activity
20182025
most citedEfficient Few-Shot Learning Without Prompts

103 citations · 123 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

Nadav Timor, Jonathan Mamou, Daniel Korat +5

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generat…

cs.CL2024

Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models

Jonathan Mamou, Oren Pereg, Daniel Korat +4

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of…

cs.CL202218 cited

Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs

Phillip Howard, Arden Ma, Vasudev Lal +5

The extraction of aspect terms is a critical step in fine-grained sentiment analysis of text. Existing approaches for this task have yielded impressive results when the training an…

cs.CL2022103 cited

Efficient Few-Shot Learning Without Prompts

Lewis Tunstall, Nils Reimers, Unso Eun Seo Jo +4

Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, t…

cs.CL20222 cited

TangoBERT: Reducing Inference Cost by using Cascaded Architecture

Jonathan Mamou, Oren Pereg, Moshe Wasserblat +1

The remarkable success of large transformer-based models such as BERT, RoBERTa and XLNet in many NLP tasks comes with a large increase in monetary and environmental cost due to the…

cs.CL2019

ABSApp: A Portable Weakly-Supervised Aspect-Based Sentiment Extraction System

Oren Pereg, Daniel Korat, Moshe Wasserblat +2

We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction. The system is interpretable and user friendly and does not require labeled training da…