1

ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inference
HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline
MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers
PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding
var dimensionValue = 'SOME_DIMENSION_VALUE'; ga('set', 'dimension1', dimensionValue);