Organisers

Organizers are listed alphabetically by last name.

Yani Ioannou

Affiliation: University of Calgary

Biography: Yani Ioannou is a Schulich Research Chair and Assistant Professor in the Department of Electrical and Software Engineering at the University of Calgary in Alberta, Canada. Yani completed his PhD at the University of Cambridge in 2018 supported by a Microsoft Research PhD Scholarship. Yani leads the Calgary Machine Learning Lab, with research interests including improving sparse neural network training, where the lab's recent work has highlighted the role of weight symmetries.

Boris Knyazev

Affiliation: Samsung AI Lab Montreal / Université de Montréal

Biography: Boris Knyazev is a Research Scientist at Samsung AI Lab, Montreal, Canada. He is also an Adjunct Professor at the University of Montreal. He completed his PhD at the Machine Learning Research Group, University of Guelph and Vector Institute in 2022. His research interests lie at the intersection of graph neural networks (GNNs), meta-learning and weight space learning with applications in faster optimization algorithms and model compression.

Ekaterina Lobacheva

Affiliation: Mila – Quebec AI Institute / Université de Montréal

Biography: Ekaterina Lobacheva is a Postdoctoral Researcher at Mila – Quebec AI Institute and Université de Montréal, working with Prof. Sarath Chandar. She completed her PhD at HSE University, and her postdoctoral research is supported by an IVADO Fellowship. Her research focuses on understanding neural network loss landscapes and training dynamics, the implicit biases of optimization, generalization, as well as ensembling and model merging techniques.

Adnan Mohammed

Affiliation: University of Calgary / Vector Institute

Biography: Adnan Mohammed is a PhD student at the University of Calgary and Vector Institute, working under the supervision of Dr. Yani Ioannou (University of Calgary) and Dr. Rahul Krishnan (University of Toronto/Vector Institute). Adnan's current research focuses on understanding the role of weight-space symmetries in optimization and linear mode-connectivity. His research is supported by the NSERC Doctoral Fellowship, Killam Doctoral Fellowship, Borealis AI Research Fellowship, and Digital Research Alliance of Canada. He received his MS and undergraduate degrees from the University of Waterloo and the Indian Institute of Technology (IIT) Guwahati, respectively.

Antonio Orvieto

Affiliation: ELLIS Institute Tübingen / MPI for Intelligent Systems

Biography: Antonio Orvieto studied Control Engineering in Italy and Switzerland. He holds a PhD in Computer Science from ETH Zürich. He is currently a Principal Investigator (PI) at the ELLIS Institute Tübingen and Independent Group Leader of the MPI for Intelligent Systems, where he leads the Deep Models and Optimization group. He received the ETH Medal for Outstanding Doctoral Theses and the Schmidt Sciences AI2050 Early Career Fellowship. His research includes understanding the intricacies of large-scale optimization dynamics and the landscape of modern neural networks.

Alexander Theus

Affiliation: ETH Zurich / MPI for Intelligent Systems

Biography: Alexander Theus is a PhD student in Machine Learning at ETH Zurich and the Max Planck Institute for Intelligent Systems, advised by Dr. Valentina Boeva and Dr. Antonio Orvieto. His research focuses on the geometry of neural network loss landscapes and weight-space symmetries, with implications for generalization, optimization, and model merging. In his previous work, he showed that accounting for weight-space symmetries beyond permutations enables linear mode connectivity in Transformer models. His research is supported by the Max Planck ETH Center for Learning Systems. He holds an MSc from ETH Zurich and a BSc from the University of Zurich.