Sort by
Refine Your Search
-
Scaling analog in-memory computing towards large generative AI models H/F Subject Your work will span device-to-algorithm co-design, focusing on state-of-the-art small language model engineering and
-
, August). ExaNBody: A HPC framework for n-body applications. In European Conference on Parallel Processing (pp. 342-354). [2] https://github.com/MarcJos/Merope [3] https://github.com/MarcJos/RSA_MPI
-
algorithm-hardware co-design of adaptive Transformer architectures using ReRAM analog in-memory computing. Using PyTorch and in-house ReRAM characterization data, you will develop reference models and
-
will initially focus on algorithm development and simulation. Starting from reference methods, you will evaluate different strategies and progressively incorporate realistic ReRAM device characteristics
-
will involve: - Understanding the various sensors. - Implementing a calibration algorithm using AI-based methods. - Adopting a rigorous scientific approach to validate the relevance of the proposed
-
Sécurité Matérielle, CEA-LETI, 07 86 86 15 21, [email protected] [1] https://spectreattack.com/spectre.pdf [2] https://meltdownattack.com/meltdown.pdf [3] https://openhwfoundation.org/ [4
-
conditions de fragmentation). [1] Rutz,A. et al. (2026) MultiMS2: A curated multi-modal, multi-energy spectral library for metabolomics. Gigascience. (https://doi.org/10.1093/gigascience/giag069). [2
-
avec le serveur HTTP. Ces serveurs suivent pour la plupart la même architecture et utilisent des outils similaires, tels que Kerberos[1], Celery[2], Apache[3] ou Flask[4]. [1] https
-
quantification ainsi que sur le framework de deep learning, développé au LIAE, pour le profiling, la compression et l’export sur cible matérielle (Aidge[3]). [1] https://le-wm.github.io/ [2] https
-
d’Aidge (framework de deep learning développé au LIAE), leurs évaluations et leurs validations sur cible. Quelques références: - Cross-Architecture KD: https://openaccess.thecvf.com/content/ACCV2022