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.
Modelling a flexible methanol production process adapted to kerosene production
To decarbonize air transport, the use of a growing share of less carbon-rich SAF (Substitute Air Fuels) will be mandatory. One of the most studied processes is MTO (Methanol To Olefins) which consists in producing methanol from carbon capture and water electrolysis, then reacting it to produce olefins.
The simulations of this process carried out previously at LSET considered continuous operation of the installation (ProSim Plus models).
Scientific issue to be addressed
In the perspective of decarbonisation of e-kerosene, the use of ENR electricity seems essential, which implies the study of the process under dynamic regime.
Study techniques
The complete system (CO2 capture, high temperature electrolysis, methanol loop, MTO reaction and purifications) should be simulated in dynamic mode. The software considered is Dymola for the process part. It can then be adapted to be integrated into a larger system with PERSEE
Several modes of system constraints are possible (ENR profile, kerosene demand curve,...).
Expected results
The dynamic model should give:
Size and cost of equipment;
Size and position of optimal storage;
Energy requirements and system efficiency;
Cost of kerosene produced.
Development of new strategies for robotic computed tomography with variable magnification
The Department of Numerical Instrumentation joins expertise on different research fields through experimental and software platforms. In the Monitoring, Control and Diagnostic Unit, one of the important research areas is the industrial inspection with X-ray methods. Within this framework, a robotic inspection facility is being employed for innovative research and validation of new algorithms and on instrumentation aspects.
One of the most important features of robotic inspection is the possibility to scan large samples. In most application cases, region-of-interest areas are defined, for which a higher spatial resolution is targeted. In this context, a research program covering several topics is proposed, with the main objective of facilitating the setup and the use of the robotic inspection configuration for industrial application cases. A focus can be set on one or two research topics, depending on the background and on personal R&D interests and initiatives of the candidate.
A first topic will consist of developing CT reconstruction algorithms for a scan configuration using a variable magnification ratio, in a first phase with analytical algorithms such as the one proposed by Dennerlein [1] and then to adapt iterative reconstruction algorithms of SART type.
A second topic will consist on a work related to adapt the algorithms towards a multi-resolution representation of the reconstructed volumes, through octree or wavelet decomposition. An approach involving the correlation of experimental data to the CAD model of the sample will allow a better implementation in order to improve the VOI (volume of interest) tomography.
A third topic focused on instrumentation will deal with the experimental validation and additionally it will aim to develop a system capable to verify the accurate positioning of the scene elements with the help of precision distance sensors. A simultaneous measure of the distance source - to part surface together with the radiographic image will allow implementing corrections for positioning errors for every scan point and in a second phase to use this additional information directly in the reconstruction process.
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.
Miniaturized fluidized bed for the efficient capture of patogens
Sepsis is a generalized, inappropriate immune response to the presence of microorganisms in the blood. This condition is a major public health problem, accounting for over 11 million deaths worldwide every year. One of the reasons for this high mortality rate is the difficulty in rapidly identifying the pathogen involved, thus delaying the rapid administration of appropriate treatment.
This thesis project, in conjunction with the IHU PROMETHEUS, focuses on the development of miniaturized fluidized beds to concentrate blood biomarkers of sepsis, present in trace amounts in biological matrices. This method, based on the use of microfluidic technology, has the potential to replace lengthy blood culture methods, enabling rapid capture and subsequent identification of enriched targets. Thanks to their high flow rates, very large capture surface area and rapid exchange kinetics, the fluidized beds developed for nucleic acid capture will revolutionize the rapid diagnosis of sepsis.
We propose to develop three axes during this thesis project: 1) development and characterization of the miniaturized fluidized bed; 2) analysis of the system's performance with synthetic DNA; 3) validation of the developed system with model biological samples containing bacterial DNA. This DNA analysis system will pave the way for microfluidic analysis of other sepsis biomarkers.
Interface physics of ferroelectric AlBN/Ga2O3 and AlBN/GaN stacks for power electronics
Commercial aviation accounts for about 2.5% total world CO2 emissions (1bT). A true, long-term, clean perspective eliminating a significant part of CO2 emissions is electric. One viable solution could be the hybrid airplane in which gas turbines are used for take-off and landing and in-flight cruising is electrically powered. Such a solution requires high voltage components. Fundamental research is required to optimize materials for integration into electronic components, capable of sustaining these power ratings.
The original idea of the Ferro4Power proposal is to increase the range of applications of Ga2O3 and GaN based devices by introducing a high breakdown, power electronics compatible, ferroelectric layer into the device stack. The up or down polarization state of the ferroelectric layer will provide an electric field capable of modulating the Ga2O3 and GaN valence and conduction bands, and hence the properties of possible devices, such as Schottky diodes (SBD), hybrid depletion mode transistors for Ga2O3 and high frequency HEMTs for GaN. Our hypothesis is to control the electronic bands of Ga2O3 and GaN using an adjacent AlBN.
We will explore the chemistry and electronic structure of AlBN/Ga2O3 and AlBN/GaN interfaces, focusing on the key phenomena of polarization screening, charge trapping/dissipation, internal fields. The project will use advanced photoelectron spectroscopy techniques including synchrotron radiation induced Hard X-ray photoelectron spectroscopy and Photoemission electron microscopy as well as complementary structural analysis including high-resolution electron microscopy, X-ray diffraction and near field microscopy.
The results should therefore be of interest to both physicists studying fundamental aspects of functionality in artificial heterostructures and engineers working in R & D applications of power electronics.
Merging Optomechanics and Photonics: A New Frontier in Multi-Physics Sensing
Optomechanical sensors are a groundbreaking class of MEMS devices, offering ultra-high sensitivity, wide bandwidth, and seamless integration with silicon photonics. These sensors enable diverse applications, including accelerometry, mass spectrometry, and gas detection. Optical sensors, leveraging photonic integrated circuits (PICs), have also shown great potential for gas sensing.
This PhD focuses on developing a hybrid multi-physics sensor, integrating optomechanical and optical components to enhance sensing capabilities. By combining these technologies, the sensor will provide unprecedented multi-dimensional insights, pushing MEMS-enabled silicon photonic devices to new limits.
At CEA-Leti, you will access world-class facilities and expertise in MEMS fabrication, photonics, and sensor integration. Your work will involve:
-Sensor Design – Using analytical Tools and simulation software for numerical analysis to optimize device architecture.
-Cleanroom Fabrication – Collaborating with CEA’s expert teams to develop the sensor.
-Experimental Characterization – Conducting optomechanical and optical evaluations.
-Benchmarking & Integration – Assessing performance with optics, electronics, and fluidics.
This PhD offers a unique chance to merge MEMS and silicon photonics in a cutting-edge research environment. Work at CEA-Leti to pioneer next-generation sensor technology with applications in healthcare, environmental monitoring, and beyond. Passionate about MEMS, photonics, and sensors? Join us and help shape the future of optomechanical sensing!
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.