Cloud GPU tenants receive a model name and a region, but cannot directly inspect the physical accelerator that runs their job. We present a software-only attestation primitive for this setting. A CUDA probe measures an SM-by-memory-region latency matrix using physical SM labels and dependent global loads. A streaming reducer commits sufficient statistics, configuration, code hashes, network evidence, and a compressed raw data archive into a certificate that a verifier can check without a GPU. The certificate supports three claims. First, the per-SM latency map is a stable physical fingerprint. Over a six-hour full-load RTX 5090 run, its median temporal jitter is 0.09 cycles, while shape-only leave-one-out classification separates distinct Blackwell dies with 100.0% accuracy. Second, cache-bypassing HBM sweeps recover hardware-class topology across generations, including a unified Volta V100 memory domain, a two-way Hopper H200 L2 split, and a Blackwell B200 two-die NV-HBI package whose 74/74 SM partition carries a 30-cycle, 15.5 ns cross-die penalty. Third, public network landmarks bind the same certificate to a coarse location. In the B200 run, 169 RIPE Atlas probes place the serv
Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context switching violates the single-program-multiple-data (SPMD) assumption underlying today's distributed training systems. We present Echo, the RL system that cleanly decouples these two phases across heterogeneous "inference" and "training" swarms while preserving statistical efficiency. Echo introduces two lightweight synchronization protocols: a sequential pull mode that refreshes policy weights according to API call for minimal bias, and an asynchronous push-pull mode that streams version-tagged rollouts through a replay buffer to maximise hardware utilisation. Training four representative RL workloads with Qwen3-4B, Qwen2.5-7B, Qwen3-30B-A3B-Thinking-2507 and Qwen3-32B on a geographically distributed cluster, Echo matches a fully co-located Verl baseline in convergence speed and final reward while off-loading trajectory generation to commodity edge hardware. These promising results demonstrate that large-scale RL for LLMs could achieve datacentre-grade
We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are characterized by low memory availability and slow communication compared to datacentre-grade GPUs. Consequently, we showcase a range of optimizations that target these bottlenecks, including activation checkpointing, offloading, and copy-engine based collectives. LLMQ is able to train or fine-tune a 7B model on a single 16GB mid-range gaming card, or a 32B model on a workstation equipped with 4 RTX 4090s. This is achieved while executing a standard 8-bit training pipeline, without additional algorithmic approximations, and maintaining FLOP utilization of around 50%. The efficiency of LLMQ rivals that of production-scale systems on much more expensive cloud-grade GPUs.
The exploration of Graph Neural Networks (GNNs) for processing graph-structured data has expanded, particularly their potential for causal analysis due to their universal approximation capabilities. Anticipated to significantly enhance common graph-based tasks such as classification and prediction, the development of a causally enhanced GNN framework is yet to be thoroughly investigated. Addressing this shortfall, our study delves into nine benchmark graph classification models, testing their strength and versatility across seven datasets spanning three varied domains to discern the impact of causality on the predictive prowess of GNNs. This research offers a detailed assessment of these models, shedding light on their efficiency, and flexibility in different data environments, and highlighting areas needing advancement. Our findings are instrumental in furthering the understanding and practical application of GNNs in diverse datacentric fields
The recent progression of Large Language Models (LLMs) has witnessed great success in the fields of data-centric applications. LLMs trained on massive textual datasets showed ability to encode not only context but also ability to provide powerful comprehension to downstream tasks. Interestingly, Generative Pre-trained Transformers utilised this ability to bring AI a step closer to human being replacement in at least datacentric applications. Such power can be leveraged to identify anomalies of cyber threats, enhance incident response, and automate routine security operations. We provide an overview for the recent activities of LLMs in cyber defence sections, as well as categorization for the cyber defence sections such as threat intelligence, vulnerability assessment, network security, privacy preserving, awareness and training, automation, and ethical guidelines. Fundamental concepts of the progression of LLMs from Transformers, Pre-trained Transformers, and GPT is presented. Next, the recent works of each section is surveyed with the related strengths and weaknesses. A special section about the challenges and directions of LLMs in cyber security is provided. Finally, possible fut
In this work, we describe our approach to compete in the autoPET3 datacentric track. While conventional wisdom suggests that larger datasets lead to better model performance, recent studies indicate that excluding certain training samples can enhance model accuracy. We find that in the autoPETIII dataset, a model that is trained on the entire dataset exhibits undesirable characteristics by producing a large number of false positives particularly for PSMA-PETs. We counteract this by removing the easiest samples from the training dataset as measured by the model loss before retraining from scratch. Using the proposed approach we manage to drive down the false negative volume and improve upon the baseline model in both false negative volume and dice score on the preliminary test set. Code and pre-trained models are available at github.com/alexanderjaus/autopet3_datadiet.
The Ghana Cashew Disease Identification with Artificial Intelligence (CADI AI) project demonstrates the importance of sound data work as a precondition for the delivery of useful, localized datacentric solutions for public good tasks such as agricultural productivity and food security. Drone collected data and machine learning are utilized to determine crop stressors. Data, model and the final app are developed jointly and made available to local farmers via a desktop application.
Shared software datapaths underpin modern datacentre networking. They implement mechanisms such as virtual switching, network virtualisation tunneling, or reliable transport, and enforce policies, such as tenant rate limits, virtual network isolation, or congestion control. However, because multiple applications, containers, or VMs share them, often across tenants, they pose a tail latency isolation challenge. Current isolation approaches either sacrifice efficiency via coarse-grained core partitioning or provide weak tail latency isolation when sharing cores with basic rate limits. This paper presents Virtuoso, a time protection mechanism for shared software datapaths that provides strong cross-tenant tail latency isolation while preserving low overhead and microsecond-scale latency. Our key insight is that tail latency is fundamentally a time metric, so byte or packet throughput is the wrong metric for controlling interference when packet processing costs vary. Our design instead enforces isolation through per-tenant CPU-time budgets at datapath intervention points within run-to-completion loops, without relying on preemption. In a case study, we instantiate Virtuoso in the TAS T
Photonic integrated circuits utilize planar waveguides to process light on a chip, encompassing functions like generation, routing, modulation, and detection. Similar to the advancements in the electronics industry, photonics research is steadily transferring an expanding repertoire of functionalities onto integrated platforms. The combination of best-in-class materials at the wafer-level increases versatility and performance, suitable for large-scale markets, such as datacentre interconnects, lidar for autonomous driving or consumer health. These applications require mature integration platforms to sustain the production of millions of devices per year and provide efficient solutions in terms of power consumption and wavelength multiplicity for scalability. Chip-scale frequency combs offer massive wavelength parallelization, holding a transformative potential in photonic system integration, but efficient solutions have only been reported at the die level. Here, we demonstrate a silicon nitride technology on a 100 mm wafer that aids the performance requirements of soliton microcombs in terms of yield, spectral stability, and power efficiency. Soliton microcombs are reported with an
In recent years, the number of Internet of Things (IoT) devices/sensors has increased to a great extent. To support the computational demand of real-time latency-sensitive applications of largely geo-distributed IoT devices/sensors, a new computing paradigm named "Fog computing" has been introduced. Generally, Fog computing resides closer to the IoT devices/sensors and extends the Cloud-based computing, storage and networking facilities. In this chapter, we comprehensively analyse the challenges in Fogs acting as an intermediate layer between IoT devices/ sensors and Cloud datacentres and review the current developments in this field. We present a taxonomy of Fog computing according to the identified challenges and its key features.We also map the existing works to the taxonomy in order to identify current research gaps in the area of Fog computing. Moreover, based on the observations, we propose future directions for research.
Internet of Things (IoT) has already proven to be the building block for next-generation Cyber-Physical Systems (CPSs). The considerable amount of data generated by the IoT devices needs latency-sensitive processing, which is not feasible by deploying the respective applications in remote Cloud datacentres. Edge/Fog computing, a promising extension of Cloud at the IoT-proximate network, can meet such requirements for smart CPSs. However, the structural and operational differences of Edge/Fog infrastructure resist employing Cloud-based service regulations directly to these environments. As a result, many research works have been recently conducted, focusing on efficient application and resource management in Edge/Fog computing environments. Scalable Edge/Fog infrastructure is a must to validate these policies, which is also challenging to accommodate in the real-world due to high cost and implementation time. Considering simulation as a key to this constraint, various software has been developed that can imitate the physical behaviour of Edge/Fog computing environments. Nevertheless, the existing simulators often fail to support advanced service management features because of their
COVID-19 has spread rapidly across the globe and become a deadly pandemic. Recently, many artificial intelligence-based approaches have been used for COVID-19 detection, but they often require public data sharing with cloud datacentres and thus remain privacy concerns. This paper proposes a new federated learning scheme, called FedGAN, to generate realistic COVID-19 images for facilitating privacy-enhanced COVID-19 detection with generative adversarial networks (GANs) in edge cloud computing. Particularly, we first propose a GAN where a discriminator and a generator based on convolutional neural networks (CNNs) at each edge-based medical institution alternatively are trained to mimic the real COVID-19 data distribution. Then, we propose a new federated learning solution which allows local GANs to collaborate and exchange learned parameters with a cloud server, aiming to enrich the global GAN model for generating realistic COVID-19 images without the need for sharing actual data. To enhance the privacy in federated COVID-19 data analytics, we integrate a differential privacy solution at each hospital institution. Moreover, we propose a new blockchain-based FedGAN framework for secur
The Internet of Things (IoT) paradigm is being rapidly adopted for the creation of smart environments in various domains. The IoT-enabled Cyber-Physical Systems (CPSs) associated with smart city, healthcare, Industry 4.0 and Agtech handle a huge volume of data and require data processing services from different types of applications in real-time. The Cloud-centric execution of IoT applications barely meets such requirements as the Cloud datacentres reside at a multi-hop distance from the IoT devices. \textit{Fog computing}, an extension of Cloud at the edge network, can execute these applications closer to data sources. Thus, Fog computing can improve application service delivery time and resist network congestion. However, the Fog nodes are highly distributed, heterogeneous and most of them are constrained in resources and spatial sharing. Therefore, efficient management of applications is necessary to fully exploit the capabilities of Fog nodes. In this work, we investigate the existing application management strategies in Fog computing and review them in terms of architecture, placement and maintenance. Additionally, we propose a comprehensive taxonomy and highlight the research
An unusual gravitational wave signal has renewed hopes that primordial black holes, long considered purely theoretical, may finally be within reach of discovery。 If confirmed, they could solve one of astronomy's greatest mysteries by explaining the nature of dark matter
Researchers solved the mystery of how soft lithium dendrites crack the hard ceramic inside solid-state batteries, triggering short circuits。 The breakthrough could help engineers build safer, longer-lasting batteries for smartphones, electric vehicles, and other electronics
NASA is marking the United States' 250th birthday with four striking red, white, and blue images of deep space from the Chandra X-ray Observatory。 The collection features an exploded star, a stellar nursery, a galaxy where stars are rapidly forming, and a galaxy cluster that provides evidence for dark matter
Researchers have achieved a major milestone by creating a long-sought two-dimensional quantum material and confirming its unusual conducting edge states。 The ability to control these states through strain could make the material a promising platform for future room-temperature quantum electronics
It's unclear how the planet avoided its star's bloated red giant stage
More police and firefighters use drones to catch and deter illegal fireworks