AI.info

Lei Zhu

Explore Lei Zhu on AI.info.

• ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
• VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
• MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
• BLM$_1$: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning