← Search

Alexander Molozhavenko

2 accepted papers

2026

LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters

ICLR 2026poster

This work presents a novel, fully Riemannian framework for Low-Rank Adaptation (LoRA) that geometrically treats low-rank adapters by optimizing them directly on the fixed-rank manifold. This formulation eliminates the parametrization ambiguity present in standard Euclidean optimizers. Our framework…

Cited by 0SourceScholar
2026

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models

CVPR 2026

In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training data to adapt the model to a narrow task. However, there is an open question: how to combine several adapters tuned for di

Cited by 0SourcecodeScholar