LRIM benchmark accepted at ICLR 2026
Our paper on the Long-Range Ising Model benchmark for provably evaluating long-range capabilities in graph learning has been accepted for poster presentation at ICLR 2026, Rio de …
Adaptive Width Neural Networks accepted at ICLR 2026
Our paper on learning unbounded layer width during training (with easy truncation and dynamic compression) has been accepted for poster presentation at ICLR 2026, Rio de Janeiro.
Presented "Guidance of Diffusion-Based Conditional Generative Models for Antibody Design" at PriGM@EurIPS 2025
Talk at the Workshop on Principles of Generative Modeling (PriGM), EurIPS 2025, Copenhagen. We introduce a formal logical composition framework for conditional diffusion (AND and …
Attended SIMBIOCHEM@EurIPS 2025 — Viktor presented "Transferable long-range interactions in machine-learned interatomic potentials"
At the 1st SIMBIOCHEM Workshop (Dec 6th, 2025, Copenhagen), Viktor Zaverkin presented our work on augmenting MLIPs with analytic long-range electrostatics and dispersion for …
Paper accepted in Journal of Chemical Theory and Computation (JCTC)
Performance of Universal Machine-Learned Potentials with Explicit Long-Range Interactions in Biomolecular Simulations accepted for publication in JCTC (ACS). Viktor Zaverkin, …
Paper on DIMOS (PyTorch molecular dynamics framework) accepted in J. Chem. Phys.
Fast, Modular, and Differentiable Framework for Machine Learning-Enhanced Molecular Simulations accepted in J. Chem. Phys. PyTorch-based framework for ML-enhanced MD/MC; code at …
Website updated with latest publications and Hugo
Added 2025–2026 papers from Google Scholar and upgraded the site to Hugo 0.155 with the latest theme.