From December 10-15 2024, Mila professors, students and staff members attended NeurIPS 2024, one of the largest AI research conferences in the world, to present their work and network with researchers and industry members from around the world. A scientific paper by Mila members was also highlighted for its foundational contribution to the field.
Test of Time Award
Generative Adversarial Nets, by Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville and Yoshua Bengio, won the Test of Time Award, which recognizes papers published 10 years ago (at NeurIPS 2014) that have significantly shaped the research field since then, according to the official announcement.
The paper, which proposed a novel framework for estimating generative models via an adversarial process, has since been cited more than 85.000 times and is considered one of the foundational works for generative modeling that has spurred many innovative research directions in the last 10 years.
Spotlights at the main conference
Among the more than 60 scientific papers presented at the main conference (see the full list of Mila-affiliated papers here), several works were highlighted as spotlight posters.
These include:
- Learning Action and Reasoning-Centric Image Editing from Videos and Simulation by Benno Krojer, Dheeraj Vattikonda, Luis Lara, Varun Jampani, Eva Portelance, Christopher Pal and Siva Reddy.
- Efficient Adversarial Training in LLMs with Continuous Attacks by Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel and Leo Schwinn.
- Cell ontology guided transcriptome foundation model by Xinyu Yuan, Zhihao Zhan, Zuobai Zhang, Manqi Zhou, Jianan Zhao, Boyu Han, Yue Li and Jian Tang.
- Trajectory Flow Matching with Applications to Clinical Time Series Modelling by Xi Zhang, Yuan Pu, Yuki Kawamura, Andrew Loza, Yoshua Bengio, Dennis Shung and Alexander Tong.
- Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences by Damien Ferbach, Quentin Bertrand, Joey Bose and Gauthier Gidel.
Workshops
Mila researchers also co-organized workshops featuring panel discussions, keynotes and collaborative working sessions on topics such as:
- Women in Machine Learning (WiML 2024)
- Tackling Climate Change with Machine Learning
- Algorithmic Fairness through the Lens of Metrics and Evaluation
- Pluralistic Alignment Workshop
- Safe Generative AI
- Causality and Large Models
- Compositional Learning: Perspectives, Methods, and Paths Forward
- Time Series in the Age of Large Models
Mila booth
Mila researchers presented their work to their peers at Mila’s booth (the day-to-day program can be found here). Staff members met with researchers and prospective students and networked with members of the industry.
A social event to attract investments and talent to Québec
In partnership with Investissement Québec International, Mila also organized an event for potential industrial partners, which was attended by high-ranking company representatives and researchers from around the world.
