papers

Publications (26)

cs.CL2023

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

Christopher Clarke, Matthew Hall, Gaurav Mittal +4

Classic approaches to content moderation typically apply a rule-based heuristic approach to flag content. While rules are easily customizable and intuitive for humans to interpret,…

cs.PL2025

Extending Data Spatial Semantics for Scale Agnostic Programming

Jason Mars

We introduce extensions to Data Spatial Programming (DSP) that enable scale-agnostic programming for application development. Building on DSP's paradigm shift from data-to-compute…

cs.PL2026

GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2

Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran +3

This paper presents GraphMend, a compiler technique that automatically fixes FX graph breaks in PyTorch 2 programs. Although PyTorch 2 introduced TorchDynamo and TorchInductor to e…

cs.SE2024

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

Chandra Irugalbandara, Ashish Mahendra, Roland Daynauth +6

Many companies use large language models (LLMs) offered as a service, like OpenAI's GPT-4, to create AI-enabled product experiences. Along with the benefits of ease-of-use and shor…

cs.HC2024

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

Christopher Clarke, Karthik Krishnamurthy, Walter Talamonti +3

Conversational agents have been gaining increasing popularity in recent years. Influenced by the widespread adoption of task-oriented agents such as Apple Siri and Amazon Alexa, th…

cs.CL2024

PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization

Christopher Clarke, Yuzhao Heng, Lingjia Tang +1

The recent emergence of Large Language Models (LLMs) has heralded a new era of human-AI interaction. These sophisticated models, exemplified by Chat-GPT and its successors, have ex…

cs.IR2025

GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval

Savini Kashmira, Jayanaka L. Dantanarayana, Krisztián Flautner +2

Conventional Retrieval Augmented Generation (RAG) approaches are common in text-based applications. However, they struggle with structured, interconnected datasets like knowledge g…

cs.CL2025

SLMEval: Entropy-Based Calibration for Human-Aligned Evaluation of Large Language Models

Roland Daynauth, Christopher Clarke, Krisztian Flautner +2

The LLM-as-a-Judge paradigm offers a scalable, reference-free approach for evaluating language models. Although several calibration techniques have been proposed to better align th…

cs.LG2025

TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG

Savini Kashmira, Jayanaka L. Dantanarayana, Joshua Brodsky +5

Retrieval-Augmented Generation (RAG) is one of the leading and most widely used techniques for enhancing LLM retrieval capabilities, but it still faces significant limitations in c…

cs.CL2025

Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat

Roland Daynauth, Christopher Clarke, Krisztian Flautner +2

Deciding which large language model (LLM) to use is a complex challenge. Pairwise ranking has emerged as a new method for evaluating human preferences for LLMs. This approach entai…

cs.LG2018

Rethinking Numerical Representations for Deep Neural Networks

Parker Hill, Babak Zamirai, Shengshuo Lu +9

With ever-increasing computational demand for deep learning, it is critical to investigate the implications of the numeric representation and precision of DNN model weights and act…

cs.CL2023

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

Jason Mars, Yiping Kang, Roland Daynauth +4

Today's production scale-out applications include many sub-application components, such as storage backends, logging infrastructure and AI models. These components have drastically…

cs.SE2026

SIGIL: Compiling Agent Skills into Typed Harnesses

Jayanaka Dantanarayana, Savini Kashmira, Lingjia Tang +1

The paper presents SIGIL, a system that compiles natural‑language agent skills into typed executable harnesses, improving step compliance and efficiency across different language m…

#agent skills#skill compilation#typed intermediate representation#harness generation
cs.CL2019

Outlier Detection for Improved Data Quality and Diversity in Dialog Systems

Stefan Larson, Anish Mahendran, Andrew Lee +6

In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outl…

cs.CL2019

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

Stefan Larson, Anish Mahendran, Joseph J. Peper +8

Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover eve…

cs.CL2024

Guylingo: The Republic of Guyana Creole Corpora

Christopher Clarke, Roland Daynauth, Charlene Wilkinson +2

While major languages often enjoy substantial attention and resources, the linguistic diversity across the globe encompasses a multitude of smaller, indigenous, and regional langua…

cs.CL2022

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

Christopher Clarke, Joseph Joshua Peper, Karthik Krishnamurthy +6

The increasing volume of commercially available conversational agents (CAs) on the market has resulted in users being burdened with learning and adopting multiple agents to accompl…

cs.DC2020

A Benchmarking Framework for Interactive 3D Applications in the Cloud

Tianyi Liu, Sen He, Sunzhou Huang +4

With the growing popularity of cloud gaming and cloud virtual reality (VR), interactive 3D applications have become a major type of workloads for the cloud. However, despite their…

cs.CL2024

Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments

Roland Daynauth, Jason Mars

The SLAM paper demonstrated that on-device Small Language Models (SLMs) are a viable and cost-effective alternative to API-based Large Language Models (LLMs), such as OpenAI's GPT-…

cs.CL2023

Label Agnostic Pre-training for Zero-shot Text Classification

Christopher Clarke, Yuzhao Heng, Yiping Kang +3

Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world ap…

cs.SE2025

Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering

Jayanaka L. Dantanarayana, Savini Kashmira, Thakee Nathees +4

AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Program…

cs.PL2025

Object-Spatial Programming

Jason Mars

The evolution of programming languages from low-level assembly to high-level abstractions demonstrates a fundamental principle: by constraining how programmers express computation…

cs.DC2022

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

Jason Mars

In this work, the case is made for a wholistic top-down re-envisioning of the system stack from the programming language level down through the system architecture to bridge this c…

cs.AI2026

Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels

Joshua Brodsky, Dhravid Kumar, Savini Kashmira +4

Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolut…

cs.PL2025

MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming

Jayanaka L. Dantanarayana, Yiping Kang, Kugesan Sivasothynathan +6

Software development is shifting from traditional programming to AI-integrated applications that leverage generative AI and large language models (LLMs) during runtime. However, in…

cs.CL2022

Towards Personalized Intelligence at Scale

Yiping Kang, Ashish Mahendra, Christopher Clarke +2

Personalized Intelligence (PI) is the problem of providing customized AI experiences tailored to each individual user. In many applications, PI is preferred or even required. Exist…