相关论文: Backpropagation-Free Multi-modal On-Device Model A…

Various deep learning models have been developed to segment anatomical structures from medical images, but they typically have poor performance when tested on another target domain with different data distribution. Recently, unsupervised…

Cloud-enabled large-scale distributed systems orchestrate resources and services from various providers in order to deliver high-quality software solutions to the end users. The space and structure created by such technological advancements…

As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed, traditional fine-tuning methods are costly, due to the need…

Context: Mobile devices have become an essential element in our daily lives, even for connecting to the Internet. Consequently, Web services have become extremely important when offering services through the Internet. However, current Web…

ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to track their accuracy, which can degrade unpredictably (e.g.,…

Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different…

In always-on HAR deployments, model accuracy erodes silently as domain shift accumulates over time. Addressing this challenge requires moving beyond one-off updates toward instance-driven adaptation from streaming data. However, continuous…

Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD…

Carrier Frequency Offset (CFO) estimation in Orthogonal Frequency Division Multiplexing (OFDM) systems faces significant performance degradation across heterogeneous software-defined radio (SDR) platforms due to uncalibrated hardware…

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapting models from a label-rich source domain to unlabeled target domains. Despite these advancements, there is a lack of research on how uDA algorithms, particularly those…

Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and…

Large Vision-Language Models typically require large text and image datasets for effective fine-tuning. However, collecting data from various sites, especially in healthcare, is challenging due to strict privacy regulations. An alternative…

Modern mobile applications are benefiting significantly from the advancement in deep learning, e.g., implementing real-time image recognition and conversational system. Given a trained deep learning model, applications usually need to…

In the realm of real-world devices, centralized servers in Federated Learning (FL) present challenges including communication bottlenecks and susceptibility to a single point of failure. Additionally, contemporary devices inherently exhibit…

Recently, foundation models, particularly large language models (LLMs), have demonstrated an impressive ability to adapt to various tasks by fine-tuning diverse instruction data. Notably, federated foundation models (FedFM) emerge as a…

Cross-device federated learning (FL) is a technique that trains a model on data distributed across typically millions of edge devices without data leaving the devices. SGD is the standard client optimizer for on device training in…

Source-free domain adaptation (SFDA) alleviates the domain discrepancy among data obtained from domains without accessing the data for the awareness of data privacy. However, existing conventional SFDA methods face inherent limitations in…

The development and operation of smart cities relyheavily on large-scale Internet-of-Things (IoT) networks and sensor infrastructures that continuously monitor various aspects of urban environments. These networks generate vast amounts of…

Effectively integrating molecular graph structures with Large Language Models (LLMs) is a key challenge in drug discovery. Most existing multi-modal alignment methods typically process these structures by fine-tuning the LLM or adding a…

In the big data era, the computer vision field benefits from large-scale datasets such as LAION-2B, LAION-400M, and ImageNet-21K, Kinetics, on which popular models like the ViT and ConvNeXt series have been pre-trained, acquiring…