Sharon Li

This page is a disambiguation page, it actually contains mutiple papers from persons of the same or a similar name.

Bibliography

2025
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense.
CoRR, October, 2025

Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions.
CoRR, October, 2025

General Exploratory Bonus for Optimistic Exploration in RLHF.
CoRR, October, 2025

KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning.
CoRR, October, 2025

2024
Maximizing Information Gain in Privacy-Aware Active Learning of Email Anomalies.
CoRR, 2024

2023
Implementing Active Learning in Cybersecurity: Detecting Anomalies in Redacted Emails.
CoRR, 2023


  Loading...