Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models
Paper • 2610.25791 • Published • 3
Cheng Jin
matrix72
·
AI & ML interests
None yet
Recent Activity
updated a collection 3 days ago
REX updated a model 3 days ago
AI45Research/REX-Qwen3.5-35B-A3B-Cyber-F3Organizations
upvoted a paper about 17 hours ago
updated a
collection 3 days ago
updated 6
models 3 days ago
AI45Research/REX-Qwen3.5-35B-A3B-Cyber-F3
Image-Text-to-Text • 37B • Updated • 27
AI45Research/REX-Qwen3.5-35B-A3B-Bio-F3
Image-Text-to-Text • 37B • Updated • 18
AI45Research/REX-Intern-S2-Cyber-F3
Image-Text-to-Text • 38B • Updated • 23
AI45Research/REX-Intern-S2-Bio-F3
Image-Text-to-Text • 36B • Updated • 27
AI45Research/REX-Gemma-4-26B-A4B-Cyber-F3
Image-Text-to-Text • 28B • Updated • 24
AI45Research/REX-Gemma-4-26B-A4B-Bio-F3
Image-Text-to-Text • 28B • Updated • 20
updated a
collection 4 days ago
published a
model 4 days ago
updated a
collection 4 days ago
published a
model 4 days ago
updated a
collection 4 days ago
published a
model 4 days ago
updated a
collection 4 days ago
published a
model 4 days ago
updated a
collection 4 days ago
published a
model 6 days ago
updated a
collection 6 days ago
published a
model 6 days ago