Search Results for author:
Found 17 papers, 7 papers with code
Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in LLMs
In an era where language models are increasingly integrated into decision-making and communication, understanding the biases within Large Language Models (LLMs) becomes imperative, especially when these models are applied in the economic and political domains.
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning.
torchmSAT: A GPU-Accelerated Approximation To The Maximum Satisfiability Problem
Then, we present a novel neural network architecture to model our differentiable function, and progressively solve MaxSAT using backpropagation.
Microscale 3-D Capacitance Tomography with a CMOS Sensor Array
Electrical capacitance tomography (ECT) is a nonoptical imaging technique in which a map of the interior permittivity of a volume is estimated by making capacitance measurements at its boundary and solving an inverse problem.
GraPhSyM: Graph Physical Synthesis Model
Given a gate-level netlist of a circuit represented as a graph, GraPhSyM utilizes graph structure, connectivity, and electrical property features to predict the impact of physical synthesis transformations such as buffer insertion and gate sizing.
Automatic MILP Solver Configuration By Learning Problem Similarities
We show that instances that have similar costs using one solver configuration also have similar costs using another solver configuration in the same runtime environment.
AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning
Specifically, we attach a task-aware lightweight policy network to the shared encoder and co-train it alongside the MTL model to recognize unnecessary computations.
BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge
However, memory footprint from activations is the main bottleneck for training on the edge.
AdaCon: Adaptive Context-Aware Object Detection for Resource-Constrained Embedded Devices
In particular, our technique clusters the object categories based on their spatial co-occurrence probability.
Characterizing and Optimizing EDA Flows for the Cloud
However, deploying EDA jobs on the cloud requires EDA teams to deeply understand the characteristics of their jobs in cloud environments.
AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices
The proposed techniques reduce the power consumption by dynamically switching among different sensor configurations as a function of the user activity.
DRiLLS: Deep Reinforcement Learning for Logic Synthesis
Logic synthesis requires extensive tuning of the synthesis optimization flow where the quality of results (QoR) depends on the sequence of optimizations used.
A Resource-Efficient Embedded Iris Recognition System Using Fully Convolutional Networks
To attain accurate and efficient FCN models, we propose a three-step SW/HW co-design methodology consisting of FCN architectural exploration, precision quantization, and hardware acceleration.
Flexible Deep Neural Network Processing
In addition, DNNs are typically deployed in ensemble to boost accuracy performance, which further exacerbates the system requirements.
Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks
In addition, we propose a hardware accelerator design to achieve low-power, low-latency inference with insignificant degradation in accuracy.
Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks
While a large number of dedicated hardware using different precisions has recently been proposed, there exists no comprehensive study of different bit precisions and arithmetic in both inputs and network parameters.
Runtime Configurable Deep Neural Networks for Energy-Accuracy Trade-off
We present a novel dynamic configuration technique for deep neural networks that permits step-wise energy-accuracy trade-offs during runtime.
