Meng Li

DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation

Attention is Not Always Needed: Attention Sink Forges a Native MoE in Attention Layers

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference

EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference

CopyLens: Dynamically Flagging Copyrighted Sub-Dataset Contributions to LLM Outputs