18 citations · 74 across the 36 of their papers we have counts for
41 papers
EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model
Rithvik Jonna, Man Namgung, Aakash Gurram +1
Vision-language navigation (VLN) models perform well but target compute-rich platforms, limiting deployment on memory- and power-constrained robotic edge devices. Compression alone…
Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
Uttej Kallakuri, Boxun Hu, Ankur A. Butala +2
Generative and Agentic IoT systems offer a promising foundation for digital healthcare applications that combine sensing, personalized reasoning, and autonomous interaction in real…
LEAP-NBV: Lightweight Edge Active-Perception for Foundation-Model Next-Best-View Planning
Boxun Hu, Jiawei Ge, Axel Krieger +2
Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visual perception. A representat…
ShatterQuant: Breaking Uniform Precision with Block-Wise Mixed-Precision on a Systolic Transformer Hardware Accelerator
Mikolaj Walczak, Edward Humes, Chao Fang +2
Due to limited support for intra-tensor heterogeneous precision in conventional accelerators, neural network quantization remains largely restricted to per-tensor precision assignm…
BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation
Rithvik Jonna, Aakash Gurram, Man Namgung +2
Vision-Language Models (VLMs) for embodied navigation rely on selecting a fixed number of frames from a growing trajectory history. As episodes extend, this selection grows increas…
SatReg: Regression-based Neural Architecture Search for Lightweight Satellite Image Segmentation
Edward Humes, Tinoosh Mohsenin
As Earth-observation workloads move toward onboard and edge processing, remote-sensing segmentation models must operate under tight latency and energy constraints. We present SatRe…
Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
Utkarsh Grover, Ravi Ranjan, Mingyang Mao +9
Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size,…
OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots
Boxun Hu, Chang Chang, Jiawei Ge +4
We naturally step sideways or lean to see around the obstacle when our view is blocked, and recover a more informative observation. Enabling robots to make the same kind of viewpoi…
Mil-SCORE: Benchmarking Long-Context Geospatial Reasoning and Planning in Large Language Models
Aadi Palnitkar, Mingyang Mao, Nicholas Waytowich +2
As large language models (LLMs) are applied to increasingly longer and more complex tasks, there is a growing need for realistic long-context benchmarks that require selective read…
EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices
Romina Aalishah, Mozhgan Navardi, Tinoosh Mohsenin
Deployment of efficient and accurate Deep Learning models has long been a challenge in autonomous navigation, particularly for real-time applications on resource-constrained edge d…
MedMambaLite: Hardware-Aware Mamba for Medical Image Classification
Romina Aalishah, Mozhgan Navardi, Tinoosh Mohsenin
AI-powered medical devices have driven the need for real-time, on-device inference such as biomedical image classification. Deployment of deep learning models at the edge is now us…
Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding
Mingyang Mao, Mariela M. Perez-Cabarcas, Utteja Kallakuri +3
To effectively engage in human society, the ability to adapt, filter information, and make informed decisions in ever-changing situations is critical. As robots and intelligent age…
EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deployment
Mikolaj Walczak, Romina Aalishah, Wyatt Mackey +5
Deep reinforcement learning agents are often fragile while humans remain adaptive and flexible to varying scenarios. To bridge this gap, we present EDEN, a biologically inspired na…
Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation
Uttej Kallakurik, Edward Humes, Rithvik Jonna +2
Large Language Models (LLMs) have significant impact on the healthcare scenarios but remain prohibitively large for deployment in real-time, resource-constrained environments such…
RAFT -- A Domain Adaptation Framework for RGB & LiDAR Semantic Segmentation
Edward Humes, Xiaomin Lin, Boxun Hu +2
Image segmentation is a powerful computer vision technique for scene understanding. However, real-world deployment is stymied by the need for high-quality, meticulously labeled dat…
ATLASv2: LLM-Guided Adaptive Landmark Acquisition and Navigation on the Edge
Mikolaj Walczak, Uttej Kallakuri, Tinoosh Mohsenin
Autonomous systems deployed on edge devices face significant challenges, including resource constraints, real-time processing demands, and adapting to dynamic environments. This wo…
GenAI at the Edge: Comprehensive Survey on Empowering Edge Devices
Mozhgan Navardi, Romina Aalishah, Yuzhe Fu +4
Generative Artificial Intelligence (GenAI) applies models and algorithms such as Large Language Model (LLM) and Foundation Model (FM) to generate new data. GenAI, as a promising ap…
MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation
Romina Aalishah, Mozhgan Navardi, Tinoosh Mohsenin
Generative Artificial Intelligence (AI) has gained significant attention in recent years, revolutionizing various applications across industries. Among these, advanced vision model…
Decentralised Resource Sharing in TinyML: Wireless Bilayer Gossip Parallel SGD for Collaborative Learning
Ziyuan Bao, Eiman Kanjo, Soumya Banerjee +2
With the growing computational capabilities of microcontroller units (MCUs), edge devices can now support machine learning models. However, deploying decentralised federated learni…
Energy-Aware FPGA Implementation of Spiking Neural Network with LIF Neurons
Asmer Hamid Ali, Mozhgan Navardi, Tinoosh Mohsenin
Tiny Machine Learning (TinyML) has become a growing field in on-device processing for Internet of Things (IoT) applications, capitalizing on AI algorithms that are optimized for th…
TinyMNet-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment
Hasib-Al Rashid, Tinoosh Mohsenin
The advancement of sophisticated artificial intelligence (AI) algorithms has led to a notable increase in energy usage and carbon dioxide emissions, intensifying concerns about cli…
TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices
Hasib-Al Rashid, Argho Sarkar, Aryya Gangopadhyay +2
Traditional machine learning models often require powerful hardware, making them unsuitable for deployment on resource-limited devices. Tiny Machine Learning (tinyML) has emerged a…
Squeezed Edge YOLO: Onboard Object Detection on Edge Devices
Edward Humes, Mozhgan Navardi, Tinoosh Mohsenin
Demand for efficient onboard object detection is increasing due to its key role in autonomous navigation. However, deploying object detection models such as YOLO on resource constr…
LLM Augmented Hierarchical Agents
Bharat Prakash, Tim Oates, Tinoosh Mohsenin
Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula r…