Sort by
Refine Your Search
-
Category
-
Program
-
Field
-
The detection of out-of-distribution (OoD) samples is crucial for deploying deep learning (DL) models in real-world scenarios. OoD samples pose a challenge to DL models as they are not represented
-
collaboration with other CEA teams, notably ; * Parallel and cluster computing environment and efficient LP/MILP algorithms for our large-scale models ; * Data structuring and storage solutions for model input
-
following areas: * Global economic analysis of long-term investment pathways , including the distribution of decarbonization effort across sectors and regions * Policy evaluation of global and sectoral
-
Aggregation [9], DP-SGD [10]. Analyze trade-offs between privacy and robustness in different scenarios, including non-i.i.d. data distributions. [1] Zhu et al. Deep Leakage from Gradients. NeurIPS 2019. [2
-
access to unevenly distributed underground storage, connect renewable-rich regions with industrial hubs and, in certain areas, limit the cost of reinforcing the electricity transmission network. CEA I-Tésé
-
challenges •Motivation to pursue a PhD in the same field The application should include CV, cover letter, and transcript of records. We offer: An internship in the heart of the Grenoble metropolitan area
-
:00 (UTC) Type of Contract Temporary Job Status Full-time Offer Starting Date 1 Jan 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to
-
required. This 6-month internship is part of the DIADEM-PEPR national project, and is designed for highly motivated candidates. The intern will have the opportunity to collaborate closely with PhD students
-
Study the SOA and approaches on LLMs/VLMs + reasoning, with emphasis on Ontologies and other formal Knowledge Representation approaches. • Research on the ways the interaction can be exploited and provide added value (e.g. conformity). • Propose, produce and integrate into experiments that...
-
on efficiency in surface, power consumption, and computing performance. Vision Transformers (ViTs) have recently demonstrated superior performance over Convolutional Neural Networks (CNNs) in a wide