Related papers: Cloud-Device Collaborative Adaptation to Continual…

Knowledge Tracing (KT) is a core component of Intelligent Tutoring Systems, modeling learners' knowledge state to predict future performance and provide personalized learning support. Traditional KT models assume that learners' learning…

Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained models with multi-task abilities, we observe that conventional…

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

Cloud computing promises a radical shift in the provisioning of computing resource within the enterprise. This paper describes the challenges that decision makers face when assessing the feasibility of the adoption of cloud computing in…

Visual detection of Unmanned Aerial Vehicles (UAVs) is a critical task in surveillance systems due to their small physical size and environmental challenges. Although deep learning models have achieved significant progress, deploying them…

Sequential recommendation effectively models dynamic user interests but continues to face challenges related to data sparsity. While self-supervised learning has alleviated this issue to some extent, most existing methods focus exclusively…

Computer Vision (CV) systems are increasingly being adopted into Command and Control (C2) systems to improve intelligence analysis on the battlefield, the tactical edge. CV systems leverage Artificial Intelligence (AI) algorithms to help…

Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data samples, deploying the pre-trained model on IoT devices, and…

One of the greatest sources of uncertainty in future climate projections comes from limitations in modelling clouds and in understanding how different cloud types interact with the climate system. A key first step in reducing this…

This paper addresses the challenges of complex dependencies and diverse anomaly patterns in cloud service environments by proposing a dependency modeling and anomaly detection method that integrates contrastive learning. The method…

It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test…

Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to…

Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications. It aims to improve the generalization ability of pre-trained models when deployed on resource-constrained…

Vision-Language Models (VLMs) are increasingly deployed in real-time applications such as autonomous driving and human-computer interaction, which demand fast and reliable responses based on accurate perception. To meet these requirements,…

AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is…

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Few-shot point cloud segmentation seeks to generate per-point masks for previously unseen categories, using only a minimal set of annotated point clouds as reference. Existing prototype-based methods rely on support prototypes to guide the…

Cloud computing is an emerging platform of service computing designed for swift and dynamic delivery of assured computing resources. Cloud computing provide Service-Level Agreements (SLAs) for guaranteed uptime availability for enabling…

Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing methods predominantly follow a backward-alignment paradigm, which rigidly aligns incoming…

Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems. Deep learning is widely adopted for UAV object detection whereas researches on this topic are limited by the amount of dataset and small…