Weakly-Supervised Multimodal Learning on MIMIC-CXR

Autor: Agostini, Andrea, Chopard, Daphné, Meng, Yang, Fortin, Norbert, Shahbaba, Babak, Mandt, Stephan, Sutter, Thomas M., Vogt, Julia E.

Multimodal data integration and label scarcity pose significant challenges for machine learning in medical settings. To address these issues, we conduct an in-depth evaluation of the newly proposed Multimodal Variational Mixture-of-Experts (MMVM) VAE

Externí odkaz: http://arxiv.org/abs/2411.10356

Bootstrapping Object-level Planning with Large Language Models

Autor: Paulius, David, Agostini, Alejandro, Quartey, Benedict, Konidaris, George

We introduce a new method that extracts knowledge from a large language model (LLM) to produce object-level plans, which describe high-level changes to object state, and uses them to bootstrap task and motion planning (TAMP) in a hierarchical manner.

Externí odkaz: http://arxiv.org/abs/2409.12262

Modelling the Kohn-Sham potential for molecular dissociation with orbital-independent functionals: a proof of principle

Autor: Giarrusso, Sara, Agostini, Federica

We model the Hartree-exchange-correlation potential of Kohn-Sham density-functional theory adopting a novel strategy inspired by the strictly-correlated-electrons limit and relying on the exact decomposition of the potential based on the exact factor

Externí odkaz: http://arxiv.org/abs/2408.06038

Searches for new physics below twice the electron mass with GERDA

Autor: GERDA Collaboration, Agostini, M., Alexander, A., Araujo, G. R., Bakalyarov, A. M., Balata, M., Barabanov, I., Baudis, L., Bauer, C., Belogurov, S., Bettini, A., Bezrukov, L., Biancacci, V., Bossio, E., Bothe, V., Brugnera, R., Caldwell, A., Calgaro, S., Cattadori, C., Chernogorov, A., Chiu, P. -J., Comellato, T., D'Andrea, V., Demidova, E. V., Di Marco, N., Doroshkevich, E., Fomina, M., Gangapshev, A., Garfagnini, A., Gooch, C., Grabmayr, P., Gurentsov, V., Gusev, K., Hakenmüller, J., Hemmer, S., Hofmann, W., Huang, J., Hult, M., Inzhechik, L. V., Csáthy, J. Janicskó, Jochum, J., Junker, M., Kazalov, V., Kermaïdic, Y., Khushbakht, H., Kihm, T., Kilgus, K., Kirpichnikov, I. V., Klimenko, A., Knöpfle, K. T., Kochetov, O., Kornoukhov, V. N., Krause, P., Kuzminov, V. V., Laubenstein, M., Lindner, M., Lippi, I., Lubashevskiy, A., Lubsandorzhiev, B., Lutter, G., Macolino, C., Majorovits, B., Maneschg, W., Marshall, G., Misiaszek, M., Morella, M., Müller, Y., Nemchenok, I., Neuberger, M., Pandola, L., Pelczar, K., Pertoldi, L., Piseri, P., Pullia, A., Ransom, C., Rauscher, L., Redchuk, M., Riboldi, S., Rumyantseva, N., Sada, C., Sailer, S., Salamida, F., Schönert, S., Schreiner, J., Schütz, A-K., Schulz, O., Schwarz, M., Schwingenheuer, B., Selivanenko, O., Shevchik, E., Shirchenko, M., Shtembari, L., Simgen, H., Smolnikov, A., Stukov, D., Sullivan, S., Vasenko, A. A., Veresnikova, A., Vignoli, C., von Sturm, K., Wester, T., Wiesinger, C., Wojcik, M., Yanovich, E., Zatschler, B., Zhitnikov, I., Zhukov, S. V., Zinatulina, D., Zschocke, A., Zuber, K., Zuzel, G.

A search for full energy depositions from bosonic keV-scale dark matter candidates of masses between 65 keV and 1021 keV has been performed with data collected during Phase II of the GERmanium Detector Array (GERDA) experiment. Our analysis includes

Externí odkaz: http://arxiv.org/abs/2405.15954

NeuraChip: Accelerating GNN Computations with a Hash-based Decoupled Spatial Accelerator

Autor: Shivdikar, Kaustubh, Agostini, Nicolas Bohm, Jayaweera, Malith, Jonatan, Gilbert, Abellan, Jose L., Joshi, Ajay, Kim, John, Kaeli, David

Graph Neural Networks (GNNs) are emerging as a formidable tool for processing non-euclidean data across various domains, ranging from social network analysis to bioinformatics. Despite their effectiveness, their adoption has not been pervasive becaus

Externí odkaz: http://arxiv.org/abs/2404.15510