34 citations · 113 across the 17 of their papers we have counts for
18 papers
Carbon-Aware Routing for Function Calling in Edge-Cloud LLM Systems
Aikaterini Maria Panteleaki, Varatheepan Paramanayakam, Spyros Tragoudas +1
Large Language Models (LLMs) with function-calling capabilities are becoming critical for modern agentic AI systems. Nevertheless, current deployments typically route inferences to…
A Vertical Approach to Designing and Managing Sustainable Heterogeneous Edge Data Centers
Aikaterini Maria Panteleaki, Varatheepan Paramanayakam, Vasileios Pentsos +3
The increasing demand for Artificial Intelligence (AI) computing poses significant environmental challenges, with both operational and embodied carbon emissions becoming major cont…
Carbon-Efficient 3D DNN Acceleration: Optimizing Performance and Sustainability
Aikaterini Maria Panteleaki, Konstantinos Balaskas, Georgios Zervakis +2
As Deep Neural Networks (DNNs) continue to drive advancements in artificial intelligence, the design of hardware accelerators faces growing concerns over embodied carbon footprint…
Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning
Syed Mhamudul Hasan, Hussein Zangoti, Iraklis Anagnostopoulos +1
Recent studies have shown that sponge attacks can significantly increase the energy consumption and inference latency of deep neural networks (DNNs). However, prior work has focuse…
CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices
Varatheepan Paramanayakam, Andreas Karatzas, Iraklis Anagnostopoulos +1
Large Language Models (LLMs) enable real-time function calling in edge AI systems but introduce significant computational overhead, leading to high power consumption and carbon emi…
Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers
Varatheepan Paramanayakam, Andreas Karatzas, Dimitrios Stamoulis +1
Edge computing systems struggle to efficiently manage multiple concurrent deep neural network (DNN) workloads while meeting strict latency requirements, minimizing power consumptio…
Late Breaking Results: Leveraging Approximate Computing for Carbon-Aware DNN Accelerators
Aikaterini Maria Panteleaki, Konstantinos Balaskas, Georgios Zervakis +2
The rapid growth of Machine Learning (ML) has increased demand for DNN hardware accelerators, but their embodied carbon footprint poses significant environmental challenges. This p…
Multi-Agent Geospatial Copilots for Remote Sensing Workflows
Chaehong Lee, Varatheepan Paramanayakam, Andreas Karatzas +7
We present GeoLLM-Squad, a geospatial Copilot that introduces the novel multi-agent paradigm to remote sensing (RS) workflows. Unlike existing single-agent approaches that rely on…
Leveraging Highly Approximated Multipliers in DNN Inference
Georgios Zervakis, Fabio Frustaci, Ourania Spantidi +3
In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our ap…
RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices
Andreas Karatzas, Dimitrios Stamoulis, Iraklis Anagnostopoulos
Modern edge data centers simultaneously handle multiple Deep Neural Networks (DNNs), leading to significant challenges in workload management. Thus, current management systems must…
LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching
Simranjit Singh, Michael Fore, Andreas Karatzas +6
As Large Language Models (LLMs) broaden their capabilities to manage thousands of API calls, they are confronted with complex data operations across vast datasets with significant…
An LLM-Tool Compiler for Fused Parallel Function Calling
Simranjit Singh, Andreas Karatzas, Michael Fore +2
State-of-the-art sequential reasoning in Large Language Models (LLMs) has expanded the capabilities of Copilots beyond conversational tasks to complex function calling, managing th…
Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization
Konstantinos Balaskas, Andreas Karatzas, Christos Sad +4
Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential…
OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload
Andreas Karatzas, Iraklis Anagnostopoulos
Modern Deep Neural Networks (DNNs) exhibit profound efficiency and accuracy properties. This has introduced application workloads that comprise of multiple DNN applications, raisin…
Energy-efficient DNN Inference on Approximate Accelerators Through Formal Property Exploration
Ourania Spantidi, Georgios Zervakis, Iraklis Anagnostopoulos +1
Deep Neural Networks (DNNs) are being heavily utilized in modern applications and are putting energy-constraint devices to the test. To bypass high energy consumption issues, appro…
Positive/Negative Approximate Multipliers for DNN Accelerators
Ourania Spantidi, Georgios Zervakis, Iraklis Anagnostopoulos +2
Recent Deep Neural Networks (DNNs) managed to deliver superhuman accuracy levels on many AI tasks. Several applications rely more and more on DNNs to deliver sophisticated services…
Reliability-Aware Quantization for Anti-Aging NPUs
Sami Salamin, Georgios Zervakis, Ourania Spantidi +3
Transistor aging is one of the major concerns that challenges designers in advanced technologies. It profoundly degrades the reliability of circuits during its lifetime as it slows…
Control Variate Approximation for DNN Accelerators
Georgios Zervakis, Ourania Spantidi, Iraklis Anagnostopoulos +2
In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is used in Mont…