Related papers: WildFit: Autonomous In-situ Model Adaptation for R…

Clock configuration takes a key role in tuning constrained general-purpose microcontrollers for performance, timing accuracy, and energy efficiency. Configuring the underlying clock tree, however, involves a large parameter space with…

In real-world Federated Learning (FL) deployments, data distributions on devices that participate in training evolve over time. This leads to asynchronous data drift, where different devices shift at different times and toward different…

To ensure reliability and service availability, next-generation networks are expected to rely on automated anomaly detection systems powered by advanced machine learning methods with the capability of handling multi-dimensional data. Such…

Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are…

Resource-constrained devices are increasingly the deployment targets of machine learning applications. Static models, however, do not always suffice for dynamic environments. On-device training of models allows for quick adaptability to new…

Internet of Things (IoT) is a pivotal technology in application domains that require connectivity and interoperability between large numbers of devices. IoT systems predominantly use a software-defined network (SDN) architecture as their…

In few-shot classification tasks (so-called episodes), a small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples. Metric-based models typically operate by computing similarities…

The Distributed Messaging Systems (DMSs) used in IoT systems require timely and reliable data dissemination, which can be achieved through configurable parameters. However, the high-dimensional configuration space makes it difficult for…

Over the past few years, the relevance of the Internet of Things (IoT) has grown significantly and is now a key component of many industrial processes and even a transparent participant in various activities performed in our daily life. IoT…

Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing…

Recent advances in training vision-language models have demonstrated unprecedented robustness and transfer learning effectiveness; however, standard computer vision datasets are image-only, and therefore not well adapted to such training…

The growing use of service robots in dynamic environments requires flexible management of on-board compute resources to optimize the performance of diverse tasks such as navigation, localization, and perception. Current robot deployments…

While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adopting context-awareness i.e. narrowing down a classification…

As deep neural networks continue to expand and become more complex, most edge devices are unable to handle their extensive processing requirements. Therefore, the concept of distributed inference is essential to distribute the neural…

Complex IoT ecosystems often require the usage of Digital Twins (DTs) of their physical assets in order to perform predictive analytics and simulate what-if scenarios. DTs are able to replicate IoT devices and adapt over time to their…

The increased maturity level of technological achievements towards the realization of the Internet of Things (IoT) vision allowed sophisticated solutions to emerge, offering reliable monitoring in highly dynamic environments that lack…

The ubiquitous adoption of Internet-of-Things (IoT) based applications has resulted in the emergence of the Fog computing paradigm, which allows seamlessly harnessing both mobile-edge and cloud resources. Efficient scheduling of application…

Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language and vision applications. In reinforcement learning, however, a key challenge is that available data of…

Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals, as users iterate toward better answers through refinements,…

As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate…