shenqi

shenqiorient's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 22 hours ago

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Paper • 2601.18491 • Published 3 days ago • 62

upvoted a collection about 23 hours ago

AgentDoG

Collection

A Diagnostic Guardrail Framework for AI Agent Safety and Security • 11 items • Updated about 15 hours ago • 80

upvoted a paper 3 months ago

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Paper • 2507.11097 • Published Jul 15, 2025 • 64

upvoted 2 papers 4 months ago

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

Paper • 2510.08211 • Published Oct 9, 2025 • 22

Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents

Paper • 2509.26354 • Published Sep 30, 2025 • 18

upvoted a paper 8 months ago

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning

Paper • 2506.02867 • Published Jun 3, 2025 • 2

upvoted a paper about 1 year ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22, 2025 • 61