AI.info

Yi Yu

Explore Yi Yu on AI.info.

• All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference
• Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
• FairGU: Fairness-aware Graph Unlearning in Social Networks
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
• When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
• TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
• From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge