1 citations · 1 across the 6 of their papers we have counts for
7 papers
ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
Akshat Ramachandran, Marina Neseem, Charbel Sakr +3
The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (KV) cache, quickly overwhelming…
PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
Marina Neseem, Conor McCullough, Randy Hsin +8
Low-precision quantization is recognized for its efficacy in neural network optimization. Our analysis reveals that non-quantized elementwise operations which are prevalent in laye…
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
Ahmed Agiza, Marina Neseem, Sherief Reda
Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods ha…
AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning
Marina Neseem, Ahmed Agiza, Sherief Reda
Modern Augmented reality applications require performing multiple tasks on each input frame simultaneously. Multi-task learning (MTL) represents an effective approach where multipl…
BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge
Abdelrahman Hosny, Marina Neseem, Sherief Reda
Training on the Edge enables neural networks to learn continuously from new data after deployment on memory-constrained edge devices. Previous work is mostly concerned with reducin…
AdaCon: Adaptive Context-Aware Object Detection for Resource-Constrained Embedded Devices
Marina Neseem, Sherief Reda
Convolutional Neural Networks achieve state-of-the-art accuracy in object detection tasks. However, they have large computational and energy requirements that challenge their deplo…
AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices
Marina Neseem, Jon Nelson, Sherief Reda
Wearable devices have strict power and memory limitations. As a result, there is a need to optimize the power consumption on those devices without sacrificing the accuracy. This pa…