Adrian Weller

Can Large Language Models Understand Symbolic Graphics Programs? ICLR 2025 Certification for Differentially Private Prediction in Gradient-Based Training ICML 2025 Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention ICML 2025 Gridded Transformer Neural Processes for Spatio-Temporal Data ICML 2025 Learning Personalized Decision Support Policies AAAI 2025 Linear Transformer Topological Masking with Graph Random Features ICLR 2025 LLMs on interactive feature collections with implicit dynamic decision strategy COLING 2025 Mitigating Shortcut Learning with InterpoLated Learning ACL 2025 On Evaluating LLMs’ Capabilities as Functional Approximators: A Bayesian Evaluation Framework COLING 2025 Orthogonal Finetuning Made Scalable EMNLP 2025 Variance-Reducing Couplings for Random Features ICLR 2025 VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning ICLR 2025 ALVIN: Active Learning Via INterpolation EMNLP 2024 Approximately Equivariant Neural Processes NeurIPS 2024 Confidential-DPproof: Confidential Proof of Differentially Private Training ICLR 2024 General Graph Random Features ICLR 2024 Large Language Models Must Be Taught to Know What They Don’t Know NeurIPS 2024 Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers AISTATS 2024 MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models ICLR 2024 Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization ICLR 2024 Repelling Random Walks ICLR 2024 Approximating Full Conformal Prediction at Scale via Influence Functions AAAI 2023 Certification of Distributional Individual Fairness NeurIPS 2023 Confidential-PROFITT: Confidential PROof of FaIr Training of Trees ICLR 2023 Controlling Text-to-Image Diffusion by Orthogonal Finetuning NeurIPS 2023 Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel NeurIPS 2023 Diffused Redundancy in Pre-trained Representations NeurIPS 2023 Do Invariances in Deep Neural Networks Align with Human Perception? AAAI 2023 Efficient Graph Field Integrators Meet Point Clouds ICML 2023 Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap ICLR 2023 Human-in-the-Loop Mixup UAI 2023 Is Learning Summary Statistics Necessary for Likelihood-free Inference? ICML 2023 Iterative Teaching by Data Hallucination AISTATS 2023 Learning to Receive Help: Intervention-Aware Concept Embedding Models NeurIPS 2023 Mnemonist: Locating Model Parameters that Memorize Training Examples UAI 2023 On the Expressive Flexibility of Self-Attention Matrices AAAI 2023 On the informativeness of supervision signals UAI 2023 Pairwise Similarity Learning is SimPLE ICCV 2023 Quasi-Monte Carlo Graph Random Features NeurIPS 2023 Robust Explanation Constraints for Neural Networks ICLR 2023 Simplex Random Features ICML 2023 Towards More Robust Interpretation via Local Gradient Alignment AAAI 2023 Towards Robust Metrics for Concept Representation Evaluation AAAI 2023 Use perturbations when learning from explanations NeurIPS 2023 A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets NeurIPS 2022 Chefs' Random Tables: Non-Trigonometric Random Features NeurIPS 2022 Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off NeurIPS 2022 CrossWalk: Fairness-Enhanced Node Representation Learning AAAI 2022 Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates AAAI 2022 From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers ICML 2022 Hybrid Random Features ICLR 2022 Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022 On the Fairness of Causal Algorithmic Recourse AAAI 2022 On the Utility of Prediction Sets in Human-AI Teams IJCAI 2022 Scalable Infomin Learning NeurIPS 2022 SphereFace2: Binary Classification is All You Need for Deep Face Recognition ICLR 2022 Structural Causal 3D Reconstruction ECCV 2022 Towards Principled Disentanglement for Domain Generalization CVPR 2022 CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices AISTATS 2021 Debiasing a First-order Heuristic for Approximate Bi-level Optimization ICML 2021 Getting a CLUE: A Method for Explaining Uncertainty Estimates ICLR 2021 Iterative Teaching by Label Synthesis NeurIPS 2021 Learning with Hyperspherical Uniformity AISTATS 2021 Orthogonal Over-Parameterized Training CVPR 2021 Rethinking Attention with Performers ICLR 2021 Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch NeurIPS 2021 Sub-Linear Memory: How to Make Performers SLiM NeurIPS 2021 Adversarial Graph Embeddings for Fair Influence Maximization over Social Networks IJCAI 2020 Evaluating and Aggregating Feature-based Model Explanations IJCAI 2020 Ode to an ODE NeurIPS 2020 Stochastic Flows and Geometric Optimization on the Orthogonal Group ICML 2020 Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models NeurIPS 2019 One-Network Adversarial Fairness AAAI 2019 Orthogonal Estimation of Wasserstein Distances AISTATS 2019 The Sensitivity of Counterfactual Fairness to Unmeasured Confounding UAI 2019 TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning ICML 2019 Train and Test Tightness of LP Relaxations in Structured Prediction JMLR 2019 Unifying Orthogonal Monte Carlo Methods ICML 2019 Blind Justice: Fairness with Encrypted Sensitive Attributes ICML 2018 Bucket Renormalization for Approximate Inference ICML 2018 Discovering Interpretable Representations for Both Deep Generative and Discriminative Models ICML 2018 Gauged Mini-Bucket Elimination for Approximate Inference AISTATS 2018 Geometrically Coupled Monte Carlo Sampling NeurIPS 2018 Structured Evolution with Compact Architectures for Scalable Policy Optimization ICML 2018 The Geometry of Random Features AISTATS 2018 Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning IJCAI 2017 Conditions beyond treewidth for tightness of higher-order LP relaxations AISTATS 2017 From Parity to Preference-based Notions of Fairness in Classification NeurIPS 2017 Lost Relatives of the Gumbel Trick ICML 2017 The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings NeurIPS 2017 Uprooting and Rerooting Higher-Order Graphical Models NeurIPS 2017 Clamping Improves TRW and Mean Field Approximations AISTATS 2016 Tightness of LP Relaxations for Almost Balanced Models AISTATS 2016 Train and Test Tightness of LP Relaxations in Structured Prediction ICML 2016 Uprooting and Rerooting Graphical Models ICML 2016 Revisiting the Limits of MAP Inference by MWSS on Perfect Graphs AISTATS 2015 Clamping Variables and Approximate Inference NeurIPS 2014 Bethe Bounds and Approximating the Global Optimum AISTATS 2013