Research
Date & Location
- May 16, 2025
- Centre Inria d'Université Côte d'Azur
Program
10:30 - 10:40
Madina Bekbergenova (Université Côte d'Azur - ICN, PhD)
lash presentation: MetaboT: AI-based agent for natural language-based interaction with metabolomics knowledge graphs
Abstract: MetaboT is an AI system that leverages large language models to translate natural language questions into SPARQL queries for metabolomics knowledge graphs (KGs). Built with LangChain and LangGraph, it uses specialized agents to extract entities and chemical taxonomies, construct ontology-informed queries, and retrieve structured results from a public plant metabolomics KG. Evaluated on 50 questions, MetaboT achieved 84% accuracy, vastly outperforming a GPT-4o baseline (8%), highlighting the advantage of its multi-agent design. By automating SPARQL query generation and execution, MetaboT lowers technical barriers, enabling researchers to easily access and explore complex metabolomics data.
Access it.
10:40 - 11:00
Xufeng Zhang (Inria - Team Neo, PhD)
Memory-efficient online caching Policies with regret guarantees
Abstract: Online learning algorithms provide robust performance in caching problems but require substantial memory to store per-file historical data, limiting their scalability to large-catalog systems. To overcome this challenge, we propose a dimensionality reduction algorithm based on the Follow-the-Perturbed-Leader framework and the Johnson-Lindenstrauss lemma. Our method significantly reduces memory consumption while preserving sublinear regret, making it well-suited for caching under resource constraints. Experiments on both synthetic and real-world traces demonstrate its advantages over other memory-efficient approaches.
11:00 - 11:20
Cloé Mahé (Université Côte d'Azur, PhD)
First robust census of binary supermassive black holes : Deep Learning techniques applied to the Euclid space mission.
Abstract: The formation of dual and binary supermassive black holes (SMBH) is a solid prediction of the current hierarchical model of galaxy formation [1]. By studying these objects, several astrophysical questions can be addressed, related to the galaxy mass build-up, the feedback of active galaxy nuclei (AGN) on the star formation history of galaxies, or the expected amount of gravitational waves due to the final merging process of the SMBH pair [2]. Detecting such rare systems require simultaneously high angular resolution capabilities and a large surveyed sky area. The ongoing ESA space mission Euclid is groundbreaking in both regards, and offers therefore an unprecedented opportunity to detect and study numerous dual systems. In this talk, I will present the first part of a methodology designed to automatically identify dual systems in the Euclid surveys, based on Machine Learning (ML) and Deep Learning (DL) techniques. The identification of the galaxies harbouring double or dual SMBH in the Euclid images will be done using a Convolutional Neural Network (CNN). As observations of genuine dual objects are scarce, we rely on the objects tagged as dual AGN in the Horizon-AGN cosmological simulation [3] to construct the CNN training database. However, since there are still very few identified systems, it is first necessary to increase the number of such images from the Horizon-AGN dataset.
To do this data augmentation process, I constructed a Variational Autoencoder (VAE) [4] that I combined to a normalizing flow [5], allowing one to generate synthetic images of dual AGN with similar properties (total flux, Gini shape parameter) and visual aspects as the initial images extracted from the simulation. I will present the technical properties of this model, including its structuration, the definition of losses, and the diagnostics used to inquire its capabilities. Using this flow-VAE model, producing a large set of images of dual AGN fulfilling a specified distribution of physical properties is feasible in a fragment of the time necessary to generate such images from the Horizon-AGN simulation.
References
11:20 - 12:00
Open discussion about the two contributions
Event reserved for students and post-docs of the 3IA consortium members. ID check at the entrance of the site with visual bag inspection.
- Save the Date!
- Next Seminars:
June 6, 2025 (Campus Valrose, Nice) - Past Seminars
-
Doctoral & Postdoctoral Seminar #44
Speakers:
- Manasi Kattel (Inria, PhD) | Flash presentation: MRI-Ultrasound Image Registration for Prostate Cancer Care
- Francesco Diana (Inria, PhD) | Attribute Inference Attacks for Federated Regression Tasks
- Alexey Sergeyev (Université Côte d'Azur, Researcher) | Asteroids in the Digital Age: Insights from Modern Sky Surveys
Doctoral & Postdoctoral Seminar #43
Speakers:
- Xufeng Zhang (Inria, PhD) | Flash presentation: Online optimistic caching with switching cost
- Lisa Guzzi (Inria, PhD) | Differentiable Soft Morphological Filters for Improving Arterial Segmentation in Peripheral Artery Disease
- Luc Lehéricy (Université Côte d'Azur, Researcher) | Deconvolution with unknown noise distribution for structured signals
Doctoral & Postdoctoral Seminar #42
Speakers:
- Morgane Fierville (IPMC CNRS - Université Côte d'Azur) | Flash presentation: Spatial transcriptomics of the human lung from health to pathologies
- Davide Adamo (PhD, CEPAM lab / INRIA) | Rethinking Multiple Kernel Learning under the lenses of Variational Inference
- Emmanuel Bouilhol (Postdoc, I3S Université Côte d'Azur) | ECMQuant: Quantitative Analysis of the Tumor Extracellular Matrix in Head and Neck cancer
Doctoral & Postdoctoral Seminar #41
Speakers:
- Seydina Niang (PhD, Université Côte d'Azur / Inria) | Flash presentation: Deep generative models for the joint analysis of networks and continuous
- Greta Damo (PhD, Université Côte d'Azur / Inria) | Detecting and Countering Hate Speech Messages on Social Media
- Benjamin Billot (Researcher, INRIA) | Domain-agnostic segmentation of brain MRI scans
Doctoral & Postdoctoral Seminar #40
Speakers:
- Olivier Bisson (PhD, INRIA) | Flash presentation: Geometry, stratification and applications of structured correlation matrices
- Tomasz Stanczyk (PhD, INRIA) | Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking
- Jean-Pierre Merlet (3IA Chairholder, INRIA) | Solving parametric systems of equations with neural network
Doctoral & Postdoctoral Seminar #39
Speakers:
- Margaux SCHMIED (PhD, UCA) | Flash presentation: Improving assignment problems with costs
- Victor DAVID (Researcher, INRIA) | An Axiomatic Study of the Evaluation of Enthymeme Decoding in Weighted Structured Argumentation
- Rémy SUN (Researcher, INRIA) |
Doctoral & Postdoctoral Seminar #38
Speakers:
- Rafael Silva (PhD, Inria) | Flash presentation: Signal Processing and Artificial Intelligence for Cardiac Monitoring
- Eloise Da Cunha (PhD, UCA) | Speech-Based Detection of Motor and Physical Deficits in the geriatric population
- Valeriia Rezapova (PhD, UCA) | Computational analysis on mature osteoclast transcriptome revealed the existence of 3 osteoclast lineages with different functional, metabolic and regulatory properties
Doctoral & Postdoctoral Seminar #37
Speakers:
- Vincenzo Marciano (PhD, EURECOM) | Flash presentation
- Mariam Grigoryan (PhD, Inria) | Identification of Molecular Patterns for Chemical Safety Assessment
- Mathieu Carrière (Research Scientist, Inria) | Diffeomorphic interpolation for efficient topological optimization
Doctoral & Postdoctoral Seminar #36
Speakers:
- Pierpaolo Goffredo (PhD, CNRS - I3S) | Argument-based Detection and Classification of Fallacies in Political Debates
- Célian Ringwald (PhD, Inria - I3S) | Impact of Syntaxes on Data Extraction with Language Models
Doctoral & Postdoctoral Seminar #35
Speakers:
- Edoardo Sarti (permanent researcher, INRIA) | Spectral partitioning into protein structural domains
- Lucile Sassatelli (full professor, Université Côte d'Azur) | Visual objectification in films as a new AI task
Doctoral & Postdoctoral Seminar #34
Speakers:
- Gonzague Radureau (PhD, OCA) | A new high-performance computation method of the Eddington tensor in radiation hydrodynamics simulation
- Stefan Sarkadi (KCL, INRIA) | Deceptive AI and Society
Doctoral & Postdoctoral Seminar #31
Speakers:
- Ryan Cotsakis (UniCA) | The extremal range: a local statistic for studying spatial extremes
- Sara Frusone (UniCA) | Identifying spatiotemporal dispersion in catheter ablation of persistent atrial fibrillation: a comparative study of machine learning techniques using both real and realistic synthetic multipolar electrograms
Doctoral & Postdoctoral Seminar #30
Speakers:
- Francesco Galati (EURECOM) | A Single Model Strategy for Multi-Domain Cerebrovascular Segmentation
- Luca Calatroni (CNRS, I3S) | Physics-inspired learning for fluctuation-based super-resolution microscopy
Doctoral & Postdoctoral Seminar #29
Speakers:
- Hava Chaptoukaev (EURECOM) | AI for e-health: Stress Identification from Multimodal Data
- Louis Ohl (Inria) | Generalised mutual information (GEMINI) - A constellation of discriminative clustering models
Doctoral & Postdoctoral Seminar #28
Speakers:
- Matej Hladis (UniCA) | Matching receptor to odorant with protein language and graph neural networks
- Elena Di Bernardino (3IA chair, UniCA) | Geometry of excursion sets: a statistical and computational point of view
Doctoral & Postdoctoral Seminar #27
Speakers:
- Faisal Jayousi (CNRS) | Geometric and statistical analysis of the extracellular matrix
- Oualid Zari (EURECOM) | Privacy Attacks in Machine Learning and Defenses
Doctoral & Postdoctoral Seminar #26
Speakers:
- Nissim Maruani (Inria) | VoroMesh: Learning Watertight Surface Meshes with Voronoi Diagrams
- Julien Aubert (CNRS) | On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm
Doctoral & Postdoctoral Seminar #25
Speakers:
- Stefano Spaziani (CNRS) | Estimating the functional connectivity in the brain via a multiscale spike-LFP autoregressive model
- Virginia d'Auria (invited researcher) | Quantum information science
Doctoral & Postdoctoral Seminar #24
Speakers:
- Zhijie Fang (Inria) | Landmark detection via convolutional neural network
- Josué Tchouanti (CNRS LJAD) | Detection of neural synchronization and implication for neuroscience experimental design
Doctoral & Postdoctoral Seminar #23
Speakers:
- Thi Khuyen Le (Inria) | Comparison of handcrafted radiomics and 3D-CNN models to diagnose striatal dopamine deficiency in Parkinsonian syndromes based on 18F-FDOPA PET images
- Irene Balelli (external researcher - Inria) | The search for causality in the analysis and modeling of biomedical data
Doctoral & Postdoctoral Seminar #22
Speakers:
- Valerya Strizhkova (Inria) | Multi-View Video Masked Autoencoder for Emotion Recognition
- Lucie Cadorel (invited outside 3IA - I3S & Inria) | Geospatial Knowledge in Real Estate Listings : Extracting and Localizing Uncertain Spatial Information from Text
Doctoral & Postdoctoral Seminar #21
Speakers:
- David Loiseaux (Inria) | Towards multiparameter persistent homology descriptors for machine learning
- Alessandro Betti (Inria) | Deep Learning to See
Doctoral & Postdoctoral Seminar #20
Speakers:
- Yacine Khacef (Université Côte d'Azur) | High-Resolution Traffic Monitoring with Distributed Acoustic Sensing and AI
- Daniel Inzunza (Inria) | A PINN approach for traffic state estimation and model calibration based on loop detector flow data
Doctoral & Postdoctoral Seminar #19
Speakers:
- Lucia Innocenti (Inria) | Analysis of Multi-centric AI-based frame-works in prostate segmentation
- Riccardo Taiello (Inria) | Privacy Preserving Image Registration
Doctoral & Postdoctoral Seminar #18
Speakers:
- Rémi Felin (UCA, I3S) | Optimizing the Computation of a Possibilistic Heuristic to Test OWL 2 SubClassOf Axioms Against RDF Data
- Huiyu Li (Inria, Epione) | Data Stealing Attack on Medical Images: Is it Safe to Export Networks from Data Lakes?
Doctoral & Postdoctoral Seminar #17
Speakers:
- Benjamin Ocampo (UCA, I3S) | "We Need Two Poke Flutes to Wake You Up'' an In-depth Analysis of Implicit and Subtle Hate Speech Messages
- Tong Zhao (Inria) | Progressive Discrete Domains for Implicit Surface Reconstruction
Doctoral & Postdoctoral Seminar #16
Speakers:
- Prof. Ludovic Dibiaggio | Introduction to the OTESIA institute
- Daniel Inzunza (Inria) | PINNs approach for traffic model calibration
- Angelo Rodio (Inria) | Resource-aware Federated Learning
Doctoral & Postdoctoral Seminar #15
Speakers:
- Andrea Castagnetti (UCA, LEAT) | Neural information coding for efficient spike-based image denoising
- Christos Bountzouklis (UCA, LJAD) | Environmental factors affecting wildfire-burned areas in southeastern France
Doctoral & Postdoctoral Seminar #14
Speakers:
- Antonia Ettorre (UCA, I3S) | A systematic approach to identify the information captured by Knowledge Graph Embeddings
- Victoriya Kashtanova (Inria) | Deep Learning Approach for Cardiac Electrophysiology Modeling
Doctoral & Postdoctoral Seminar #13
Speakers:
- Aude Sportisse (Inria) | Informative labels in Semi-Supervised Learning
- Alexandra Würth (Inria) | Data driven traffic management by Macroscopic models
Doctoral & Postdoctoral Seminar #12
Speakers:
- Hind Dadoun (Inria) | AI-based Real Time Diagnosis of Abdominal Ultrasound Images
- Victor Jung (UCA) | Checking Constraint Satisfaction
Doctoral & Postdoctoral Seminar #11
Speakers:
- Bogdan Kozyrskiy (EURECOM) | Binarization for Optical Processing Units via REINFORCE
- Paul Tourniaire (Inria) | Attention-based Multiple Instance Learning for Histopathology
Doctoral & Postdoctoral Seminar #10
Speakers:
- Etrit Haxholli (Inria) | On the Estimation of Shape Parameters of Tails of Marginal Distributions
- Cedric Vincent-Cuaz (UCA) | Semi-relaxed Gromov-Wasserstein divergence with applications on graphs
Doctoral & Postdoctoral Seminar #9
Speakers:
- Santiago Marro (CNRS) | Natural Language Argumentation Quality Assessment maps
- Artem Muliukov (UCA) | Cortex-inspired multimodal AI approach based on self-organizing
Doctoral & Postdoctoral Seminar #8
Speakers:
- Kristof Huszar (Inria) | Towards Efficient Algorithms in Computational Topology
- Mauro Zucchelli (Inria) | Diffusion MRI based Brain Tissue Microstructure Characterization Using Autoencoder Neural-Networks
Doctoral & Postdoctoral Seminar #7
Speakers:
- Vasiliki Stergiopoulou (CNRS) | COL0RME: Super-Resolution Microscopy Based on the Localization of Sparse Blinking Fluorophores
- Ali Ballout (UCA) | Predicting the Possibilistic Score of Atomic Candidate OWL Axioms
Doctoral & Postdoctoral Seminar #6
Speakers:
- Hugo Schmutz (Inria) | Towards safe deep semi-supervised learning
- Amirhossein Tavakoli (MINES ParisTech) | Hybrid combinatorial optimization and machine learning algorithms for energy-efficient water network
Doctoral & Postdoctoral Seminar #5
Speakers:
- Ayse Unsal (Eurecom) | A Statistical Threshold for Adversarial Classification in Laplace Mechanisms
- Ashwin James (CNRS) | Inference of choice granularity via learning model selection in a cognitive task
Doctoral & Postdoctoral Seminar #4
Speakers:
- Mohsen Tabejamaat (Inria) | Conditional image generation using structural priors
- William Hammersley (UCA) | Randomizing gradient descents on the space of probability measures
- Athanasios Vasileiadis (UCA) | Exploration noise for Mean Field Games
Doctoral & Postdoctoral Seminar #3
Speakers:
- Amar Bouali (3IA Côte d'Azur) | Introduction to the Partnership and Innovation initiatives of 3IA Côte d'Azur
- Antoine Collin (CNRS) | Automatic cell type annotation for cell atlas construction
- Ziming Liu (Inria) | High-resolution Detection Network for Small Objects
Doctoral & Postdoctoral Seminar #2
Speakers:
- Aurélie Delort (3IA Côte d'Azur) | Presentation of the Education & Training program
- Boris Shminke (CNRS) | Using Denoising Autoencoder for Cayley table completion task
- Dingge Liang (Inria) | A Deep Latent Recommender System based on User Ratings and Reviews
- Martijn Van Den Ende (UCA) | Fibre-optics, earthquakes, and a zebra: intelligent signal denoising with Deep Learning
Doctoral & Postdoctoral Seminar #1