Tim G. J. Rudner

Affiliations

University of Oxford

papers

491

total citations

papers (12)

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

NEURIPS 2023arXiv

citations

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

NEURIPS 2021arXiv

citations

Outcome-Driven Reinforcement Learning via Variational Inference

NEURIPS 2021arXiv

citations

Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models

NEURIPS 2025arXiv

citations

Can Transformers Learn Full Bayesian Inference in Context?

ICML 2025arXiv

citations

Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design

ICML 2024arXiv

citations

Should We Learn Most Likely Functions or Parameters?

NEURIPS 2023arXiv

citations

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

NEURIPS 2023

citations

Tim G. J. Rudner

Affiliations

papers (12)

Protein Design with Guided Discrete Diffusion

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Non-Vacuous Generalization Bounds for Large Language Models

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Outcome-Driven Reinforcement Learning via Variational Inference

Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models

Can Transformers Learn Full Bayesian Inference in Context?

Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design

Should We Learn Most Likely Functions or Parameters?

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

papers (12)

Protein Design with Guided Discrete Diffusion

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Non-Vacuous Generalization Bounds for Large Language Models

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Outcome-Driven Reinforcement Learning via Variational Inference

Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models

Can Transformers Learn Full Bayesian Inference in Context?

Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design

Should We Learn Most Likely Functions or Parameters?

An Information Theory Perspective on Variance-Invariance-Covariance Regularization