6 papers
CREST: Deployment-Realistic Hardware-in-the-Loop NAS for Embedded Sensing Systems
Joseph Q. Zales, Pragya Sharma, Mani Srivastava
Deploying neural networks on low-power microcontrollers (MCUs) requires selecting model architectures under tight memory, latency, and energy constraints. Existing workflows often…
FMplex: Model Virtualization for Serving Extensible Foundation Models
Hetvi Shastri, Pragya Sharma, Walid A. Hanafy +3
Foundation models (FMs) are increasingly used as backbones for downstream tasks across language, vision, time-series, and multimodal applications. Yet existing model-serving system…
CADET: A Modular Platform for Evaluating Distributed Cooperative Autonomy in Connected Autonomous Vehicles
Pragya Sharma, Brian Wang, Mani Srivastava
Deep learning models are increasingly central to autonomous vehicle (AV) pipelines, yet their integration has traditionally followed a monolithic design where perception, planning,…
Real-Time Trust Verification for Safe Agentic Actions using TrustBench
Tavishi Sharma, Vinayak Sharma, Pragya Sharma
As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time act…
Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference
Pragya Sharma, Hang Qiu, Mani Srivastava
The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution pl…
FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
Hetvi Shastri, Pragya Sharma, Walid A. Hanafy +2
Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-se…