Research Papers
Research Papers news — Wednesday 28 October 2026
23 stories from 2 sources, every one in English. Each links to its publisher.
-
Differential Privacy of Decentralized Learning: Centralized Rate Conditions and Nearly Tight Guarantees
arXiv cs.DC (Distributed)
arXiv:2505.19969v4 Announce Type: replace-cross Abstract: We analyze the differential privacy of gossip averaging on a graph with independent Gaussian noise at every node, as seen by a subset of observing nodes. We characterize the privacy…
-
From Generation to Scoring: Scaling LLM-Based Semantic Labeling at LinkedIn
arXiv cs.DC (Distributed)
arXiv:2610.36383v1 Announce Type: cross Abstract: For efficiency, industrial large language model (LLM) labelers often pack many candidate labels into one prompt and generate a YES/NO answer for each, even when each decision depends only…
-
Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring
arXiv cs.DC (Distributed)
arXiv:2610.36329v1 Announce Type: cross Abstract: GPU clusters have become essential computing resources for AI and scientific research in academia and industry. However, their high cost and growing demand often result in long queueing…
-
IOSage: Detecting HPC I/O Bottleneck Patterns to Guide LLM Recommendations
arXiv cs.DC (Distributed)
arXiv:2610.36370v1 Announce Type: new Abstract: HPC applications often leave much of their parallel file system's bandwidth unused, and turning their Darshan logs into concrete I/O fixes still requires a scarce I/O expert. Rule-based tools…
-
InfraDev: Can Coding Agents Develop AI Infrastructure, and How Can We Tell?
arXiv cs.DC (Distributed)
arXiv:2610.36589v1 Announce Type: cross Abstract: Coding agents are beginning to develop the production-grade AI infrastructure that trains and serves large models, yet existing benchmarks cover only single kernels or single-GPU tasks, and…
-
JustGoal: With Only a Goal, the AI Baseline Is Above the Expert Kernels
arXiv cs.DC (Distributed)
arXiv:2610.36434v1 Announce Type: new Abstract: A small number of GPU kernels often determines the efficiency of large language model training and inference. High-performance kernel development typically relies on expert knowledge through…
-
Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
arXiv cs.DC (Distributed)
arXiv:2604.02344v2 Announce Type: replace-cross Abstract: WebGPU's security-focused design imposes per-operation validation that compounds across the many small dispatches in neural network inference, yet the true cost of this overhead is…
-
Merkle-Tree-Based Verifiable Public Data Auditing for Cloud Object Storage Using Smart Contracts
arXiv cs.DC (Distributed)
arXiv:2610.36001v1 Announce Type: cross Abstract: Owners of data in cloud object storage cannot directly check whether the provider still keeps every object unchanged. Existing research mostly checks blocks inside files or relies on…
-
R2CC: Reliable and Resilient Collective Communication for Distributed Learning
arXiv cs.DC (Distributed)
arXiv:2512.25059v2 Announce Type: replace Abstract: Modern ML training and inference now span hundreds to tens of thousands of GPUs, where failures can waste 10-15% of GPU hours due to slow recovery. Common network errors and link…
-
Quality-Driven Energy-Efficient Big Data Aggregation in WBANs
arXiv cs.DC (Distributed)
arXiv:2206.05699v1 Announce Type: cross Abstract: In the Internet-of-Things (IoT) era, the development of Wireless Body Area Networks (WBANs) and their applications in big data infrastructure has gotten a lot of attention from the medical…
-
ML-ECS: Heterogeneity-Aware Collaborative Multimodal Learning for Edge-Cloud Synergies
arXiv cs.DC (Distributed)
arXiv:2602.14107v2 Announce Type: replace Abstract: Edge-cloud synergies provide a promising paradigm for privacy-preserving deployment of foundation models in heterogeneous web environments, enabling lightweight edge models to support…
-
From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow
arXiv cs.DC (Distributed)
arXiv:2509.12443v4 Announce Type: replace-cross Abstract: Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward…
-
Agar: What-If Analysis for Microservice Applications
arXiv cs.DC (Distributed)
arXiv:2610.36636v1 Announce Type: new Abstract: Microservice operators must reason about how applications would behave under changes that have not yet occurred: different workloads, resource allocations, or SLO targets. Evaluating every…
-
PipeLink: Contract-Guided Linking of GPU Kernel Components
arXiv cs.DC (Distributed)
arXiv:2610.37200v1 Announce Type: new Abstract: The fastest machine-learning kernels are compositions of components, such as loaders, matrix-multiply mainloops, epilogues and communication stages, that run concurrently on one GPU streaming…
-
Seeing is believing: The case for hardware-centric inefficiency detection and remediation
arXiv cs.DC (Distributed)
arXiv:2510.26008v3 Announce Type: replace-cross Abstract: Large-scale machine learning workloads on the cloud suffer from silent inefficiencies, which do not trigger failures or obvious anomalies, making them hard to detect and diagnose…
-
Request-Adaptive Execution for Efficient Hybrid LLM Inference
arXiv cs.DC (Distributed)
arXiv:2610.37432v1 Announce Type: new Abstract: Hybrid large language models (LLMs) have emerged as a promising way to combine the modeling capability of the Attention mechanism with the efficiency of state space models (SSMs). However…
-
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving
arXiv cs.DC (Distributed)
arXiv:2610.37230v1 Announce Type: new Abstract: Agentic services alternate between model inference on clustered GPUs and external tools on distributed CPUs. In this scenario, existing systems (1) overlook tool-return readiness in service…
-
IoT-based Smart Real-Time Energy-Aware Server Room Monitoring System
arXiv cs.DC (Distributed)
arXiv:2610.35873v1 Announce Type: cross Abstract: The integration of the Internet of Things (IoT) into monitoring systems has become increasingly significant across various fields, including energy management, environmental monitoring, and…
-
INC-MoE: Overlapping In-Network Collectives and Expert Computation for Expert-Parallel Mixture-of-Experts Inference
arXiv cs.DC (Distributed)
arXiv:2610.36339v1 Announce Type: new Abstract: In expert-parallel mixture-of-experts (MoE) serving, dispatch moves tokens to the accelerators hosting their selected experts, and combine returns expert outputs to each token's owner. Both…
-
Taming Multi-Dimensional Skew in Sparse Matrix Multiplication with Contention-Aware Scheduling [Technical Report]
arXiv cs.DC (Distributed)
arXiv:2610.36822v1 Announce Type: new Abstract: Sparse general matrix-matrix multiplication (SpGEMM) is a key kernel in graph analytics, relational queries, and machine learning. Yet, its performance remains a significant challenge, due to…
-
Correcting Before Adapting: Gradient Correction for Federated Adaptive Optimization
arXiv cs.DC (Distributed)
arXiv:2502.02727v4 Announce Type: replace-cross Abstract: Client-drift compensation methods mitigate the impact of data heterogeneity in federated learning (FL). While drift correction is well studied for stochastic gradient descent…
-
Could a giant sunshade in space ‘solve global warming’? Scientists are taking the idea seriously
Nature Technology
-
Development, validation and AI chatbot evaluation of the Adolescent Mental Health AI Response Tool
Nature Technology