activity
20232026
most citedDartsReNet: Exploring new RNN cells in ReNet architectures

9 citations · 13 across the 21 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds

Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov +3

Generative modeling of time-dependent data is typically formulated on a discrete temporal grid, restricting supervision to the observed timestamps in the training data. We instead…

cs.LG2026

Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive

Brian B. Moser, Ahmed Anwar, Tobias Christian Nauen +5

Continual learning regularizers like EWC fight forgetting by penalizing changes from previous-task parameters with per-parameter importance, typically diagonal Fisher values. Per-p…

cs.LG2026

Hyperspherical Forward-Forward with Prototypical Representations

Shalini Sarode, Brian Moser, Joachim Folz +4

The Forward-Forward (FF) algorithm presents a compelling, bio-inspired alternative to backpropagation. However, while efficient in training, it has a computationally prohibitive in…

cs.LG2025

PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors

Brian B. Moser, Shalini Sarode, Federico Raue +6

Dataset distillation (DD) promises compact yet faithful synthetic data, but existing approaches often inherit the inductive bias of a single teacher model. As dataset size increase…

cs.LG2025

SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection

Brian B. Moser, Tobias C. Nauen, Arundhati S. Shanbhag +4

The goal of coreset selection is to identify representative subsets of datasets for efficient model training. Yet, existing approaches paradoxically require expensive training-base…

cs.LG2025

HyperCore: Coreset Selection under Noise via Hypersphere Models

Brian B. Moser, Arundhati S. Shanbhag, Tobias C. Nauen +4

The goal of coreset selection methods is to identify representative subsets of datasets for efficient model training. Yet, existing methods often ignore the possibility of annotati…