Adrian Weller

Affiliations

Alan Turing InstituteUniversity of Cambridge

papers

1,311

total citations

papers (25)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

NEURIPS 2025arXiv

citations

Use perturbations when learning from explanations

NEURIPS 2023arXiv

citations

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

ICML 2025arXiv

citations

Certification of Distributional Individual Fairness

NEURIPS 2023arXiv

citations

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

NEURIPS 2023

citations

A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets

NEURIPS 2022

citations

Adrian Weller

Affiliations

papers (25)

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Towards Principled Disentanglement for Domain Generalization

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

Orthogonal Over-Parameterized Training

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

Ode to an ODE

Sub-Linear Memory: How to Make Performers SLiM

Chefs' Random Tables: Non-Trigonometric Random Features

Iterative Teaching by Label Synthesis

Structural Causal 3D Reconstruction

Learning Personalized Decision Support Policies

Quasi-Monte Carlo Graph Random Features

Scalable Infomin Learning

General Graph Random Features

Pairwise Similarity Learning is SimPLE

Diffused Redundancy in Pre-trained Representations

Certification for Differentially Private Prediction in Gradient-Based Training

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Use perturbations when learning from explanations

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Certification of Distributional Individual Fairness

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets

papers (25)

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Towards Principled Disentanglement for Domain Generalization

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

Orthogonal Over-Parameterized Training

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

Ode to an ODE

Sub-Linear Memory: How to Make Performers SLiM

Chefs' Random Tables: Non-Trigonometric Random Features

Iterative Teaching by Label Synthesis

Structural Causal 3D Reconstruction

Learning Personalized Decision Support Policies

Quasi-Monte Carlo Graph Random Features

Scalable Infomin Learning

General Graph Random Features

Pairwise Similarity Learning is SimPLE

Diffused Redundancy in Pre-trained Representations

Certification for Differentially Private Prediction in Gradient-Based Training

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Use perturbations when learning from explanations

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Certification of Distributional Individual Fairness

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets