Johannes von Oswald
14 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (27) π§ Keyword Pioneer π Cross-Pollinator (13) π Interdisciplinary Bridge π Conference Polyglot (3)
π
Academic Marathon
(5)
π£
Hot Topic Early Bird
π
Century Club
(14)
π₯
Unstoppable
(6)
Conferences
NIPS (7)
ICLR (6)
ICML (1)
Top co-authors
Keywords
continual learning
(2)
in-context learning
(2)
contrastive learning
(1)
few-shot learning
(1)
bayesian learning
(1)
bayesian inference
(1)
local learning
(1)
gradient descent
(1)
uncertainty quantification
(1)
attention mechanism
(1)
matrix factorization
(1)
gradient estimation
(1)
posterior distribution
(1)
optimal control
(1)
neural tangent kernel
(1)
synaptic plasticity
(1)
nuclear norm regularization
(1)
low-rank representation
(1)
nuclear norm
(1)
transformer architecture
(1)
Papers
Multi-agent cooperation through learning-aware policy gradients
ICLR 2025
Learning Randomized Algorithms with Transformers
ICLR 2025
Linear Transformers are Versatile In-Context Learners
NIPS 2024
Discovering modular solutions that generalize compositionally
ICLR 2024
Weight decay induces low-rank attention layers
NIPS 2024
Transformers Learn In-Context by Gradient Descent
ICML 2023
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel
NIPS 2022
The least-control principle for local learning at equilibrium
NIPS 2022
A contrastive rule for meta-learning
NIPS 2022
Learning where to learn: Gradient sparsity in meta and continual learning
NIPS 2021
Posterior Meta-Replay for Continual Learning
NIPS 2021
Continual learning in recurrent neural networks
ICLR 2021
Neural networks with late-phase weights
ICLR 2021
Continual learning with hypernetworks
ICLR 2020