Program

You can find the slides used during the presentations on this link : https://cirrus.universite-paris-saclay.fr/s/MKqnt6E3GexK929

Thursday 26th September

• 08:45 – 09:15 Coffee & Registration
• 09:15 – 09:30 Opening speech
• 09:30 – 10:30 Keynote: Deep Learning in protein-protein interactions, Alessandra Carbone, Professor, Sorbonne Université
• 10:30 – 11:00 Coffee break
• 11:00 – 12:00 Student presentations
  • A stock region predictor for path clearing with object manipulation, Kai Zhang, Eric Lucet, Julien Alexandre Dit Sandretto, David Filliat
  • Highlighting hurdles to benchmarking machine learning methods, Célestin Eve, Thomas Moreau, Gael Varoquaux
  • Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence, Clémentine Chazal
• 12:00 – 13:00 Lunch break
• 13:00 – 14:00 Keynotes:
  • Trajectoire d’une Startup Deep Tech en IA : De l’IA Exploratoire pour les Industries à l’IA Générative pour le Droit, Anthony Coutant, Cofounder/Co-CEO, CTO HephIA
  • AI Agent Precision: Maximizing Decision Accuracy with Business Rules Integration, Harley Davis, Athena Decision Systems
• 14:00 – 15:00 Students presentations:
  • Label Leakage from Regression Models Gradients in Federated Learning, Jean Leprovost, Pierre Jobic, Aurélien Mayoue
  • A New Efficient Algorithm for Exact Multiple Change Point Detection in Time Series, Simon Querné, Vincent Runge
  • Semantic-Based Dataset Discovery in Data Lakes, KAID Nassima
• 15:00 – 16:30 Student poster session (pitch and poster):
  • Efficient Vertical Federated Learning: Leveraging Foundation Models to Improve Communication, Xavier Desprez, Oudom Kem
  • ML-DOA estimation using a sparse representation of array covariance, Thomas Aussaguès, Anne Ferréol, Alice Delmer, Pascal Larzabal
  • Exploring quasi-optimal contraction strategies for fast scalar product in Tensor-Train format, Przemyslaw Dominikowski
  • BEST POSTER AWARD AdaptiveCausalWVAE: Certifiably Robust and Stable Causal Disentanglement with Lipschitz-Constrained Spline Neural Networks, Manal Benhamza
  • Predictive Modeling of Fluid Flows Using Conditional Score-Based Diffusion Models, Wilfried Genuist, Eric Savin, Filippo Gatti, Didier Clouteau
  • Schema Discovery for Property Graphs, Yuzhan Wang
  • Finite-sample performance of the maximum likelihood estimator in logistic regression, Hugo Chardon
  • Deep multivariate autoencoder for capturing complexity in Brain Structure and Behaviour Relationships, Gabriela P. Gomez Jimenez
  • Constituting a dataset for applying Natural Language Inference to Chinese Clinical Trials: possible approaches and challenges, Mathilde Aguiar, Ying Lai, Pierre Zweigenbaum, Nona Naderi
  • Named Entity Extraction in Connection Lens Based on Large Language Models, Minh Hoang Duong, Ioana Manolescu

Friday 27th September

• 09:00 – 9:15 Coffee viennoiseries & Registration
• 9:15 – 10h15 Keynote: Data and AI techniques for Fact-checking and Investigative journalism, Ioana Manolescu, Senior Researcher, INRIA
• 10:15 – 10:45 Coffee break
• 10:45 – 11:45 Student presentations:
  • A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning, Amadou Siaka Sangare, Nicolas Dunou, Jhony H. Giraldo, Fragkiskos D. Malliara
  • BEST PRESENTATION AWARD Max-plus algebra in deep neural networks, Ikhlas Enaieh
  • Identifying GANs Blind Spots in Transcriptomic Data Generation, Assmaa Alsamadi, Alice Lacan, Blaise Hanczar, Michele Sebag
• 11:45 – 12:00 Presentation of IDIA, GS ISN/SIS and DATAIA
• 12:00 – 12:15 Best presentation and poster awards
• 12:15 – 13:45 Lunch