相关论文: Towards Low-Energy Adaptive Personalization for Re…

The majority of IoT devices like smartwatches, smart plugs, HVAC controllers, etc., are powered by hardware with a constrained specification (low memory, clock speed and processor) which is insufficient to accommodate and execute large,…

Energy efficiency has emerged as a defining constraint in the evolution of sustainable Internet of Things (IoT) networks. This work moves beyond simulation-based or device-centric studies to deliver measurement-driven, network-level smart…

The performance of deep learning models depends heavily on test samples at runtime, and shifts from the training data distribution can significantly reduce accuracy. Test-time adaptation (TTA) addresses this by adapting models during…

Detecting drifts in data is essential for machine learning applications, as changes in the statistics of processed data typically has a profound influence on the performance of trained models. Most of the available drift detection methods…

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. However, the learning accuracy decreases due to the heterogeneity of devices' data, and the computation and communication latency…

Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to new tasks with minimal loss in performance. Previous…

Deploying Transformer-based large language models (LLMs) on resource-constrained edge devices for long-sequence tasks remains challenging due to the quadratic time complexity of self-attention and growing Key-Value (KV) cache demands. While…

Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning…

Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication latency. However, the high computational and energy overhead…

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative machine learning while preserving data privacy, making it particularly suitable for Internet of Things (IoT) environments. However, resource-constrained…

The ability to perform computation on devices, such as smartphones, cars, or other nodes present at the Internet of Things leads to constraints regarding bandwidth, storage, and energy, as most of these devices are mobile and operate on…

Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter…

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

Tiny Machine Learning (TML) is a new research area whose goal is to design machine and deep learning techniques able to operate in Embedded Systems and IoT units, hence satisfying the severe technological constraints on memory, computation,…

Efficiently adapting large foundation models is critical, especially with tight compute and memory budgets. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA offer limited granularity and effectiveness in few-parameter regimes. We…

Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited by the scarcity of real-world fall data and the dominance of non-fall feedback…

The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy constraints to prolong battery-life, or may even operate…

Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use of on-policy data. We propose a framework to bridge this…