activity
20202026
most citedLearning where to learn: Gradient sparsity in meta and continual learning

24 citations · 25 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

From Words to Amino Acids: Does the Curse of Depth Persist?

Aleena Siji, Amir Mohammad Karimi Mamaghan, Ferdinand Kapl +9

Protein language models (PLMs) have become widely adopted as general-purpose models, demonstrating strong performance in protein engineering and de novo design. Like large language…

cs.LG2025

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel +12

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. Du…

cs.LG2024

Learning Randomized Algorithms with Transformers

Johannes von Oswald, Seijin Kobayashi, Yassir Akram +1

Randomization is a powerful tool that endows algorithms with remarkable properties. For instance, randomized algorithms excel in adversarial settings, often surpassing the worst-ca…

cs.LG20221 cited

Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel

Seijin Kobayashi, Pau Vilimelis Aceituno, Johannes von Oswald

Identifying unfamiliar inputs, also known as out-of-distribution (OOD) detection, is a crucial property of any decision making process. A simple and empirically validated technique…

cs.LG202124 cited

Learning where to learn: Gradient sparsity in meta and continual learning

Johannes von Oswald, Dominic Zhao, Seijin Kobayashi +4

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight ch…

cs.LG2020

Continual Learning in Recurrent Neural Networks

Benjamin Ehret, Christian Henning, Maria R. Cervera +3

While a diverse collection of continual learning (CL) methods has been proposed to prevent catastrophic forgetting, a thorough investigation of their effectiveness for processing s…