Jason Mars

Jason Mars

University of Michigan

H-index: 38

North America-United States

About Jason Mars

Jason Mars, With an exceptional h-index of 38 and a recent h-index of 28 (since 2020), a distinguished researcher at University of Michigan, specializes in the field of Computer Architecture - Runtime Systems - Compilers - Emerging Cloud/Mobile Platforms.

His recent articles reflect a diverse array of research interests and contributions to the field:

System and methods for sharing memory subsystem resources among datacenter applications

One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI

Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's GPT-4 with Self-Hosted Open Source SLMs in Production

Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection

Label Agnostic Pre-training for Zero-shot Text Classification

Jaseci: Programming Paradigm and Runtime Stack for Building Scale-Out Production Applications Easy and Fast

Systems and methods for zero-shot, fast-generation and implementation of an intelligent virtual dialogue agent using one or more pre-trained machine learning-based language …

Systems and methods for intelligently configuring and deploying a control structure of a machine learning-based dialogue system

Jason Mars Information

University

Position

Professor of Computer Science and Engineering

Citations(all)

7733

Citations(since 2020)

4806

Cited By

4858

hIndex(all)

38

hIndex(since 2020)

28

i10Index(all)

66

i10Index(since 2020)

51

Email

University Profile Page

Google Scholar

Jason Mars Skills & Research Interests

Computer Architecture - Runtime Systems - Compilers - Emerging Cloud/Mobile Platforms

Top articles of Jason Mars

System and methods for sharing memory subsystem resources among datacenter applications

2024/1/16

One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI

arXiv preprint arXiv:2401.07123

2024/1/13

Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's GPT-4 with Self-Hosted Open Source SLMs in Production

arXiv preprint arXiv:2312.14972

2023/12/20

Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection

arXiv preprint arXiv:2307.12935

2023/7/24

Label Agnostic Pre-training for Zero-shot Text Classification

arXiv preprint arXiv:2305.16521

2023/5/25

Jaseci: Programming Paradigm and Runtime Stack for Building Scale-Out Production Applications Easy and Fast

IEEE Computer Architecture Letters

2023/5/18

Jason Mars
Jason Mars

H-Index: 30

Lingjia Tang
Lingjia Tang

H-Index: 30

Systems and methods for zero-shot, fast-generation and implementation of an intelligent virtual dialogue agent using one or more pre-trained machine learning-based language …

2022/11/15

Systems and methods for intelligently configuring and deploying a control structure of a machine learning-based dialogue system

2022/10/25

The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond--The Philosophy of Jaseci and Jac

arXiv preprint arXiv:2206.08434

2022/6/16

Jason Mars
Jason Mars

H-Index: 30

One agent to rule them all: Towards multi-agent conversational AI

arXiv preprint arXiv:2203.07665

2022/3/15

Towards Personalized Intelligence at Scale

arXiv preprint arXiv:2203.06668

2022/3/13

System and method for implementing an artificially intelligent virtual assistant using machine learning

2021/8/19

Systems and methods for automatically categorizing unstructured data and improving a machine learning-based dialogue system

2021/6/24

Systems and methods for automatically detecting and repairing slot errors in machine learning training data for a machine learning-based dialogue system

2021/2/23

Systems and methods for constructing an artificially diverse corpus of training data samples for training a contextually-biased model for a machine learning-based dialogue system

2020/10/6

Systems and methods for machine learning-based multi-intent segmentation and classification

2020/11/3

A benchmarking framework for interactive 3d applications in the cloud

2020/10/17

Systems and methods for intelligently curating machine learning training data and improving machine learning model performance

2020/6/9

Systems and methods for automatically configuring training data for training machine learning models of a machine learning-based dialogue system

2020/6/9

See List of Professors in Jason Mars University(University of Michigan)