Related papers: A Deep-Learning-Aided Pipeline for Efficient Post-…

Accurate hardware performance models are critical to efficient code generation. They can be used by compilers to make heuristic decisions, by superoptimizers as a minimization objective, or by autotuners to find an optimal configuration for…

In recent years, power line maintenance has seen a paradigm shift by moving towards computer vision-powered automated inspection. The utilization of an extensive collection of videos and images has become essential for maintaining the…

For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them. However, tuning these hyperparameters can come at a high computational cost, especially on larger datasets,…

As with any quantum computing platform, semiconductor quantum dot devices require sophisticated hardware and controls for operation. The increasing complexity of quantum dot devices necessitates the advancement of automated control software…

Pruning is a widely used method for compressing Deep Neural Networks (DNNs), where less relevant parameters are removed from a DNN model to reduce its size. However, removing parameters reduces model accuracy, so pruning is typically…

In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and…

Deep learning compiler frameworks are gaining ground as a more portable back-end for deep learning applications on increasingly diverse hardware. However, they face the daunting challenge of matching performance offered by hand-tuned…

GPUs have been favored for training deep learning models due to their highly parallelized architecture. As a result, most studies on training optimization focus on GPUs. There is often a trade-off, however, between cost and efficiency when…

Pre-trained models have been shown effective in many code intelligence tasks. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks…

For certain industrial control applications an explicit function capturing the nontrivial trade-off between competing objectives in closed loop performance is not available. In such scenarios it is common practice to use the human innate…

Complex image processing and computer vision systems often consist of a processing pipeline of functional modules. We intend to replace parts or all of a target pipeline with deep neural networks to achieve benefits such as increased…

Atomic scale characterization and manipulation with scanning probe microscopy rely upon the use of an atomically sharp probe. Here we present automated methods based on machine learning to automatically detect and recondition the quality of…

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that…

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is…

Optimizing the performance of computational fluid dynamics (CFD) applications accelerated by graphics processing units (GPUs) is crucial for efficient simulations. In this study, we employed a machine learning-based autotuning technique to…

Automotive manufacturing assembly tasks are built upon visual inspections such as scratch identification on machined surfaces, part identification and selection, etc, which guarantee product and process quality. These tasks can be related…

In glass bottle manufacturing, precise control of forming machines is critical for ensuring quality and minimizing defects. This study presents a deep learning-based control algorithm designed to optimize the forming process in real…

As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the…

Modern radio telescopes produce unprecedented amounts of data, which are passed through many processing pipelines before the delivery of scientific results. Hyperparameters of these pipelines need to be tuned by hand to produce optimal…

At submicron manufacturing technology nodes, pro- cess variations affect circuit performance significantly. To counter these variations, engineers are reserving more timing margin to maintain yield, leading to an unaffordable overdesign.…