Safin-1: Safety from Within through Memory-Native State Evolution Paper • 2609.00092 • Published Aug 31 • 22
Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models Paper • 2610.25791 • Published Oct 19 • 4
REX Collection Towards Architectural-Level Safety Control: Relocating Hazardous Knowledge into Removable Experts in Mixture-of-Experts Models • 7 items • Updated about 1 month ago • 3
ReSI Collection ReSI: Recursive Safety Improvement toward Resistant and Resilient AI • 5 items • Updated Oct 11 • 1
ReSI: Recursive Safety Improvement toward Resistant and Resilient AI Paper • 2610.12233 • Published Oct 8 • 30
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning Paper • 2601.21468 • Published Jan 29 • 25
Quantile Advantage Estimation for Entropy-Safe Reasoning Paper • 2509.22611 • Published Sep 26, 2025 • 119
view article Article Open-R1: a fully open reproduction of DeepSeek-R1 +1 eliebak, lvwerra, lewtun • Jan 28, 2025 • 891