Alert button
Picture for Jason Mars

Jason Mars

Alert button

A Trade-off Analysis of Replacing Proprietary LLMs with Open Source SLMs in Production

Jan 15, 2024
Chandra Irugalbandara, Ashish Mahendra, Roland Daynauth, Tharuka Kasthuri Arachchige, Krisztian Flautner, Lingjia Tang, Yiping Kang, Jason Mars

Viaarxiv icon

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

Jan 13, 2024
Christopher Clarke, Karthik Krishnamurthy, Walter Talamonti, Yiping Kang, Lingjia Tang, Jason Mars

Viaarxiv icon

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

Dec 20, 2023
Chandra Irugalbandara, Ashish Mahendra, Roland Daynauth, Tharuka Kasthuri Arachchige, Krisztian Flautner, Lingjia Tang, Yiping Kang, Jason Mars

Viaarxiv icon

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

Jul 24, 2023
Christopher Clarke, Matthew Hall, Gaurav Mittal, Ye Yu, Sandra Sajeev, Jason Mars, Mei Chen

Viaarxiv icon

Label Agnostic Pre-training for Zero-shot Text Classification

May 25, 2023
Christopher Clarke, Yuzhao Heng, Yiping Kang, Krisztian Flautner, Lingjia Tang, Jason Mars

Figure 1 for Label Agnostic Pre-training for Zero-shot Text Classification
Figure 2 for Label Agnostic Pre-training for Zero-shot Text Classification
Figure 3 for Label Agnostic Pre-training for Zero-shot Text Classification
Figure 4 for Label Agnostic Pre-training for Zero-shot Text Classification
Viaarxiv icon

The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast

May 17, 2023
Jason Mars, Yiping Kang, Roland Daynauth, Baichuan Li, Ashish Mahendra, Krisztian Flautner, Lingjia Tang

Figure 1 for The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast
Figure 2 for The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast
Figure 3 for The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast
Figure 4 for The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast
Viaarxiv icon

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

Jun 16, 2022
Jason Mars

Figure 1 for The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond -- The Philosophy of Jaseci and Jac
Figure 2 for The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond -- The Philosophy of Jaseci and Jac
Figure 3 for The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond -- The Philosophy of Jaseci and Jac
Figure 4 for The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond -- The Philosophy of Jaseci and Jac
Viaarxiv icon

One Agent To Rule Them All: Towards Multi-agent Conversational AI

Mar 15, 2022
Christopher Clarke, Joseph Joshua Peper, Karthik Krishnamurthy, Walter Talamonti, Kevin Leach, Walter Lasecki, Yiping Kang, Lingjia Tang, Jason Mars

Figure 1 for One Agent To Rule Them All: Towards Multi-agent Conversational AI
Figure 2 for One Agent To Rule Them All: Towards Multi-agent Conversational AI
Figure 3 for One Agent To Rule Them All: Towards Multi-agent Conversational AI
Figure 4 for One Agent To Rule Them All: Towards Multi-agent Conversational AI
Viaarxiv icon

Towards Personalized Intelligence at Scale

Mar 13, 2022
Yiping Kang, Ashish Mahendra, Christopher Clarke, Lingjia Tang, Jason Mars

Figure 1 for Towards Personalized Intelligence at Scale
Figure 2 for Towards Personalized Intelligence at Scale
Figure 3 for Towards Personalized Intelligence at Scale
Figure 4 for Towards Personalized Intelligence at Scale
Viaarxiv icon

An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction

Sep 04, 2019
Stefan Larson, Anish Mahendran, Joseph J. Peper, Christopher Clarke, Andrew Lee, Parker Hill, Jonathan K. Kummerfeld, Kevin Leach, Michael A. Laurenzano, Lingjia Tang, Jason Mars

Figure 1 for An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Figure 2 for An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Figure 3 for An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Figure 4 for An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Viaarxiv icon