Lipeng (Tony) He's picture

3 5 25

Lipeng (Tony) He

ttttonyhe

·

https://lipeng.ac

ttttonyhe

AI & ML interests

Trustworthy Machine Learning

Recent Activity

authored a paper 18 days ago

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

submitted a paper 19 days ago

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

updated a collection 20 days ago

Red-Teaming Models & Datasets

View all activity

Organizations

authored a paper 18 days ago

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

Paper • 2601.01887 • Published 22 days ago • 1

submitted a paper to Daily Papers 19 days ago

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

Paper • 2601.01887 • Published 22 days ago • 1

authored a paper 3 months ago

Locket: Robust Feature-Locking Technique for Language Models

Paper • 2510.12117 • Published Oct 14, 2025 • 1

authored a paper 8 months ago

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs

Paper • 2505.20139 • Published May 26, 2025 • 19

authored a paper over 1 year ago

LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts

Paper • 2401.07261 • Published Jan 14, 2024