Cheng Jin

matrix72

2 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 19 days ago

Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models

updated a collection 21 days ago

updated a model 21 days ago

AI45Research/REX-Qwen3.5-35B-A3B-Cyber-F3

View all activity

Organizations

upvoted a paper 19 days ago

Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models

Paper • 2610.25791 • Published 22 days ago • 4

upvoted a paper 26 days ago

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

Paper • 2610.12233 • Published Oct 8 • 30