Yarin Gal

papers

755

total citations

papers (25)

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

NEURIPS 2021arXiv

161

citations

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

NEURIPS 2021arXiv

citations

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

NEURIPS 2021arXiv

citations

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

NEURIPS 2022arXiv

citations

A Bayesian Perspective on Training Speed and Model Selection

NEURIPS 2020arXiv

citations

Outcome-Driven Reinforcement Learning via Variational Inference

NEURIPS 2021arXiv

citations

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

ICML 2024arXiv

citations

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

NEURIPS 2025arXiv

citations

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

NEURIPS 2025arXiv

citations

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

ICML 2024arXiv

citations

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations

NEURIPS 2020arXiv

citations

Scaling Up Active Testing to Large Language Models

NEURIPS 2025arXiv

citations

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

NEURIPS 2020arXiv

citations

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

NEURIPS 2025arXiv

citations

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

ICML 2024

citations

Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions

NEURIPS 2022

citations

Deep Deterministic Uncertainty: A New Simple Baseline

CVPR 2023

citations

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers

NEURIPS 2023

citations

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design

NEURIPS 2023

citations

Yarin Gal

papers (25)

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Domain Invariant Representation Learning with Domain Density Transformations

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models

Improving black-box optimization in VAE latent space using decoder uncertainty

Interventions, Where and How? Experimental Design for Causal Models at Scale

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Speedy Performance Estimation for Neural Architecture Search

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

A Bayesian Perspective on Training Speed and Model Selection

Outcome-Driven Reinforcement Learning via Variational Inference

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations

Scaling Up Active Testing to Large Language Models

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions

Deep Deterministic Uncertainty: A New Simple Baseline

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design

papers (25)

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Domain Invariant Representation Learning with Domain Density Transformations

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models

Improving black-box optimization in VAE latent space using decoder uncertainty

Interventions, Where and How? Experimental Design for Causal Models at Scale

Tractable Function-Space Variational Inference in Bayesian Neural Networks

Speedy Performance Estimation for Neural Architecture Search

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

A Bayesian Perspective on Training Speed and Model Selection

Outcome-Driven Reinforcement Learning via Variational Inference

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations

Scaling Up Active Testing to Large Language Models

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions

Deep Deterministic Uncertainty: A New Simple Baseline

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design