With the growing deployment of intelligent applications in the Internet of Vehicles (IoV), collaborative deep neural network (DNN) inference across edge nodes has become essential for satisfying real-time processing and service demands. As a key enabler for 6G networks, rate-splitting multiple access (RSMA) offers impr...
Zhi-Jian Lin, Shao-Wei Yang, Xiaopei Chen et al.· IEEE Transactions on Mobile...· 0 citations
Through bypassing the long-distance transmission of cloud services, Mobile Edge Computing (MEC) reduces response delay and ensures Quality-of-Service (QoS). In resource-constrained MEC, due to the strong coupling between service provisioning and task execution, reasonable service caching and resource allocation face ma...
Zhe-Yi Chen, Jia-Yun Zheng, Hong-Ju Cheng et al.· IEEE Transactions on Mobile...· 1 citation
With the development of UAV communications and aerial edge intelligence, Uncrewed Aerial Vehicles (UAVs) are increasingly used for inspection in high-risk environments. However, limited onboard energy and data-privacy constraints make efficient collaborative learning challenging. Hierarchical Federated Learning (HFL) p...
Tian-Le Xia, Hai-Tao Zhao, Miao Liu et al.· IEEE Transactions on Paralle...· 0 citations
Regarding the computational intensity and stringent latency requirements of modern applications comprised of many dependent subtasks, collaborative edge computing (CEC) emerges as a solution to guarantee the service-level objectives (SLOs) by offloading subtasks to multiple distributed edge servers. However, existing o...
Zi-Xuan He, Yan-Jing Sun, Zhen-Guo Ma et al.· IEEE Transactions on Mobile...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-tenant computing, which executes multiple neural networks on a single GPU, is essential for maximizing hardware utilization in both cloud and edge environments. However, effective co-location faces a fundamental trade-off between utilization and safety. On one hand, the diverse computing patterns of concurrent mo...
Yongbo Yu, Fuxun Yu, Jia-Qi Yang et al.· IEEE transactions on compute...· 0 citations
Nano-size-induced shifts in alloy phase-separation critical temperatures (TCnano) are investigated by introducing an atomistic concept of site-specific contributions to the shift (SSCS) associated with different atomic coordination environments in cuboctahedral and truncated-octahedral nanoparticles (NPs). TCnano previ...
A dynamic vertical scaling strategy based on Proximal Policy Optimization, formulated as a Partially Observable Markov Decision Process, which jointly adjusts task allocations and prioritizes compliance with a p95 end-to-end latency Service Level Objective is presented.
Guilherme Hiago Costa dos Santos, C. Kayser, Tiago Ferreto· 0 citations
The sCXR demonstrated image quality characteristics that were generally comparable to conventional chest radiography in several of the categories under investigation, highlighting the potential of sCXR as a companion image with the added flexibility of generating multiple projection views.
A. Shields, Kateland N. Howard, Shivapriya Somasundaram et al.· Academic Radiology· 0 citations
In this article, we compute the Hilbert series of the generalized binomial edge ideal associated with the join of two graphs. Consequently, we compute the Hilbert series of complete $r$-partite graphs. Further, we show that if a vertex satisfies a certain degree condition, then some Hilbert coefficients remain unchange...
This paper implements HeatCache atop vLLM and shows that it reduces computing energy by up to 18.0%, decreases thermal-throttle exposure by 81.7%, and maintains SLO violation rates below 0.9% even up to $48~^{\circ}\mathrm{C}$.
Rui Lu, Huanghuang Liang, Kai-Qi Guan et al.· 0 citations
NovaFabric is presented, producing audit-grade execution evidence: provider-neutral, tamper-evident, replayable, shareable and conditional on a stated trusted computing base.
The search for stable and lead-free perovskite materials has attracted considerable interest in next-generation optoelectronic and photovoltaic applications. This paper presents a detailed first-principles study of the structure, electronic, optical, and transport properties of formamidinium germanium trichloride (FAGe...
Md. Al-Amin, Hatem Taha, Farah Habib Pritu et al.· Next Materials· 0 citations
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 2, 2026
