Zobrazeno 1 - 10
of 2 608
pro vyhledávání: '"P. Nemeček"'
Autor:
Abdallah, J., Agaras, M. N., Ahmad, A., Bartos, P., Guardia, A. Berrocal, Bogavac, D., Argos, F. Carrio, Alberich, L. Cerda, Chargeishvili, B., Muiño, P. Conde, Cortes-Gonzalez, A., Gomes, A., Davidek, T., Djobava, T., Durglishvili, A., Epari, S., Facini, G., Faltova, J., Medeiros, M. Fontes, Glatzer, J., Delegido, A. J. Gomez, Harkusha, S., Correia, A. M. Henriques, Kholodenko, M., Klimek, P., Korolkov, I., Maio, A., Martins, F. M. Pedro, Saraiva, J. G., Menke, S., Petukhova, K., Minashvili, I. A., Mlynarikova, M., Mosidze, M., Mosulishvili, N., Nemecek, S., Pedro, R., Pereira, B. C. Pinheiro, Pleskot, V., Polacek, S., Qin, Y., Rosten, R., Santos, H., Schaefer, D., Scuri, F., Smirnov, Y, Sanchez, C. A. Solans, Solodkov, A. A., Solovyanov, O. V., Valero, A., Wilkens, H. G., Zakareishvili, T.
This paper presents a study of the radiation hardness of the hadronic Tile Calorimeter of the ATLAS experiment in the LHC Run 2. Both the plastic scintillators constituting the detector active media and the wavelength-shifting optical fibres collecti
Externí odkaz:
http://arxiv.org/abs/2412.15944
The indistinguishability of text generated by large language models (LLMs) from human-generated text poses significant challenges. Watermarking algorithms are potential solutions by embedding detectable signatures within LLM-generated outputs. Howeve
Externí odkaz:
http://arxiv.org/abs/2404.02138
Explainability of decisions made by AI systems is driven by both recent regulation and user demand. These decisions are often explainable only \emph{post hoc}, after the fact. In counterfactual explanations, one may ask what constitutes the best coun
Externí odkaz:
http://arxiv.org/abs/2401.14086
Tame functions are a class of nonsmooth, nonconvex functions, which feature in a wide range of applications: functions encountered in the training of deep neural networks with all common activations, value functions of mixed-integer programs, or wave
Externí odkaz:
http://arxiv.org/abs/2311.13544
In classification and forecasting with tabular data, one often utilizes tree-based models. Those can be competitive with deep neural networks on tabular data and, under some conditions, explainable. The explainability depends on the depth of the tree
Externí odkaz:
http://arxiv.org/abs/2306.06777
An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common solution is for a human expert to define either a penalty in the reward function or a cost to be minimised when reaching u
Externí odkaz:
http://arxiv.org/abs/2306.00035
Autor:
Nemecek, Adam
We argue that all building blocks of transformer models can be expressed with a single concept: combinatorial Hopf algebra. Transformer learning emerges as a result of the subtle interplay between the algebraic and coalgebraic operations of the combi
Externí odkaz:
http://arxiv.org/abs/2302.01834
Autor:
Leong, Colin, Nemecek, Joshua, Mansdorfer, Jacob, Filighera, Anna, Owodunni, Abraham, Whitenack, Daniel
Publikováno v:
EMNLP 2022
We present Bloom Library, a linguistically diverse set of multimodal and multilingual datasets for language modeling, image captioning, visual storytelling, and speech synthesis/recognition. These datasets represent either the most, or among the most
Externí odkaz:
http://arxiv.org/abs/2210.14712
Autor:
Nkadimeng, E., Mckenzie, R., Moayedi, S., Nemecek, S., Hadavand, H., Mellado, B., van Rensburg, R.
The ATLAS detector is set to undergo a substantial upgrade termed the "Phase-II" upgrade during the Long-Shutdown in preparation for the start of operation of the High Luminosity Large Hadron Collider (HL-LHC). This paper describes the development an
Externí odkaz:
http://arxiv.org/abs/2205.03374
Running automatic speech recognition (ASR) on edge devices is non-trivial due to resource constraints, especially in scenarios that require supporting multiple languages. We propose a new approach to enable multilingual speech recognition on edge dev
Externí odkaz:
http://arxiv.org/abs/2108.02034