Title |
|---|
 Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in
ML ServingSymposium on Operating Systems Principles (SOSP), 2023 |
 BERT Lost Patience Won't Be Robust to Adversarial SlowdownNeural Information Processing Systems (NeurIPS), 2023 |
 Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight
BERTIEEE Transactions on Signal Processing (IEEE Trans. Signal Process.), 2022 |
 Avoid Overthinking in Self-Supervised Models for Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 BEBERT: Efficient and Robust Binary Ensemble BERTIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionInterspeech (Interspeech), 2022 |
 Latency Adjustable Transformer Encoder for Language UnderstandingIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022 |
 Pre-trained Models for Natural Language Processing: A SurveyScience China Technological Sciences (Sci China Technol Sci), 2020 |
