Sharon Li

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

Bibliography

2026

DECOR: Auditing LLM Deception via Information Manipulation Theory.

[BibT_eX]

[DOI]

CoRR, May, 2026

Auditing Agent Harness Safety.

[BibT_eX]

[DOI]

CoRR, May, 2026

Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks.

[BibT_eX]

[DOI]

Yu Wang

Sharon Li

CoRR, April, 2026

Combating Data Laundering in LLM Training.

[BibT_eX]

[DOI]

CoRR, April, 2026

LAD: Learning Advantage Distribution for Reasoning.

[BibT_eX]

[DOI]

Wendi Li

Sharon Li

CoRR, February, 2026

How Retrieved Context Shapes Internal Representations in RAG.

[BibT_eX]

[DOI]

Samuel Yeh

Sharon Li

CoRR, February, 2026

Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents.

[BibT_eX]

[DOI]

CoRR, February, 2026

Unsupervised Domain Adaptation for Binary Classification with an Unobservable Source Subpopulation.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2026

2025

Learning to Think Fast and Slow for Visual Language Models.

[BibT_eX]

[DOI]

CoRR, November, 2025

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

[BibT_eX]

[DOI]

CoRR, October, 2025

Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions.

[BibT_eX]

[DOI]

CoRR, October, 2025

General Exploratory Bonus for Optimistic Exploration in RLHF.

[BibT_eX]

[DOI]

Wendi Li

Changdae Oh

Sharon Li

CoRR, October, 2025

Visual Instruction Bottleneck Tuning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024

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

[BibT_eX]

[DOI]

CoRR, 2024

2023

Implementing Active Learning in Cybersecurity: Detecting Anomalies in Redacted Emails.

[BibT_eX]

[DOI]

CoRR, 2023

Sharon Li

Bibliography

Loading...