Long Phan

~Long_Phan1

5

论文总数

2.5

年均投稿

6.1

平均评分

接收情况3/5

会议分布

ICLR

3

NeurIPS

2

发表论文 (5 篇)

20252 篇

Tamper-Resistant Safeguards for Open-Weight LLMs

ICLR 2025Poster

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

NeurIPS 2025Spotlight

20243 篇

Robustness Evaluation of Proxy Models against Adversarial Optimization

ICLR 2024Rejected

Improving Alignment and Robustness with Circuit Breakers

NeurIPS 2024Poster

Enhancing Neural Network Transparency through Representation Analysis

ICLR 2024Rejected

合作者 (20)

Dan Hendrycks5 篇

Mantas Mazeika4 篇

J Zico Kolter3 篇

Matt Fredrikson3 篇

Justin Wang2 篇

Maxwell Lin2 篇