Johannes von Oswald

14 papers · 2020–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+3 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (30)

💎 Century Club · Bronze 🔥 Unstoppable · Bronze 🗃️ Keyword Collector (65)

Venues

NeurIPS (7) ICLR (6) ICML (1)

Top co-authors

Seijin Kobayashi (9) João Sacramento (9) Christian Henning (4) Alexander Meulemans (4) Simon Schug (3) Yassir Akram (3) Nicolas Zucchet (3) Benjamin F Grewe (2) Angelika Steger (2) Benjamin F. Grewe (2)

Research topics

Machine Learning (13) Artificial Intelligence (8) Deep Learning (8) Learning Types · Machine Learning (8) Optimization & Theory · Machine Learning (8) Architectures (6) Core AI (4) Learning Paradigms · Artificial Intelligence (4) Learning Paradigms · Machine Learning (3) Learning Types · Deep Learning (3) Optimization & Theory · Deep Learning (3) Core Methods (2) Reinforcement Learning (1) Application Areas (1) Bayesian & Probabilistic (1)

Keywords

continual learning (4) transformer model (2) in-context learning (2) catastrophic forgetting (2) recurrent neural network (2) local learning (1) bayesian inference (1) multi-agent reinforcement learning (1) bayesian learning (1) few-shot learning (1) contrastive learning (1) matrix factorization (1) adversarial robustness (1) policy gradient (1) attention mechanism (1) uncertainty quantification (1) stochastic gradient descent (1) model merging (1) gradient estimation (1) neural tangent kernel (1)

Papers

Learning Randomized Algorithms with Transformers ICLR 2025 Multi-agent cooperation through learning-aware policy gradients ICLR 2025 Discovering modular solutions that generalize compositionally ICLR 2024 Linear Transformers are Versatile In-Context Learners NeurIPS 2024 Weight decay induces low-rank attention layers NeurIPS 2024 Transformers Learn In-Context by Gradient Descent ICML 2023 A contrastive rule for meta-learning NeurIPS 2022 Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel NeurIPS 2022 The least-control principle for local learning at equilibrium NeurIPS 2022 Continual learning in recurrent neural networks ICLR 2021 Learning where to learn: Gradient sparsity in meta and continual learning NeurIPS 2021 Neural networks with late-phase weights ICLR 2021 Posterior Meta-Replay for Continual Learning NeurIPS 2021 Continual learning with hypernetworks ICLR 2020