Dongrui Liu's picture

Dongrui Liu

shenqiorient

·

https://shenqildr.github.io/

AI & ML interests

Trustworthy AI

Recent Activity

authored a paper about 13 hours ago

Trap of Feature Diversity in the Learning of MLPs

authored a paper about 13 hours ago

MLP Can Be A Good Transformer Learner

authored a paper about 13 hours ago

Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues

View all activity

Organizations

commented a paper about 18 hours ago

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5

Paper • 2602.14457 • Published 5 days ago • 7 •

commented 2 papers 8 days ago

DeepSight: An All-in-One LM Safety Toolkit

Paper • 2602.12092 • Published 8 days ago • 13 •

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Paper • 2602.08990 • Published 11 days ago • 69 •

commented a paper 24 days ago

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

Paper • 2601.18491 • Published 25 days ago • 123 •