Automatic modelling language variations for socially responsive chatbots

Conversational agents are increasingly present in our daily lives thanks to advances in natural language processing and artificial intelligence and are attracting growing interest. However, their ability to understand human communication in all its complexity remains a major challenge. This PhD project aims to model linguistic variation to develop agents capable of socially adaptive interactions, taking into account the socio-demographic profile and emotional state of their interlocutors. It also focuses on evaluating linguistic cues at different levels, leveraging both spoken and written language varieties, and assessing the generalization capacity of models trained on multilingual and multi-situational data, with the goal of improving interaction modeling with conversational agents.

Compositional Generalization of Visual Language Models

The advent of the foundation models led to increase the state-of-the art performance on a large number of tasks in several fields of AI, in particular computer vision and natural language processing. However, despite the huge amount of data used to train them, these models are still limited in their ability to generalize, in particular for a use case of interest that is in a specific domain, not well represented on the Web. A way to formalize this issue is compositional generalization, i.e. generalising to a new, unseen concept from concepts learned during training. This "generalization" is the ability to learn disentangle concepts and to be able to recombine
them into unseen composition when the model is in production. The proposed thesis will address this issue, aiming at proposing visual representations that enable generic visual language models to generalize compositionally within specific domains. It will investigate strategies to reduce shortcut learning, promoting deeper understanding of compositional structures in multimodal data. It will also address the problem of compositional generalization beyond simple attribute–object pairs, capturing more subtle and complex semantics. The proposed thesis aims at proposing preogress at a quite theoretical level but has many potential practical interest, in the fields of health, administration and services sectors, security and defense, manufacturing and agriculture.

Artificial Intelligence for Integrated Electronics Design

As the technology fabrication processes improve towards nanometer-scale nodes, it is more and more complex to maintain the performance increase foreseen by Moore Law. To cope with this issue, technology processes provide various enhancing featuresi. More over, elementary components such as logic gates become legion. Providing a relevant design framework thus becomes a huge manual development task. As AI grows, it shows its skill to help decision making and hence components design, shaping a promising candidate to automate design flow. In this PhD subject, you will work on an AI model (LLM) capable of understanding electronic components. The works ultimately aim at developing a generation engine for electronic components.
Throughout this PhD, interdisciplinary research works will encompass a broad spectrum of knowledge around integrated electronics design, spanning microelectronics processes, electronic functions and logic gates implementation, neural networks architectures, large language models and generative AI.

Towards real-time simulation of thermal scenes in a tokamak to support plasma operations.

Monitoring the surface temperatures and heat fluxes of the walls in nuclear fusion devices is crucial for the operation of fusion machines. To ensure the reliability of these measurements, particularly through infrared imaging, CEA is developing a digital twin capable of modeling the entire infrared (IR) measurement chain, from the thermal source to the sensor.
The objective of this thesis is to create a thermal model that can predict heat fluxes and surface temperatures across the entire machine wall, with a goal of real-time computation. This approach is based on two key developments:
1)Development of a Monte Carlo statistical method: This method will solve the heat equation over large geometries in a complex environment, including a variety of heat sources and materials.
2)Acceleration of calculations on graphics processing units (GPU): Utilization of the Kokkos environment to optimize calculation performance while ensuring portability across all high-performance computing (HPC) platforms.
These developments will be validated and quantitatively evaluated on two experimental platforms: the laboratory test bench MAGRYT and the WEST tokamak, used as a demonstrator machine. The thesis will be conducted in a collaborative framework between CEA/DRF/IRFM and CEA/DES/ISAS. The developments will be integrated into the IR digital twin developed by CEA/IRFM for fusion machines and within a dedicated ray-tracing application for CEA/DES.

Towards a low-resistive base contact for the InP-HBT transistor

Join CEA LETI for an exciting technological journey! Immerse yourself in the world of III V
based transistors integrated on compatible CMOS circuits for 6 G future communications
This thesis offers the chance to work on a ambitious project, with potential to continue into
a thesis If you're curious, innovative, and eager for a challenge, this opportunity is perfect
for you!

As the consumption of digital content continues to grow, we can foresee that 6 G
communication systems will have to find more capacity to support the increase in traffic
New Sub THz frequencies based systems are a huge opportunity to increase data rate but
are very challenging to build and maturate the power amplifier required to transmit a
signal will have to offer sufficient power and energy efficiency which is not obtained with
actual silicon technology InP based HBTs (Heterojunction Bipolar Transistors) developed
on large Silicon substrates have the potential to meet the requirements and be integrated
as close as possible to the CMOS circuits to enable minimal system/interconnect losses
Sb based semiconductors for GaAsSb HBT are emerging as highly promising materials,
especially for its electrical properties to integrate the Base layer of the Transistor It is
therefore necessary to produce high performance electrical contacts on this type of
semiconductor while remaining compatible with the manufacturing processes of the Si Fab
technology platforms
Throughout
this thesis, you will gain a broad spectrum of knowledge, beneficiate from the
rich technical environment of the 300 200 mm clean room and the nano characterization
platform You will collaborate with multidisciplinary teams to develop a deep understanding
of the ohmic contacts and analyse existing measurements Several apsects of the metal
(Ni or Ti p GaAs 1 x Sb x contact will be investigated
•Identify wet and plasma solutions allowing the GaAsSb native oxide removing without
damaging the surface with XPS and AFM
•Characterize GaAs 1 x Sb x epitaxy doping level (Hall effect, SIMS, TEM)
•Understand the phase sequence during annealing between the semiconductor and the
metal with XRD and Tof SIMS Manage this intermetallic alloys formation to not
deteriorate the contact interface (TEM image associated)
•Evaluate electrical contact properties using TLM structures Measurement of the
specific contact resistivity, sheet resistance of the semiconductor ant transfer length
associated The student will be a motive force to perform electrical tests on an automatic prober

architecture for embedded system of Automated and Reliable Mapping of indoor installations

The research focuses on the 3D localization of data from measurements inside buildings, where satellite location systems, such as GPS, are not operational. Different solutions exist in the literature, they rely in particular on the use of SLAM (Simultaneous Localization And Mapping) algorithms, but the 3D reconstruction is generally carried out a posteriori. In order to be able to propose this type of approach for embedded systems, a first thesis was carried out and led to a choice of algorithms to embed and a draft of the electronic architecture. A first proof of concept was also realized. Continuing this work, the thesis will have to propose a method allowing the localization device to be easily embedded on a wide range of nuclear measuring equipment (diameter, contamination meter, portable spectrometry, etc.). The work is not limited to a simple integration phase; it requires an architectural exploration, which will be based on adequacy between algorithm and architecture. These approaches will make it possible to respect different criteria, such as weight and small size so as not to compromise ergonomics for the operators carrying out the maps and quality of the reconstruction to ensure the reliability of the input data for the Digital Twin models.

Bayesian Neural Networks with Ferroelectric Memory Field-Effect Transistors (FeMFETs)

Artificial Intelligence (AI) increasingly powers safety-critical systems that demand robust, energy-efficient computation, often in environments marked by data scarcity and uncertainty. However, conventional AI approaches struggle to quantify confidence in their predictions, making them prone to unreliable or unsafe decisions.

This thesis contributes to the emerging field of Bayesian electronics, which exploits the intrinsic randomness of novel nanodevices to perform on-device Bayesian computation. By directly encoding probability distributions at the hardware level, these devices naturally enable uncertainty estimation while reducing computational overhead compared to traditional deterministic architectures.

Previous studies have demonstrated the promise of memristors for Bayesian inference. However, their limited endurance and high programming energy pose significant obstacles for on-chip learning applications.

This thesis proposes the use of ferroelectric memory field-effect transistors (FeMFETs)—which offer nondestructive readout and high endurance—as a promising alternative for implementing Bayesian neural networks.

Dynamics of a very high temperature heat pump coupled to a thermal storage system. Experimental and numerical study.

In the context of an electricity mix with a high proportion of intermittent renewable energy sources, massive energy storage solutions will be of major interest. For the vast majority of these solutions, electricity is converted into energy that can be stored on a large scale (e.g. pressure energy, chemical or electrochemical energy, etc.), then converted back into electricity. Losses occur during each of these stages (conversion, storage), so the efficiency of the complete system is an important issue and requires a good understanding of each conversion and storage stage.
The innovative system that we want to study is a Carnot battery, i.e. a thermal battery associated with thermodynamic conversion cycles (electrical energy to thermal energy to electrical energy). The anticipated advantages are numerous: the possibility of integrating thermal flows, the absence of geographical constraints, a degree of freedom in the choice of temperatures and storage materials, the use of alternators for inertia, etc. The identified challenges are reactivity and overall efficiency.
The research will focus on the charging cycle (very high temperature heat pump) and its coupling with thermal storage, initially from a static and then a dynamic perspective. Unsteady numerical modelling will be developed and used to design the Carnot battery system. Tests carried out on an experimental installation at the CEA will be used to validate and enhance the modelling results.

Field Effect Transistor with Oxide Semiconductor Channel: Multi-Level Synaptic Functions and Analog Neurons

This thrilling PhD position invites you to dive into the groundbreaking field of 2T0C (Two-Transistor, Zero-Capacitor) BEOL FET (Back-End-of-Line Field-Effect Transistor) based neurons and synapses, a revolutionary approach poised to transform neuromorphic computing. As a PhD student, you will be at the forefront of research that bridges advanced semiconductor technology with brain-inspired architectures, exploring how these innovative neuron circuits can emulate synaptic functions and enhance data processing efficiency.
Throughout this project, you will engage in hands-on design and characterization of cutting-edge 2T0C neuron circuits, utilizing state-of-the-art tools and techniques. You’ll collaborate with a dynamic, multidisciplinary team of engineers and researchers, tackling exciting challenges related to device performance and energy optimization.
Your work will involve extensive characterization of BEOL FET devices and circuits. You will have the opportunity to propose, specify and design new memory read architectures, that enables the exploration of multi-level synaptic behaviors toward the implementation of more energy and area efficient next-generation neuromorphic systems.
Join us for this unique opportunity to push the boundaries of technology and be part of a transformative journey that could redefine the future of computing! Your contributions could pave the way for breakthroughs in brain-inspired systems, making a lasting impact on the field.

Superconducting RF Filters for Quantum Applications

Within the Quantum Devices Laboratory, you will work in an environment ranging from fundamental physics to new nano-electronics technologies, with a team that collaborates closely with quantum computing startups and physicists from CEA-IRIG and Institut Néel.
The operating conditions of qubits (cryogenic temperatures <= 1K, GHz frequencies , high signal density) require the development of suitable components and technological bricks. In particular, the passive radiofrequency components developed around the CEA-LETI superconducting interposer technology show extremely interesting electrical properties up to several GHz. These elements, including inductors available over wide value ranges, have already made it possible to establish the first proofs of concept for very compact and low-loss RF filters. The integration of superconducting materials now makes it possible to envisage the creation of new high-performance filters adapted to signal management in cryogenic environments.
You will be required to develop your expertise in the physics of materials and superconducting components. You will study the different superconducting filters that exist in the scientific literature. Using the models developed in the laboratory and the results of the RF measurements in which you will participate, and relying on 3D RF electromagnetic simulation, you will contribute to the design of different RF filters and functions that meet the needs of cryogenic applications.

Top