Yarin Gal

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025 Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions EMNLP 2025 Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction ICML 2025 Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation EMNLP 2025 Challenges and Considerations in the Evaluation of Bayesian Causal Discovery ICML 2024 Deep Bayesian Active Learning for Preference Modeling in Large Language Models NeurIPS 2024 Estimating the Hallucination Rate of Generative AI NeurIPS 2024 How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions ICLR 2024 In-Context Learning Learns Label Relationships but Is Not Conventional Learning ICLR 2024 Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities NeurIPS 2024 Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches ICML 2024 Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control NeurIPS 2024 ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages ICML 2024 Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning? CLeaR 2023 Deep Deterministic Uncertainty: A New Simple Baseline CVPR 2023 Differentiable Multi-Target Causal Bayesian Experimental Design ICML 2023 DiscoBAX: Discovery of optimal intervention sets in genomic experiment design ICML 2023 Prediction-Oriented Bayesian Active Learning AISTATS 2023 ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design NeurIPS 2023 ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers NeurIPS 2023 Revisiting Automated Prompting: Are We Actually Doing Better? ACL 2023 Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation ICLR 2023 Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation NeurIPS 2022 Continual Learning via Sequential Function-Space Variational Inference ICML 2022 GeneDisco: A Benchmark for Experimental Design in Drug Discovery ICLR 2022 Interlocking Backpropagation: Improving depthwise model-parallelism JMLR 2022 Interventions, Where and How? Experimental Design for Causal Models at Scale NeurIPS 2022 KL Guided Domain Adaptation ICLR 2022 Learning Dynamics and Generalization in Deep Reinforcement Learning ICML 2022 Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt ICML 2022 Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients ICLR 2022 Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions NeurIPS 2022 Tractable Function-Space Variational Inference in Bayesian Neural Networks NeurIPS 2022 Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval ICML 2022 Active Testing: Sample-Efficient Model Evaluation ICML 2021 Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data NeurIPS 2021 Domain Invariant Representation Learning with Domain Density Transformations NeurIPS 2021 Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties AISTATS 2021 Improving black-box optimization in VAE latent space using decoder uncertainty NeurIPS 2021 Learning Invariant Representations for Reinforcement Learning without Reconstruction ICLR 2021 On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations NeurIPS 2021 On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes ICML 2021 On Statistical Bias In Active Learning: How and When to Fix It ICLR 2021 Outcome-Driven Reinforcement Learning via Variational Inference NeurIPS 2021 PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning ICML 2021 Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding ICML 2021 Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning NeurIPS 2021 Speedy Performance Estimation for Neural Architecture Search NeurIPS 2021 VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning JMLR 2021 A Bayesian Perspective on Training Speed and Model Selection NeurIPS 2020 BayesOpt Adversarial Attack ICLR 2020 Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts? ICML 2020 How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19? NeurIPS 2020 Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models NeurIPS 2020 Inter-domain Deep Gaussian Processes ICML 2020 Invariant Causal Prediction for Block MDPs ICML 2020 Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations NeurIPS 2020 Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning AISTATS 2020 Uncertainty Estimation Using a Single Deep Deterministic Neural Network ICML 2020 VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning ICLR 2020 An Empirical study of Binary Neural Networks' Optimisation ICLR 2019 BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning NeurIPS 2019 BRUNO: A Deep Recurrent Model for Exchangeable Data NeurIPS 2018 Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam ICML 2018 Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics CVPR 2018 Concrete Dropout NeurIPS 2017 Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning IJCAI 2017 Deep Bayesian Active Learning with Image Data ICML 2017 Dropout Inference in Bayesian Neural Networks with Alpha-divergences ICML 2017 Real Time Image Saliency for Black Box Classifiers NeurIPS 2017 What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? NeurIPS 2017 A Theoretically Grounded Application of Dropout in Recurrent Neural Networks NeurIPS 2016 Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning ICML 2016 Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs ICML 2015 Latent Gaussian Processes for Distribution Estimation of Multivariate Categorical Data ICML 2015 Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models NeurIPS 2014 Pitfalls in the use of Parallel Inference for the Dirichlet Process ICML 2014 A Systematic Bayesian Treatment of the IBM Alignment Models NAACL 2013