JM
Jason Mars
cs.AIcs.CLcs.LGcs.PLcs.SEcs.DCcs.IRcs.HCcs.MAcs.AR
On Valency
published · living versionsW_n7xvfsx5·v1 · currentpublished
LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
with Thamirawaran Sathiyalogeswaran, Navindu De Silva, Chamikara Siriwardane, W. K. Alwis +2
1 version
Preprints & journals
28 papers in the corpus · 2018–2026LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition2610.27444v1 · Thamirawaran Sathiyalogeswaran, Navindu De Silva, Chamikara Siriwardane et al.2026 · 0 citationsarXivon Valency
ContextRender: From Execution Dependencies to Agent Context2609.37743v1 · Savini Kashmira, Jayanaka L. Dantanarayana, Lingjia Tang et al.2026 · 0 citationsarXiv
Automated Prefetching for Object Spatial Programming Using Temporal Trace Graphs2609.38439v1 · Baichuan Li, Jayanaka Dantanarayana, Savini Kashmira et al.2026 · 0 citationsarXiv
SIGIL: Skill Compilation for Reliable and Efficient Agent Execution2607.27309v3 · Jayanaka Dantanarayana, Savini Kashmira, Lingjia Tang et al.2026 · 0 citationsarXiv
Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels2607.24762v1 · Joshua Brodsky, Dhravid Kumar, Savini Kashmira et al.2026 · 0 citationsarXiv
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 22509.16248v5 · Savini Kashmira, Jayanaka Dantanarayana, Thamirawaran Sathiyalogeswaran et al.2025 · 0 citationsarXiv
GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval2507.08945v1 · Savini Kashmira, Jayanaka L. Dantanarayana, Kriszti'an Flautner et al.2025 · 0 citationsarXiv
SLMEval: Entropy-Based Calibration for Human-Aligned Evaluation of Large Language Models2505.16003v1 · Roland Daynauth, Christopher Clarke, Krisztian Flautner et al.2025 · 0 citationsarXiv
Extending Data Spatial Semantics for Scale Agnostic Programming2504.03109v1 · Jason Mars2025 · 0 citationsarXiv
Object-Spatial Programming2503.15812v6 · Jason Mars2025 · 0 citationsarXiv
TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG2412.05447v3 · Savini Kashmira, Jayanaka L. Dantanarayana, Joshua Brodsky et al.2024 · 5 citationsarXiv
Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat2411.14483v2 · Roland Daynauth, Christopher Clarke, Krisztian Flautner et al.2024 · 2 citationsarXiv
PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization2407.18078v1 · Christopher Clarke, Yuzhao Heng, Lingjia Tang et al.2024 · 0 citationsarXiv
Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments2407.12847v1 · Roland Daynauth, Jason Mars2024 · 0 citationsarXiv
MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming2405.08965v6 · Jayanaka L. Dantanarayana, Yiping Kang, Kugesan Sivasothynathan et al.2024 · 0 citationsarXiv
Guylingo: The Republic of Guyana Creole Corpora2405.03832v3 · Christopher Clarke, Roland Daynauth, Charlene Wilkinson et al.2024 · 3 citationsarXiv
One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI2401.07123v1 · Christopher Clarke, Karthik Krishnamurthy, Walter Talamonti et al.2024 · 1 citationarXiv
Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production2312.14972v3 · Chandra Irugalbandara, Ashish Mahendra, Roland Daynauth et al.2023 · 57 citationsISPASS-2024: 2024 IEEE International Symposium on Performance Analysis of Systems and Software
Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection2307.12935v1 · Christopher Clarke, Matthew Hall, Gaurav Mittal et al.2023 · 10 citationsarXiv
Label Agnostic Pre-training for Zero-shot Text Classification2305.16521v1 · Christopher Clarke, Yuzhao Heng, Yiping Kang et al.2023 · 5 citationsarXiv
The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast2305.09864v1 · Jason Mars, Yiping Kang, Roland Daynauth et al.2023 · 1 citationarXiv
The Case for a Wholistic Serverless Programming Paradigm and Full Stack Automation for AI and Beyond -- The Philosophy of Jaseci and Jac2206.08434v1 · Jason Mars2022 · 1 citationarXiv
One Agent To Rule Them All: Towards Multi-agent Conversational AI2203.07665v1 · Christopher Clarke, Joseph Joshua Peper, Karthik Krishnamurthy et al.2022 · 11 citationsarXiv
Towards Personalized Intelligence at Scale2203.06668v1 · Yiping Kang, Ashish Mahendra, Christopher Clarke et al.2022 · 2 citationsarXiv
A Benchmarking Framework for Interactive 3D Applications in the Cloud2006.13378v2 · Tianyi Liu, Sen He, Sunzhou Huang et al.2020 · 14 citationsarXiv
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction1909.02027v1 · Stefan Larson, Anish Mahendran, Joseph J. Peper et al.2019 · 406 citationsarXiv
Outlier Detection for Improved Data Quality and Diversity in Dialog Systems1904.03122v1 · Stefan Larson, Anish Mahendran, Andrew Lee et al.2019 · 36 citationsarXiv
Rethinking Numerical Representations for Deep Neural Networks1808.02513v1 · Parker Hill, Babak Zamirai, Shengshuo Lu et al.2018 · 6 citationsarXiv
Career total: 141 works. 28 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.