Qihan Ren
jasonrqh
AI & ML interests
explainable AI, LLM
Recent Activity
upvoted
a
paper
about 2 hours ago
DeepSeek-OCR 2: Visual Causal Flow
upvoted
a
paper
about 3 hours ago
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
authored
a paper
about 19 hours ago
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Organizations
