Moshe Wasserblat

Efficient Few-Shot Learning Without Prompts

Nils Reimers, Lewis Tunstall, Unso Eun Seo Jo, 2022, ArXiv.

Prune Once for All: Sparse Pre-Trained Language Models pdf

Moshe Wasserblat, Haihao Shen, Ofir Zafrir, 2021, ArXiv.

Term Set Expansion based NLP Architect by Intel AI Lab pdf

Moshe Wasserblat, Oren Pereg, Peter Izsak, 2018, EMNLP.

Q8BERT: Quantized 8Bit BERT pdf

Moshe Wasserblat, Peter Izsak, Ofir Zafrir, 2019, 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS).

QuaLA-MiniLM: a Quantized Length Adaptive MiniLM

Haihao Shen, Chang Wang, Moshe Wasserblat, 2022, ArXiv.

Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction

Moshe Wasserblat, Oren Pereg, Daniel Korat, 2020, COLING.

InterpreT: An Interactive Visualization Tool for Interpreting Transformers

Moshe Wasserblat, Oren Pereg, Phillip Howard, 2021, EACL.

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

Yi Ding, Haihao Shen, Yunqian Luo, 2023, ArXiv.

Fast DistilBERT on CPUs

Yi Ding, Haihao Shen, Xinyu. Ye, 2022, ArXiv.

Optimizing Retrieval-augmented Reader Models via Token Elimination

Ido Dagan, Avi Caciularu, Moshe Wasserblat, 2023, EMNLP.

Distributed Speculative Inference of Large Language Models

Tomer Galanti, Daniel Korat, Moshe Wasserblat, 2024, ArXiv.