6 citations · 8 across the 10 of their papers we have counts for
6 papers · 1 filter
Disentangling Marginal Capacity from Geometry in Optimal-Transport Label Transfer
Ali Khodabandeh Yalabadi, Azim Dehghani Amirabad, Artem Moskalev +4
Optimal transport (OT) is widely used to align distributions and transfer labels between unpaired source and target data, but source-target composition shifts can cause rare classe…
HyperHELM: Hyperbolic Hierarchy Encoding for mRNA Language Modeling
Max van Spengler, Artem Moskalev, Tommaso Mansi +2
Language models are increasingly applied to biological sequences like proteins and mRNA, yet their default Euclidean geometry may mismatch the hierarchical structures inherent to b…
Geometric Hyena Networks for Large-scale Equivariant Learning
Artem Moskalev, Mangal Prakash, Junjie Xu +3
Processing global geometric context while preserving equivariance is crucial when modeling biological, chemical, and physical systems. Yet, this is challenging due to the computati…
HELM: Hierarchical Encoding for mRNA Language Modeling
Mehdi Yazdani-Jahromi, Mangal Prakash, Tommaso Mansi +2
Messenger RNA (mRNA) plays a crucial role in protein synthesis, with its codon structure directly impacting biological properties. While Language Models (LMs) have shown promise in…
SE(3)-Hyena Operator for Scalable Equivariant Learning
Artem Moskalev, Mangal Prakash, Rui Liao +1
Modeling global geometric context while maintaining equivariance is crucial for accurate predictions in many fields such as biology, chemistry, or vision. Yet, this is challenging…
LieGG: Studying Learned Lie Group Generators
Artem Moskalev, Anna Sepliarskaia, Ivan Sosnovik +1
Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symme…