Recurrent Joint Embedding Predictive Architecture with Recurrent Forward Propagation Learning

Autor: Velarde, Osvaldo M, Parra, Lucas C

Conventional computer vision models rely on very deep, feedforward networks processing whole images and trained offline with extensive labeled data. In contrast, biological vision relies on comparatively shallow, recurrent networks that analyze seque

Externí odkaz: http://arxiv.org/abs/2411.16695

Optimization and Generalization Guarantees for Weight Normalization

Autor: Cisneros-Velarde, Pedro, Chen, Zhijie, Koyejo, Sanmi, Banerjee, Arindam

Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In this paper, we provide the first theoretical characterizations of both op

Externí odkaz: http://arxiv.org/abs/2409.08935

Measurement and analysis of the $^{246}$Cm and $^{248}$Cm neutron capture cross-sections at the EAR2 of the n TOF facility

Autor: Alcayne, V., Kimura, A., Mendoza, E., Cano-Ott, D., Aberle, O., Álvarez-Velarde, F., Amaducci, S., Andrzejewski, J., Audouin, L., Bécares, V., Babiano-Suarez, V., Bacak, M., Barbagallo, M., Bečvář, F., Bellia, G., Berthoumieux, E., Billowes, J., Bosnar, D., Brown, A., Busso, M., Caamaño, M., Caballero-Ontanaya, L., Calviño, F., Calviani, M., Casanovas, A., Cerutti, F., Chen, Y. H., Chiaveri, E., Colonna, N., Cortés, G., Cortés-Giraldo, M. A., Cosentino, L., Cristallo, S., Damone, L. A., Diakaki, M., Dietz, M., Domingo-Pardo, C., Dressler, R., Dupont, E., Durán, I., Eleme, Z., Fernández-Domınguez, B., Ferrari, A., Finocchiaro, P., Furman, V., Göbel, K., Garg, R., Gawlik-Ramiega, A., Gilardoni, S., Glodariu, T., Gonçalves, I. F., González-Romero, E., Guerrero, C., Gunsing, F., Harada, H., Heinitz, S., Heyse, J., Jenkins, D. G., Jericha, E., Käppeler, F., Kadi, Y., Kivel, N., Kokkoris, M., Kopatch, Y., Krtička, M., Kurtulgil, D., Ladarescu, I., Lederer-Woods, C., Leeb, H., Lerendegui-Marco, J., Meo, S. Lo, Lonsdale, S. J., Macina, D., Manna, A., Martınez, T., Masi, A., Massimi, C., Mastinu, P., Mastromarco, M., Matteucci, F., Maugeri, E. A., Mazzone, A., Mengoni, A., Michalopoulou, V., Milazzo, P. M., Mingrone, F., Musumarra, A., Negret, A., Nolte, R., Ogállar, F., Oprea, A., Patronis, N., Pavlik, A., de Rada, A. Pérez, Perkowski, J., Persanti, L., Porras, I., Praena, J., Quesada, J. M., Radeck, D., Ramos-Doval, D., Rauscher, T., Reifarth, R., Rochman, D., Romanets, Y., Rubbia, C., Sabaté-Gilarte, M., Saxena, A., Schillebeeckx, P., Schumann, D., Smith, A. G., Sosnin, N. V., Stamatopoulos, A., Tagliente, G., Tain, J. L., Talip, T., Tarifeño-Saldivia, A., Tassan-Got, L., Torres-Sánchez, P., Tsinganis, A., Ulrich, J., Urlass, S., Valenta, S., Vannini, G., Variale, V., Vaz, P., Ventura, A., Vlachoudis, V., Vlastou, R., Wallner, A., Woods, P. J., Wright, T., Žugec, P.

The $^{246}$Cm(n,$\gamma$) and $^{248}$Cm(n,$\gamma$) cross-sections have been measured at the Experimental Area 2 (EAR2) of the n_TOF facility at CERN with three C$_6$D$_6$ detectors. This measurement is part of a collective effort to improve the ca

Externí odkaz: http://arxiv.org/abs/2407.06377

On the Principles behind Opinion Dynamics in Multi-Agent Systems of Large Language Models

Autor: Cisneros-Velarde, Pedro

We study the evolution of opinions inside a population of interacting large language models (LLMs). Every LLM needs to decide how much funding to allocate to an item with three initial possibilities: full, partial, or no funding. We identify biases t

Externí odkaz: http://arxiv.org/abs/2406.15492

A Half-Century Research Footpath in Statistical Physics

Autor: Robledo, Alberto, Velarde, Carlos

We give an abridged account of a continued string of studies in condensed matter physics and in complex systems that span five decades. We provide links to access abstracts and full texts of a selected list of publications. The studies were carried o

Externí odkaz: http://arxiv.org/abs/2401.06181