Atanasova, Pepa, Augenstein, Isabelle
Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned the faithfulness of NLEs, as they may not accurately reflect the mode
Externí odkaz:
http://arxiv.org/abs/2412.12318
Relation extraction is crucial for constructing knowledge graphs, with large high-quality datasets serving as the foundation for training, fine-tuning, and evaluating models. Generative data augmentation (GDA) is a common approach to expand such data
Externí odkaz:
http://arxiv.org/abs/2410.08393
Autor:
Aydin, Irem, Diebel-Fischer, Hermann, Freiberger, Vincent, Möller-Klapperich, Julia, Buchmann, Erik, Färber, Michael, Lauber-Rönsberg, Anne, Platow, Birte
The growing use of Machine Learning and Artificial Intelligence (AI), particularly Large Language Models (LLMs) like OpenAI's GPT series, leads to disruptive changes across organizations. At the same time, there is a growing concern about how organiz
Externí odkaz:
http://arxiv.org/abs/2410.08381
Autor:
Anderson, L. D., Camilo, F., Faerber, Timothy, Bietenholz, M., Bordiu, C., Bufano, F., Chibueze, J. O., Cotton, W. D., Ingallinera, A., Loru, S., Rigby, A., Riggi, S., Thompson, M. A., Trigilio, C., Umana, G., Williams, G. M.
Context. Sensitive radio continuum data could remove the difference between the number of known supernova remnants (SNRs) in the Galaxy compared to that expected, but due to confusion in the Galactic plane, faint SNRs can be challenging to distinguis
Externí odkaz:
http://arxiv.org/abs/2409.16607
Autor:
Susanti, Yuni, Färber, Michael
Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with variables rath
Externí odkaz:
http://arxiv.org/abs/2407.18752
In this paper, we introduce AutoRDF2GML, a framework designed to convert RDF data into data representations tailored for graph machine learning tasks. AutoRDF2GML enables, for the first time, the creation of both content-based features -- i.e., featu
Externí odkaz:
http://arxiv.org/abs/2407.18735
We introduce ComplexTempQA, a large-scale dataset consisting of over 100 million question-answer pairs designed to tackle the challenges in temporal question answering. ComplexTempQA significantly surpasses existing benchmarks like HOTPOTQA, TORQUE,
Externí odkaz:
http://arxiv.org/abs/2406.04866
Autor:
Shao, Chen, Giacoumidis, Elias, Matalla, Patrick, Li, Jialei, Li, Shi, Randel, Sebastian, Richter, Andre, Faerber, Michael, Kaefer, Tobias
We experimentally demonstrate a novel, low-complexity Fourier Convolution-based Network (FConvNet) based equalizer for 112 Gb/s upstream PAM4-PON. At a BER of 0.005, FConvNet enhances the receiver sensitivity by 2 and 1 dB compared to a 51-tap Sato e
Externí odkaz:
http://arxiv.org/abs/2405.02609
Autor:
Shao, Chen, Giacoumidis, Elias, Billah, Syed Moktacim, Li, Shi, Li, Jialei, Sahu, Prashasti, Richter, Andre, Kaefer, Tobias, Faerber, Michael
In recent years, extensive research has been conducted to explore the utilization of machine learning algorithms in various direct-detected and self-coherent short-reach communication applications. These applications encompass a wide range of tasks,
Externí odkaz:
http://arxiv.org/abs/2405.09557
Autor:
Shao, Chen, Giacoumidis, Elias, Li, Shi, Li, Jialei, Faerber, Michael, Kaefer, Tobias, Richter, Andre
A frequency-calibrated SCINet (FC-SCINet) equalizer is proposed for down-stream 100G PON with 28.7 dB path loss. At 5 km, FC-SCINet improves the BER by 88.87% compared to FFE and a 3-layer DNN with 10.57% lower complexity.
Comment: 3 pages, 6 fi
Comment: 3 pages, 6 fi
Externí odkaz:
http://arxiv.org/abs/2405.00720