Picture for Weiwei Pan

Weiwei Pan

A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning

May 31, 2024
Viaarxiv icon

Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders

Mar 13, 2024
Figure 1 for Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
Figure 2 for Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
Figure 3 for Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
Figure 4 for Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
Viaarxiv icon

Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks

Jan 26, 2024
Figure 1 for Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks
Figure 2 for Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks
Figure 3 for Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks
Figure 4 for Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks
Viaarxiv icon

Signature Activation: A Sparse Signal View for Holistic Saliency

Add code
Sep 20, 2023
Figure 1 for Signature Activation: A Sparse Signal View for Holistic Saliency
Figure 2 for Signature Activation: A Sparse Signal View for Holistic Saliency
Figure 3 for Signature Activation: A Sparse Signal View for Holistic Saliency
Figure 4 for Signature Activation: A Sparse Signal View for Holistic Saliency
Viaarxiv icon

Why do universal adversarial attacks work on large language models?: Geometry might be the answer

Sep 01, 2023
Viaarxiv icon

SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text

Jul 28, 2023
Figure 1 for SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text
Figure 2 for SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text
Figure 3 for SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text
Figure 4 for SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text
Viaarxiv icon

The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning

Jun 20, 2023
Figure 1 for The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
Figure 2 for The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
Figure 3 for The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
Figure 4 for The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
Viaarxiv icon

Modeling Mobile Health Users as Reinforcement Learning Agents

Dec 01, 2022
Figure 1 for Modeling Mobile Health Users as Reinforcement Learning Agents
Figure 2 for Modeling Mobile Health Users as Reinforcement Learning Agents
Figure 3 for Modeling Mobile Health Users as Reinforcement Learning Agents
Figure 4 for Modeling Mobile Health Users as Reinforcement Learning Agents
Viaarxiv icon

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

Add code
Nov 28, 2022
Figure 1 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Figure 2 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Figure 3 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Figure 4 for An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
Viaarxiv icon

Does the explanation satisfy your needs?: A unified view of properties of explanations

Nov 10, 2022
Figure 1 for Does the explanation satisfy your needs?: A unified view of properties of explanations
Viaarxiv icon