2022-2023年论文系列之模型轻量化和推理加速

定义最新

通过Connected Papers搜索引用PaBEE/DeeBERT/FastBERT的最新工作，涵盖：

• 模型推理加速
• 边缘设备应用
• 生成模型
• BERT模型
• 知识蒸馏

论文目录

1. SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference

2. SKDBERT: Compressing BERT via Stochastic Knowledge Distillation

3. COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models

4. Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression

5. Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting

6. A Simple Hash-Based Early Exiting Approach For Language Understanding and Generat