SCOPE
liuqirui
neuqrui
AI & ML interests
ai safety
Recent Activity
authored a paper 4 days ago
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models authored a paper 4 days ago
SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning authored a paper 4 days ago
EOPSA: Efficient On-Policy Self-Distilled Safety AlignmentOrganizations
None yet
models 9
neuqrui/webshop-analyzer-qwen2.5-3b
Text Generation • 3B • Updated • 69
neuqrui/alfworld-analyzer-qwen2.5-3b
3B • Updated • 26
neuqrui/EOPSA-DeepSeek-R1-7B
Text Generation • 8B • Updated • 33
neuqrui/EOPSA-Qwen3-32B
Text Generation • 33B • Updated • 96
neuqrui/EOPSA-Qwen3-14B
Text Generation • 15B • Updated • 15
neuqrui/EOPSA-Qwen3-4B
Text Generation • 4B • Updated • 14
neuqrui/EOPSA-Qwen3-1.7B
Text Generation • 2B • Updated • 17 • 1
neuqrui/safe-rlsd-qwen3-4B
4B • Updated • 6
neuqrui/safe-rlsd-qwen3-1.7b
2B • Updated • 6 • 1