Related papers: MT-lib: A Topology-aware Message Transfer Library …
Recent advances in large language models have led to specialized models excelling in specific domains, creating a need for efficient model merging techniques. While traditional merging approaches combine parameters into a single static…
Cloud applications need network data encryption to isolate from other tenants and protect their data from potential eavesdroppers in the network infrastructure. This paper presents SMT, a protocol design for emerging datacenter transport…
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…
Demands for data traffic in high-speed railway (HSR) has increased drastically. The increasing entertainment needs of passengers, safety control information exchanges of trains, etc., make train-to-train (T2T) communications face the…
Software transactional memory (STM) allows programmers to easily implement concurrent data structures. STMs simplify atomicity. Recent STMs can achieve good performance for some workloads but they have some limitations. In particular, STMs…
Recent works in end-to-end speech-to-text translation (ST) have proposed multi-tasking methods with soft parameter sharing which leverage machine translation (MT) data via secondary encoders that map text inputs to an eventual cross-modal…
In this paper we present and evaluate a parallel algorithm for solving a minimum spanning tree (MST) problem for supercomputers with distributed memory. The algorithm relies on the relaxation of the message processing order requirement for…
Multi-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each image, may greatly reduce the cost of annotation and thus facilitate large-scale MLR. We find that strong semantic…
The Mapbox Vector Tile (MVT) format is widely considered the leading open standard for large-scale map visualization, as evidenced by its widespread adoption by major technology companies such as AWS, Meta, and Microsoft for their products…
In recent studies, neural message passing has proved to be an effective way to design graph neural networks (GNNs), which have achieved state-of-the-art performance in many graph-based tasks. However, current neural-message passing…
Language style transfer has attracted more and more attention in the past few years. Recent researches focus on improving neural models targeting at transferring from one style to the other with labeled data. However, transferring across…
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this…
In this paper, we investigate the impact of cooperation between a secondary transmitter-receiver pair and a primary transmitter (PT) on the maximum stable throughput of the primary-secondary network. Each transmitter, primary or secondary,…
Memory-(in)efficiency is a crucial consideration that oftentimes prevents deployment of state-of-the-art distributed algorithms in real-life modern networks. In the context of the MST problem, roughly speaking, there are three types of…
Recent neural style transfer frameworks have obtained astonishing visual quality and flexibility in Single-style Transfer (SST), but little attention has been paid to Multi-style Transfer (MST) which refers to simultaneously transferring…
Semantic communications have been utilized to execute numerous intelligent tasks by transmitting task-related semantic information instead of bits. In this article, we propose a semantic-aware speech-to-text transmission system for the…
Text-to-image synthesis has witnessed remarkable advancements in recent years. Many attempts have been made to adopt text-to-image models to support multiple tasks. However, existing approaches typically require resource-intensive…
Recently, Transformer-based methods have achieved impressive results in single image super-resolution (SISR). However, the lack of locality mechanism and high complexity limit their application in the field of super-resolution (SR). To…
The classical-quantum system heterogeneity (different data characteristics, execution paradigms and synchronization mechanism etc.) renders existing distributed communication mechanisms (e.g. MPI, NCCL etc.) inadequate. This bottleneck…
Multi-Task Learning (MTL) is a powerful technique that has gained popularity due to its performance improvement over traditional Single-Task Learning (STL). However, MTL is often challenging because there is an exponential number of…