← Authors

Yarin Gal

78 papers · 2013–2025 · 11 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (11) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (9) πŸƒ Academic Marathon (12) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (22) 🧭 Keyword Pioneer 🏠 Conference Loyalist (28) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (26) 🀝 Dynamic Duo (10) ⚑ Prolific Year (9) πŸ”₯ Unstoppable (13) ❓ The Questioner (6) πŸ“ˆ Trend Setter πŸ’Ž Century Club (78) πŸ—ƒοΈ Keyword Collector (64)

Conferences

NIPS (28) ICML (25) ICLR (12) AISTATS (3) CVPR (2) EMNLP (2) JMLR (2) ACL (1) CLEAR (1) IJCAI (1) NAACL (1)

Top co-authors

Andrew Jesson (10) Sebastian Farquhar (9) Tim G. J. Rudner (9) Clare Lyle (7) Jannik Kossen (7) Pascal Notin (7) Zoubin Ghahramani (5) Panagiotis Tigas (5) Stefan Bauer (5) Andreas Kirsch (5)

Research topics

Deep Learning (1)

Keywords

variational inference (14) uncertainty quantification (10) causal inference (7) epistemic uncertainty (6) bayesian inference (6) active learning (5) large language model (5) reinforcement learning (4) hallucination detection (4) uncertainty estimation (4) bayesian active learning (4) bayesian neural network (4) gaussian process (4) bayesian deep learning (4) aleatoric uncertainty (3) multi-task learning (3) representation learning (3) model uncertainty (3) acquisition function (3) neural network (3)

Papers

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