相关论文: MT-lib: A Topology-aware Message Transfer Library …
Sign Language Translation (SLT) converts sign language videos into spoken-language text, bridging communication between Deaf and hearing communities. Current gloss-free approaches rely on large encoder-decoder models, limiting deployment.…
Most compilers for machine learning (ML) frameworks need to solve many correlated optimization problems to generate efficient machine code. Current ML compilers rely on heuristics based algorithms to solve these optimization problems one at…
The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation performance on low…
In this paper, we propose a new Multiple-Input Multiple-Output (MIMO) Molecular Communication (MC) system where multiple types of molecules are utilized for transmission and reception of information. We call the proposed framework as…
We present a new open-source cosmological code, called SWIFT, designed to solve the equations of hydrodynamics using a particle-based approach (Smooth Particle Hydrodynamics) on hybrid shared/distributed-memory architectures. SWIFT was…
Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both…
The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…
In this paper, we propose a novel transmission scheme, called sparse layered MIMO (SL-MIMO), that combines non-orthogonal transmission and singular value decomposition (SVD) precoding. Nonorthogonality in SL-MIMO allows re-using of the…
Process malleability has proved to have a highly positive impact on the resource utilization and global productivity in data centers compared with the conventional static resource allocation policy. However, the non-negligible additional…
Massive machine type communication (mMTC) is one of the basic components of the future fifth generation (5G) wireless communication system. In mMTC, the information processing at the sensor nodes is required to be simple, low power…
Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…
Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc. The prototype editing approach, which is known to be quite successful in TST, involves two…
Message hiding, a technique that conceals secret message bits within a cover image, aims to achieve an optimal balance among message capacity, recovery accuracy, and imperceptibility. While convolutional neural networks have notably…
In cellular massive Machine-Type Communications (MTC), a device can transmit directly to the base station (BS) or through an aggregator (intermediate node). While direct device-BS communication has recently been in the focus of 5G/3GPP…
Deep learning has been used in a wide range of areas and made a huge breakthrough. With the ever-increasing model size and train-ing data volume, distributed deep learning emerges which utilizes a cluster to train a model in parallel.…
Unsupervised Multiplex Graph Learning (UMGL) aims to learn node representations on various edge types without manual labeling. However, existing research overlooks a key factor: the reliability of the graph structure. Real-world data often…
Collective communication is becoming increasingly important in data center and supercomputer workloads with an increase in distributed AI related jobs. However, existing libraries that provide collective support such as NCCL, RCCL, and…
The multi-link operation (MLO) is a new feature proposed to be part of the IEEE 802.11be Extremely High Throughput (EHT) amendment. Through MLO, access points and stations will be provided with the capabilities to transmit and receive data…
The Bulk Synchronous Parallel(BSP) computational model has emerged as the dominant distributed framework to build large-scale iterative graph processing systems. While its implementations(e.g., Pregel, Giraph, and Hama) achieve high…
Graph clustering is a central topic in unsupervised learning with a multitude of practical applications. In recent years, multi-view graph clustering has gained a lot of attention for its applicability to real-world instances where one has…