Lipeng (Tony) He

ttttonyhe's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 9 days ago

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense

Paper • 2502.00840 • Published 12 days ago •

3

liked a dataset 21 days ago

PKU-Alignment/BeaverTails

Viewer • Updated Oct 17, 2023 • 364k • 5.03k • 48

liked a model 2 months ago

cais/HarmBench-Llama-2-13b-cls

Text Generation • Updated Mar 17, 2024 • 54.9k • 18

upvoted 2 papers 2 months ago

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Paper • 2402.04249 • Published Feb 6, 2024 • 4

Star Attention: Efficient LLM Inference over Long Sequences

Paper • 2411.17116 • Published Nov 26, 2024 • 50

liked a dataset 3 months ago

walledai/AdvBench

Viewer • Updated Jul 4, 2024 • 520 • 5.7k • 13

authored a paper 4 months ago

LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts

Paper • 2401.07261 • Published Jan 14, 2024