Yanxuan Yu

Efficient Inference for Language Models · Query-Aware Caching · Sparse Attention · Systems for Large-Scale NLP · Real-Time Inference · CUDA Kernel Optimization · Multimodal Biomedical Applications · Signal Processing for Neural Data · Machine Learning for Biomedical Engineering · Embedded AI Systems · Small Language Models · TinyLLaMA · Lightweight Transformer Runtime · Token Selection · Page-Level Cache Scheduling · Memory-Constrained Serving