LM

Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length

Dynamic sequence length reduction to further enhance the inference efficiency of TinyBERT beyond static compression - ___[ENLSP Workshop @ NeurIPS 2021](https://neurips2021-nlp.github.io)___

Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search

Train-once, anytime-inference framework for any transformer via length drop training and multi-objective evolutionary search - ___[ACL 2021](https://2021.aclweb.org)___

Large Product Key Memory for Pretrained Language Models

Large product key memory augmentation for pretrained language models with catastrophic drift mitigation for improved accuracy and speed trade-off in finetuning - ___[Findings of EMNLP 2020](https://2020.emnlp.org/)___

Subword Language Model for Query Auto-Completion

Subword language model for faster query auto-completion with a retrace algorithm and a reranking method by approximate marginalization - ___[EMNLP-IJCNLP 2019](https://www.emnlp-ijcnlp2019.org/)___

Mimicry Resilient Program Behavior Modeling with LSTM based Branch Models

Anomaly detection robust to mimicry attacks via language modeling of branch sequences - ___[S&P 2018 DLS Workshop](https://www.ieee-security.org/TC/SPW2018/DLS/)___

LSTM-Based System-Call Language Modelling and Robust Ensemble Method for Designing Host-Based Intrusion Detection System

System-call language modeling for anomaly-based host intrusion detection with an ensemble method to accumulate highly normal sequences and reduce false-alarm rates