activity
20192026
most citedPerformance of Hyperbolic Geometry Models on Top-N Recommendation Tasks

29 citations · 39 across the 7 of their papers we have counts for

collaborators

10 papers

cs.LG2026

Efficient Reasoning on the Edge

Yelysei Bondarenko, Thomas Hehn, Rob Hesselink +15

Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large…

cs.LG2025

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs

Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar +3

Upcycling pre-trained dense models into sparse Mixture-of-Experts (MoEs) efficiently increases model capacity but often suffers from poor expert specialization due to naive weight…

cs.CV2025

Learning Optical Flow Field via Neural Ordinary Differential Equation

Leyla Mirvakhabova, Hong Cai, Jisoo Jeong +3

Recent works on optical flow estimation use neural networks to predict the flow field that maps positions of one image to positions of the other. These networks consist of a featur…

cs.CV2024

Neural Mesh Fusion: Unsupervised 3D Planar Surface Understanding

Farhad G. Zanjani, Hong Cai, Yinhao Zhu +2

This paper presents Neural Mesh Fusion (NMF), an efficient approach for joint optimization of polygon mesh from multi-view image observations and unsupervised 3D planar-surface par…

cs.CV2022★ 2 cited

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov +2

Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. Th…

cs.CV2021

Latent Transformations via NeuralODEs for GAN-based Image Editing

Valentin Khrulkov, Leyla Mirvakhabova, Ivan Oseledets +1

Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN. Speci…