Výsledky vyhledávání - "Xu, Shengzhe"

Report

LLM Augmentations to support Analytical Reasoning over Multiple Documents

Autor: Yousuf, Raquib Bin, Defelice, Nicholas, Sharma, Mandar, Xu, Shengzhe, Ramakrishnan, Naren

Building on their demonstrated ability to perform a variety of tasks, we investigate the application of large language models (LLMs) to enhance in-depth analytical reasoning within the context of intelligence analysis. Intelligence analysts typically

Externí odkaz: http://arxiv.org/abs/2411.16116

Zobrazit plný text záznamu

Report

Are LLMs Naturally Good at Synthetic Tabular Data Generation?

Autor: Xu, Shengzhe, Lee, Cho-Ting, Sharma, Mandar, Yousuf, Raquib Bin, Muralidhar, Nikhil, Ramakrishnan, Naren

Large language models (LLMs) have demonstrated their prowess in generating synthetic text and images; however, their potential for generating tabular data -- arguably the most common data type in business and scientific applications -- is largely und

Externí odkaz: http://arxiv.org/abs/2406.14541

Zobrazit plný text záznamu

Report

Information Guided Regularization for Fine-tuning Language Models

Autor: Sharma, Mandar, Muralidhar, Nikhil, Xu, Shengzhe, Yousuf, Raquib Bin, Ramakrishnan, Naren

The pretraining-fine-tuning paradigm has been the de facto strategy for transfer learning in modern language modeling. With the understanding that task adaptation in LMs is often a function of parameters shared across tasks, we argue that a more surg

Externí odkaz: http://arxiv.org/abs/2406.14005

Zobrazit plný text záznamu

Report

Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems

Autor: Xu, Shengzhe, Thomas, Christo Kurisummoottil, Hashash, Omar, Muralidhar, Nikhil, Saad, Walid, Ramakrishnan, Naren

Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. However, recent efforts on LLMs for wireless networks are limited to a direct application of existing language models that were designed fo

Externí odkaz: http://arxiv.org/abs/2402.01748

Zobrazit plný text záznamu

Akademický článek

Practical Security of Continuous Variable Quantum Key Distribution Ascribable to Imperfect Modulator for Fiber Channel.

Autor: Xu, Shengzhe^1,2 (AUTHOR) 2023201648@qdu.edu.cn, Zhou, Zicheng^2,3 (AUTHOR), Guo, Ying^2,4 (AUTHOR) guoying@bupt.edu.cn

Publikováno v: Mathematics (2227-7390). May2024, Vol. 12 Issue 9, p1356. 8p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

STAN: Synthetic Network Traffic Generation with Generative Neural Models

Autor: Xu, Shengzhe, Marwah, Manish, Arlitt, Martin, Ramakrishnan, Naren

Deep learning models have achieved great success in recent years but progress in some domains like cybersecurity is stymied due to a paucity of realistic datasets. Organizations are reluctant to share such data, even internally, due to privacy reason

Externí odkaz: http://arxiv.org/abs/2009.12740

Zobrazit plný text záznamu