Yarin Gal

24

Papers

1

Total Citations

Papers (24)

Scaling Up Active Testing to Large Language Models

NeurIPS 2025arXiv

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

NeurIPS 2025arXiv

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

NeurIPS 2025arXiv

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

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

Deep Deterministic Uncertainty: A New Simple Baseline

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

NeurIPS 2020arXiv

A Bayesian Perspective on Training Speed and Model Selection

NeurIPS 2020arXiv

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models

NeurIPS 2020arXiv

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

NeurIPS 2020arXiv

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

NeurIPS 2021arXiv

Speedy Performance Estimation for Neural Architecture Search

NeurIPS 2021arXiv

Domain Invariant Representation Learning with Domain Density Transformations

NeurIPS 2021arXiv

Outcome-Driven Reinforcement Learning via Variational Inference

NeurIPS 2021arXiv

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

NeurIPS 2021arXiv

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

NeurIPS 2021arXiv

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

NeurIPS 2021arXiv

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

Tractable Function-Space Variational Inference in Bayesian Neural Networks

NeurIPS 2022arXiv

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

NeurIPS 2022arXiv

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

NeurIPS 2022arXiv

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

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