Safin-1: Safety from Within through Memory-Native State Evolution
Paper • 2609.00092 • Published • 21
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Mingzh21
authored a
paper about 1 month ago
Mingzh21
submitted a
paper to Daily Papers about 1 month ago
Mingzh21
authored a
paper about 1 month ago
yushaohan
submitted a
paper to Daily Papers about 1 month ago
two-tiger
updated a
dataset about 1 month ago
Add Safety-v2 trajectories
#3 opened about 1 month ago
by 
two-tiger
Replace Capability with Capability_v2
#2 opened about 1 month ago
by two-tiger
shenqiorient
published a
dataset 3 months ago
yueyue0407
updated a
dataset 3 months ago
YuLillll
authored 3
papers 3 months ago
Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
Paper • 2506.05872 • Published • 1
ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent Safety
Paper • 2604.02022 • Published • 16
Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance
Paper • 2605.24203 • Published • 1
jinjinyien
updated a
collection 4 months ago
jinjinyien
updated a
dataset 4 months ago
jinjinyien
published a
dataset 4 months ago
jasonrqh
authored 3
papers 4 months ago
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
Paper • 2601.15075 • Published
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Paper • 2605.26494 • Published • 38
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Paper • 2605.29801 • Published • 145
jasonrqh
submitted a
paper to Daily Papers 4 months ago
RainbowQTT
updated a
model 4 months ago