Picture for Yevgeniy Vorobeychik

Yevgeniy Vorobeychik

Dataset Representativeness and Downstream Task Fairness

Add code
Jun 28, 2024
Figure 1 for Dataset Representativeness and Downstream Task Fairness
Figure 2 for Dataset Representativeness and Downstream Task Fairness
Figure 3 for Dataset Representativeness and Downstream Task Fairness
Figure 4 for Dataset Representativeness and Downstream Task Fairness
Viaarxiv icon

Adversarial Machine Unlearning

Add code
Jun 11, 2024
Viaarxiv icon

GOMAA-Geo: GOal Modality Agnostic Active Geo-localization

Add code
Jun 04, 2024
Viaarxiv icon

Verified Safe Reinforcement Learning for Neural Network Dynamic Models

Add code
May 25, 2024
Viaarxiv icon

Axioms for AI Alignment from Human Feedback

Add code
May 23, 2024
Viaarxiv icon

Learning Linear Utility Functions From Pairwise Comparison Queries

Add code
May 07, 2024
Viaarxiv icon

Attacks on Node Attributes in Graph Neural Networks

Add code
Feb 19, 2024
Viaarxiv icon

Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning

Add code
Feb 14, 2024
Figure 1 for Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning
Figure 2 for Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning
Figure 3 for Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning
Figure 4 for Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning
Viaarxiv icon

Preference Poisoning Attacks on Reward Model Learning

Add code
Feb 02, 2024
Viaarxiv icon

Hierarchical Multi-Agent Reinforcement Learning for Assessing False-Data Injection Attacks on Transportation Networks

Add code
Dec 22, 2023
Viaarxiv icon