Posts

“Enhancing LLM Training via Spectral Clipping” (with Xiaowen Jiang and Sebastian U. Stich).

I am accepted at University of Zurich to follow the PhD program at the Department of Mathematical Modeling and Machine Learning (D3ML) in the research group of Prof. Dr. Anastasiia Koloskova.

“Apertus: Democratizing Open and Compliant LLMs for Global Language Environments” – a project by Team Apertus within the Swiss AI Initiative.

“Enhancing LLM Training via Spectral Clipping” – joint work with Xiaowen Jiang and Sebastian U. Stich.

“Gradient-Normalized Smoothness for Optimization with Approximate Hessians” – joint work with Martin Jaggi and Nikita Doikov.

“Adaptive Regularized Newton Method with Inexact Hessian” – joint work with Aleksandr Shestakov, Nail Bashirov, Alexander Gasnikov, Martin Takáč, Aleksandr Beznosikov and Dmitry Kamzolov.

Between December 2 and December 7, I will attend EurIPS 2025 in Copenhagen, an event officially endorsed by NeurIPS. I will present two papers there: “Benchmarking Optimizers for Large Language Model Pretraining” and “Just a Simple Transformation is Enough for Data Protection in Split Learning”.

“Adaptive Regularized Newton Method with Inexact Hessian” – joint work with Aleksandr Shestakov, Nail Bashirov, Alexander Gasnikov, Martin Takáč, Aleksandr Beznosikov and Dmitry Kamzolov.

“Apertus: Democratizing Open and Compliant LLMs for Global Language Environments” – a project by Team Apertus within the Swiss AI Initiative.

“Benchmarking Optimizers for Large Language Model Pretraining” – joint work with Matteo Pagliardini and Martin Jaggi.