88 citations · 119 across the 13 of their papers we have counts for
14 papers
Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection
Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda
Parameter Efficient Fine-Tuning (PEFT) has become the de-facto approach in adapting Large Language Models (LLMs) for downstream tasks in Natural Language Processing. However, its a…
Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits
Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda
Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive c…
Intelligent Sensing-to-Action for Robust Autonomy at the Edge: Opportunities and Challenges
Amit Ranjan Trivedi, Sina Tayebati, Hemant Kumawat +9
Autonomous edge computing in robotics, smart cities, and autonomous vehicles relies on the seamless integration of sensing, processing, and actuation for real-time decision-making…
Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing
Abhiroop Bhattacharjee, Abhishek Moitra, Youngeun Kim +2
In-Memory Computing (IMC) platforms such as analog crossbars are gaining focus as they facilitate the acceleration of low-precision Deep Neural Networks (DNNs) with high area- & co…
Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems
Yeshwanth Venkatesha, Youngeun Kim, Hyoungseob Park +1
Federated Learning (FL) is a privacy-preserving distributed machine learning approach geared towards applications in edge devices. However, the problem of designing custom neural a…
Exploring Temporal Information Dynamics in Spiking Neural Networks
Youngeun Kim, Yuhang Li, Hyoungseob Park +3
Most existing Spiking Neural Network (SNN) works state that SNNs may utilize temporal information dynamics of spikes. However, an explicit analysis of temporal information dynamics…
Exploring Lottery Ticket Hypothesis in Spiking Neural Networks
Youngeun Kim, Yuhang Li, Hyoungseob Park +3
Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks, which is suitable to be implemented on low-power mobile/edge devices. As…
MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning
Abhiroop Bhattacharjee, Yeshwanth Venkatesha, Abhishek Moitra +1
Recent years have seen a paradigm shift towards multi-task learning. This calls for memory and energy-efficient solutions for inference in a multi-task scenario. We propose an algo…
Addressing Client Drift in Federated Continual Learning with Adaptive Optimization
Yeshwanth Venkatesha, Youngeun Kim, Hyoungseob Park +2
Federated learning has been extensively studied and is the prevalent method for privacy-preserving distributed learning in edge devices. Correspondingly, continual learning is an e…
Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?
Youngeun Kim, Hyoungseob Park, Abhishek Moitra +3
Recent Spiking Neural Networks (SNNs) works focus on an image classification task, therefore various coding techniques have been proposed to convert an image into temporal binary s…
Neural Architecture Search for Spiking Neural Networks
Youngeun Kim, Yuhang Li, Hyoungseob Park +2
Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-s…
Federated Learning with Spiking Neural Networks
Yeshwanth Venkatesha, Youngeun Kim, Leandros Tassiulas +1
As neural networks get widespread adoption in resource-constrained embedded devices, there is a growing need for low-power neural systems. Spiking Neural Networks (SNNs)are emergin…
PrivateSNN: Privacy-Preserving Spiking Neural Networks
Youngeun Kim, Yeshwanth Venkatesha, Priyadarshini Panda
How can we bring both privacy and energy-efficiency to a neural system? In this paper, we propose PrivateSNN, which aims to build low-power Spiking Neural Networks (SNNs) from a pr…
Activation Density based Mixed-Precision Quantization for Energy Efficient Neural Networks
Karina Vasquez, Yeshwanth Venkatesha, Abhiroop Bhattacharjee +2
As neural networks gain widespread adoption in embedded devices, there is a need for model compression techniques to facilitate deployment in resource-constrained environments. Qua…