Lecture materials and slides

Part of ELLIS Summer School on Large-Scale AI for Research and Industry, 18–22 September 2023. This event has ended: the information below is kept for reference.

Lecture slides

• Rita Cucchiara - Opening
• Lorenzo Baraldi - Program Overview, Student Projects and Practical information
• Giuseppe Fiameni - Larger-scale model training on multi-GPU systems
• Bernt Schiele - Interpretability for Deep Learning in Computer Vision
• Alberto Del Bimbo - Science Writing
• Sergio Orlandini - Larger-scale model training on multi-GPU systems
• Federico Tombari - 3D Scene Understanding
• Laura Leal-Taixé - From hand-crafted to end-to-end learning and back: a journey for MOT
• Fabian Manhardt - Neural Radiance Fields
• Fabian Manhardt - Neural Radiance Fields Notebook
• Cristian Canton Ferrer - Responsible AI in the age of GenAI: the case of Llama2
• Nicu Sebe - Cross-modal Video Generation
• Cees Snoek - Learning to Generalize in Video Space and Time
• Björn Schuller - Think Big: Entering Large Scale Affective Computing
• Pietro Perona - Responsible AI: Measuring accuracy and bias in Computer Vision Systems
• Mario Fritz - Trustworthy AI, a Cybersecurity perspective
• Victor Sanh - Training an open-access 80 billion parameters vision and language model, lessons learned
• Marc’Aurelio Ranzato - Modular Large-Scale Continual Learning
• SLURM usage statistics

Project reports

• 1 - Detecting and Watermarking text generated by Large Language Models 🏆
  Pierre Fernandez, Pavan Kartheek Rachabathuni, ANAMARIA-ROBERTA PREDA, Felipe Torrres Figueroa, Vitjan Zavrtanik, Roberto Amoroso, Robin San Roman
• 2 - Detecting and Watermarking text generated by Large Language Models
  Daryna Dementieva, Amelia Sorrenti, Badr Youbi Idrissi, Monica Millunzi, Lorenzo Baraldi
• 3 - Detecting and Watermarking text generated by Large Language Models
  Chenyu Zhang, Tural Mammadov, Federico Betti, Emmanouil Angelis, Megi Dervishi, Alberto Vitto
• 4 - Efficient Foundation Model Training Using FLIP 🏆
  Bo Wan, Luca Zanella, Francesco Tonini, Giancarlo Paoletti, Ayush Kumar Rai, Federico Cocchi
• 5 - Efficient Foundation Model Training Using FLIP
  Amir Hamza, Simone Alberto Peirone, Rochelle Choenni, Roman Pflugfelder, Tingyu Qu, Giuseppe Cartella
• 6 - Efficient Foundation Model Training Using FLIP
  Vitus Benson, Gorjan Radevski, Beatrice Portelli, Emanuele Vivoli, Mingxiao Li, Nicholas Moratelli
• 7 - Multi-Instance-Learning (MIL) models to Perform a Multi-Scale Classification of Large Histological Images (WSIs)
  Gennaro Iannuzzo, Rutger Hendrix, Andrea Favilli, Weronika Hryniewska-Guzik, Luca Lumetti, Mattia Paladino
• 8 - Multi-Instance-Learning (MIL) models to Perform a Multi-Scale Classification of Large Histological Images (WSIs)
  Alex Falcon, Ali Abdari, Roberto Basla, Putra Manggala, Sonali Andani, Giacomo Capitani
• 9 - Per-Object Distance Estimation from Monocular Images
  Davide Alessandro Coccomini, Jérôme Fink, BIN REN, Aniello Panariello, Luca Barsellotti, Enrico Martini
• 10 - Per-Object Distance Estimation from Monocular Images
  Federico Vasile, Giulia Castagnolo, Tsung-Ming (Nick) Tai, Matteo Fincato, Mirco De Marchi, Gianluca Mancusi
• 11 - Predicting gene and protein expression levels from DNA and protein sequences exploiting Transformer-based architectures
  Angelo Casolaro, Nicola Dall’Asen, Francesca Miccolis, Martin Menabue
• 12 - Predicting gene and protein expression levels from DNA and protein sequences exploiting Transformer-based architectures
  Teemu Sarapisto, Vincenzo Mariano Scarrica, Mathurin VIDEAU, Vittorio Pippi, Emanuele Frascaroli, Brandon Wily Viglianisi
• 13 - Using Neural Radiance Fields in real scenarios
  Gabriele Mario Caddeo, (Cosmo) Haoyu Wei, Lorenzo Bianchi, Emanuele Balloni, Alessandro Simoni, Michele Boldo
• 14 - Using Neural Radiance Fields in real scenarios 🏆
  Snehal Jauhri, Chang Liu, Kai Konen, Sanket Sabharwal, Davide Di Nucci, Fabio Quattrini