Related papers: OBASE: Object-Based Address-Space Engineering to I…

Future networks (including 6G) are poised to accelerate the realisation of Internet of Everything. However, it will result in a high demand for computing resources to support new services. Mobile Edge Computing (MEC) is a promising…

We present OrbitCache, a new in-network caching architecture that can cache variable-length items to balance a wide range of key-value workloads. Unlike existing works, OrbitCache does not cache hot items in the switch memory. Instead, we…

Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.We use a shared representation (mask proposals with class…

Code embeddings capture the semantic representations of code and are crucial for various code-related large language model (LLM) applications, such as code search. Previous training primarily relies on optimizing the InfoNCE loss by…

Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more…

Mobile-edge computing (MEC) is an emerging technology for enhancing the computational capabilities of mobile devices and reducing their energy consumption via offloading complex computation tasks to the nearby servers. Multiuser MEC at…

Modern workloads are demanding increasingly larger memory capacity. Compute Express Link (CXL)-based memory tiering has emerged as a promising solution for addressing this problem by utilizing traditional DRAM alongside slow-tier CXL memory…

Distributed Asynchronous Object Store (DAOS) is a novel software-defined object store leveraging Non-Volatile Memory (NVM) devices, designed for high performance. It provides a number of interfaces for applications to undertake I/O, ranging…

Work in the Open Archives Initiative - Object Reuse and Exchange (OAI-ORE) focuses on an important aspect of infrastructure for eScience: the specification of the data model and a suite of implementation standards to identify and describe…

Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis-small, critical, and easily lost in a desert…

The need for increased performance of mobile device directly conflicts with the desire for longer battery life. Offloading compu-tation to multiple devices is an effective method to reduce energy consumption and enhance performance for…

The counting task, which plays a fundamental role in numerous applications (e.g., crowd counting, traffic statistics), aims to predict the number of objects with various densities. Existing object counting tasks are designed for a single…

Humans have always been seeking greater control over their surrounding objects. Today, with the help of Internet of Things (IoT), we can fulfill this goal. In order for objects to be connected to the internet, they should have an address,…

Recent advances in deep learning have enabled complex real-world use cases comprised of multiple vision tasks and detection tasks are being shifted to the edge side as a pre-processing step of the entire workload. Since running a deep model…

Technological evolution of mobile user equipments (UEs), such as smartphones or laptops, goes hand-in-hand with evolution of new mobile applications. However, running computationally demanding applications at the UEs is constrained by…

The demand for stringent interactive quality-of-service has intensified in both mobile edge computing (MEC) and cloud systems, driven by the imperative to improve user experiences. As a result, the processing of computation-intensive tasks…

Mixture-of-Experts (MoE) layers activate a subset of model weights, dubbed experts, to improve model performance. MoE is particularly promising for deployment on process-in-memory (PIM) architectures, because PIM can naturally fit experts…

Bit-serial architectures can handle Neural Networks (NNs) with different weight precisions, achieving higher resource efficiency compared with bit-parallel architectures. Besides, the weights contain abundant zero bits owing to the fault…

Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications. Although recent research has proposed ways of quickly estimating…

Occupancy prediction tasks focus on the inference of both geometry and semantic labels for each voxel, which is an important perception mission. However, it is still a semantic segmentation task without distinguishing various instances.…