Picture for Jerry Zhi-Yang He

Jerry Zhi-Yang He

CoS: Enhancing Personalization and Mitigating Bias with Context Steering

Add code
May 02, 2024
Viaarxiv icon

Quantifying Assistive Robustness Via the Natural-Adversarial Frontier

Add code
Oct 16, 2023
Viaarxiv icon

Learning Representations that Enable Generalization in Assistive Tasks

Add code
Dec 05, 2022
Viaarxiv icon

A Study of Causal Confusion in Preference-Based Reward Learning

Add code
Apr 13, 2022
Figure 1 for A Study of Causal Confusion in Preference-Based Reward Learning
Figure 2 for A Study of Causal Confusion in Preference-Based Reward Learning
Figure 3 for A Study of Causal Confusion in Preference-Based Reward Learning
Figure 4 for A Study of Causal Confusion in Preference-Based Reward Learning
Viaarxiv icon

Assisted Robust Reward Design

Add code
Nov 18, 2021
Figure 1 for Assisted Robust Reward Design
Figure 2 for Assisted Robust Reward Design
Figure 3 for Assisted Robust Reward Design
Figure 4 for Assisted Robust Reward Design
Viaarxiv icon