TianGao

ThomasGao

2 1

·

AI & ML interests

None yet

Recent Activity

authored a paper 3 days ago

Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks

liked a model 11 days ago

XHToken/Spark-X2.5-4B

upvoted a paper 2 months ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

View all activity

Organizations

None yet

authored a paper 3 days ago

Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks

Paper • 2609.05794 • Published 11 days ago

liked a model 11 days ago

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated about 15 hours ago • 25.7k • 1.2k

upvoted a paper 2 months ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Paper • 2605.29801 • Published May 28 • 150

upvoted an article about 1 year ago

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

NormalUhr

•

Feb 11, 2025

• 132