Alert button
Picture for Yarin Gal

Yarin Gal

Alert button

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

Jul 20, 2023
David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan

Figure 1 for LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
Figure 2 for LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
Viaarxiv icon

BatchGFN: Generative Flow Networks for Batch Active Learning

Jun 26, 2023
Shreshth A. Malik, Salem Lahlou, Andrew Jesson, Moksh Jain, Nikolay Malkin, Tristan Deleu, Yoshua Bengio, Yarin Gal

Figure 1 for BatchGFN: Generative Flow Networks for Batch Active Learning
Figure 2 for BatchGFN: Generative Flow Networks for Batch Active Learning
Figure 3 for BatchGFN: Generative Flow Networks for Batch Active Learning
Figure 4 for BatchGFN: Generative Flow Networks for Batch Active Learning
Viaarxiv icon

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

Jun 12, 2023
Andrew Jesson, Chris Lu, Gunshi Gupta, Angelos Filos, Jakob Nicolaus Foerster, Yarin Gal

Figure 1 for ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
Figure 2 for ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
Figure 3 for ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
Figure 4 for ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
Viaarxiv icon

The Curse of Recursion: Training on Generated Data Makes Models Forget

May 31, 2023
Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, Yarin Gal, Nicolas Papernot, Ross Anderson

Figure 1 for The Curse of Recursion: Training on Generated Data Makes Models Forget
Figure 2 for The Curse of Recursion: Training on Generated Data Makes Models Forget
Figure 3 for The Curse of Recursion: Training on Generated Data Makes Models Forget
Figure 4 for The Curse of Recursion: Training on Generated Data Makes Models Forget
Viaarxiv icon

Prediction-Oriented Bayesian Active Learning

Apr 17, 2023
Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar, Yarin Gal, Adam Foster, Tom Rainforth

Figure 1 for Prediction-Oriented Bayesian Active Learning
Figure 2 for Prediction-Oriented Bayesian Active Learning
Figure 3 for Prediction-Oriented Bayesian Active Learning
Figure 4 for Prediction-Oriented Bayesian Active Learning
Viaarxiv icon

Revisiting Automated Prompting: Are We Actually Doing Better?

Apr 07, 2023
Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, Yarin Gal

Figure 1 for Revisiting Automated Prompting: Are We Actually Doing Better?
Figure 2 for Revisiting Automated Prompting: Are We Actually Doing Better?
Figure 3 for Revisiting Automated Prompting: Are We Actually Doing Better?
Figure 4 for Revisiting Automated Prompting: Are We Actually Doing Better?
Viaarxiv icon

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Feb 21, 2023
Lorenz Kuhn, Yarin Gal, Sebastian Farquhar

Figure 1 for Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Figure 2 for Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Figure 3 for Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Figure 4 for Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Viaarxiv icon

Differentiable Multi-Target Causal Bayesian Experimental Design

Feb 21, 2023
Yashas Annadani, Panagiotis Tigas, Desi R. Ivanova, Andrew Jesson, Yarin Gal, Adam Foster, Stefan Bauer

Figure 1 for Differentiable Multi-Target Causal Bayesian Experimental Design
Figure 2 for Differentiable Multi-Target Causal Bayesian Experimental Design
Figure 3 for Differentiable Multi-Target Causal Bayesian Experimental Design
Figure 4 for Differentiable Multi-Target Causal Bayesian Experimental Design
Viaarxiv icon

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Dec 28, 2022
Tim G. J. Rudner, Cong Lu, Michael A. Osborne, Yarin Gal, Yee Whye Teh

Figure 1 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
Figure 2 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
Figure 3 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
Figure 4 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
Viaarxiv icon

CLAM: Selective Clarification for Ambiguous Questions with Large Language Models

Dec 15, 2022
Lorenz Kuhn, Yarin Gal, Sebastian Farquhar

Figure 1 for CLAM: Selective Clarification for Ambiguous Questions with Large Language Models
Figure 2 for CLAM: Selective Clarification for Ambiguous Questions with Large Language Models
Figure 3 for CLAM: Selective Clarification for Ambiguous Questions with Large Language Models
Figure 4 for CLAM: Selective Clarification for Ambiguous Questions with Large Language Models
Viaarxiv icon