Related papers: Drift-Adapter: A Practical Approach to Near Zero-D…

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of…

This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algorithms simplify networks based on the number of MACs or…

The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained…

The Transformer architecture is widely used for machine translation tasks. However, its resource-intensive nature makes it challenging to implement on constrained embedded devices, particularly where available hardware resources can vary at…

Fine-tuning a language model on a new domain is standard practice for domain adaptation. However, it can be infeasible when it comes to modern large-scale language models such as GPT-3, which can only be accessed through APIs, making it…

We seek to enable classic processing of continuous ultra-sparse spatiotemporal data generated by event-based sensors with dense machine learning models. We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous…

A permanently increasing number of on-board automotive control systems requires new approaches to their digital mapping that improves functionality in terms of adaptability and robustness as well as enables their easier on-line software…

The demand for high speed data transmission has increased rapidly, leading to advanced optical communication techniques. In the past few years, multiple equalizers based on neural network (NN) have been proposed to recover signal from…

While current Vision Transformer (ViT) adapter methods have shown promising accuracy, their inference speed is implicitly hindered by inefficient memory access operations, e.g., standard normalization and frequent reshaping. In this work,…

Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with…

Multi-Domain Learning (MDL) refers to the problem of learning a set of models derived from a common deep architecture, each one specialized to perform a task in a certain domain (e.g., photos, sketches, paintings). This paper tackles MDL…

Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…

Cross-subject brain-to-visual decoding remains a core challenge in brain-computer interfaces due to severe inter-individual variability that induces systematic subject-specific functional misalignment. To address this issue, we propose…

When deep learning models are sequentially trained on new data, they tend to abruptly lose performance on previously learned tasks, a critical failure known as catastrophic forgetting. This challenge severely limits the deployment of AI in…

Complete depth information and efficient estimators have become vital ingredients in scene understanding for automated driving tasks. A major problem for LiDAR-based depth completion is the inefficient utilization of convolutions due to the…

Nonlinear model predictive control (NMPC) requires accurate and computationally efficient plant models. Our previous work has shown that the classical compartmentalization model reduction approach for distillation columns can be enhanced by…

Accurate road surface classification is crucial for autonomous vehicles (AVs) to optimize driving conditions, enhance safety, and enable advanced road mapping. However, deep learning models for road surface classification suffer from poor…

It has been well established that increasing scale in deep transformer networks leads to improved quality and performance. However, this increase in scale often comes with prohibitive increases in compute cost and inference latency. We…

Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by training small…

Sensor drift is a long-existing unpredictable problem that deteriorates the performance of gaseous substance recognition, calling for an antidrift domain adaptation algorithm. However, the prerequisite for traditional methods to achieve…