Related papers: Eliminating Hidden Serialization in Multi-Node Meg…

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is…

Complex electromagnetic interference increasingly compromises Global Navigation Satellite Systems (GNSS), threatening the reliability of Space-Air-Ground Integrated Networks (SAGIN). Although deep learning has advanced interference…

Pervasive encryption makes large-scale labeling infeasible for traffic analysis, while security operations demand edge analysis to avert service degradation and further vulnerabilities. These pressures have produced two disjoint research…

Using multiple nodes and parallel computing algorithms has become a principal tool to improve training and execution times of deep neural networks as well as effective collective intelligence in sensor networks. In this paper, we consider…

Fully Homomorphic Encryption (FHE) is one of the most promising technologies for privacy protection as it allows an arbitrary number of function computations over encrypted data. However, the computational cost of these FHE systems limits…

In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors.…

Computational grids typically consist of nodes utilizing ordinary processors such as the Intel Pentium. Field Programmable Gate Arrays (FPGAs) are able to perform certain compute-intensive tasks very well due to their inherent parallel…

Modern computer processors use microarchitectural optimization mechanisms to improve performance. As a downside, such optimizations are prone to introducing side-channel vulnerabilities. Speculative loading of memory, called prefetching, is…

We present new two-party protocols for the Unbalanced Private Set Union (UPSU) problem. Here, the Sender holds a set of data points, and the Receiver holds another (possibly much larger) set, and they would like for the Receiver to learn…

Sequential recommender systems have made significant progress. Recently, due to increasing concerns about user data privacy, some researchers have implemented federated learning for sequential recommendation, a.k.a., Federated Sequential…

Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE…

A graph neural network (GNN) approach is introduced in this work which enables mesh-based three-dimensional super-resolution of fluid flows. In this framework, the GNN is designed to operate not on the full mesh-based field at once, but on…

Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise in enhancing inference efficiency. However, we have…

Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative state. We re-frame…

We present Synkhronos, an extension to Theano for multi-GPU computations leveraging data parallelism. Our framework provides automated execution and synchronization across devices, allowing users to continue to write serial programs without…

Nowadays a wide range of applications is constrained by low-latency requirements that cloud infrastructures cannot meet. Multi-access Edge Computing (MEC) has been proposed as the reference architecture for executing applications closer to…

Encrypted traffic classification is a critical task for network security. While deep learning has advanced this field, the occlusion of payload semantics by encryption severely challenges standard modeling approaches. Most existing…

Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…

The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms…

The Mixture of Experts (MoE) selects a few feed-forward networks (FFNs) per token, achieving an effective trade-off between computational cost and performance. In conventional MoE, each expert is treated as entirely independent, and experts…