activity
20222026
most citedSPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training

7 citations · 7 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Data Unlearning via Inverse Distillation

Aleksei Leonov, Nikita Kornilov, Zhenhe Zhang +3

Multi-step matching models, including flow and diffusion models, produce high-quality outputs but incur substantial inference costs and may reproduce unwanted components of their t…