Research Papers
Research Papers news — Thursday 01 October 2026
46 stories from 2 sources, every one in English. Each links to its publisher.
-
Snowball refrigeration of Earth’s crust mimics glacial erosion
Science Magazine Tech
Science, Ahead of Print.
-
Robustifying Asynchronous SGD via Soft Throttling
arXiv cs.DC (Distributed)
arXiv:2609.39357v1 Announce Type: cross Abstract: Asynchronous SGD is a popular algorithm for distributed learning where each client's gradient update is applied on arrival. This leads to a speed-up, but also an increased vulnerability to…
-
Preserving Provenance in Shared KV Caches for LLM Serving
arXiv cs.DC (Distributed)
arXiv:2609.38706v1 Announce Type: new Abstract: Production LLM serving stacks combine an inference engine's local prefix cache with a shared KV-cache tier for fleet-wide reuse. The local cache distinguishes requests by adapter, weight…
-
Darpan: A Digital Twin Framework for the Next-Generation Computing Continuum
arXiv cs.DC (Distributed)
arXiv:2609.39799v1 Announce Type: new Abstract: Computing-continuum applications distribute work across devices, edge systems, fog resources, and clouds. While a placement, scheduling, or recovery decision is being made, resource…
-
ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations
arXiv cs.DC (Distributed)
arXiv:2609.32868v3 Announce Type: replace Abstract: Traditional scientific computing requires researchers to translate intent into environment configuration, resource requests, and executable jobs, then diagnose failures from scheduler…
-
IBLTs Measure Before They Decode: Self-Sizing Set Reconciliation for Database Consistency Verification
arXiv cs.DC (Distributed)
arXiv:2608.26537v4 Announce Type: replace-cross Abstract: Cross-system data replication pipelines cannot confirm end-to-end consistency from the local guarantees of each hop, so the two endpoints must be compared directly on a periodic…
-
SWB-DM: A Calibrated Sliced-Wasserstein-Barycenter Aggregator with Delayed-Momentum Caching for Byzantine-Robust Federated Learning under Partial Participation
arXiv cs.DC (Distributed)
arXiv:2609.16099v2 Announce Type: replace-cross Abstract: Robust aggregation methods for federated learning quietly rest on a fragile assumption: that whoever shows up in a given round is a fair sample of the full population. In practice…
-
Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution
arXiv cs.DC (Distributed)
arXiv:2609.29808v2 Announce Type: replace-cross Abstract: In July 2026, an unconstrained autonomous agent participating in a frontier AI cybersecurity evaluation harness breached its evaluation sandbox, established an external…
-
Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure
arXiv cs.DC (Distributed)
arXiv:2609.38697v1 Announce Type: new Abstract: We present Cascadia, a system for serving large language models on fleets of commodity Intel AIPCs using their CPU, integrated-GPU, and NPU resources. Every node embeds ingress, scheduling…
-
LatencyLab: A DPDK-Based P4 Pipeline Latency Measurement Framework for FPGA SmartNICs
arXiv cs.DC (Distributed)
arXiv:2609.39978v1 Announce Type: new Abstract: P4-programmable FPGA SmartNICs place packet processing directly on the wire, but open FPGA P4 toolflows do not expose timestamping at the pipeline boundary, so the latency a P4 program adds…
-
Enabling Efficient Client Selection in FL-as-a-Service for Multi-Application based Society 5.0
arXiv cs.DC (Distributed)
arXiv:2609.38626v1 Announce Type: cross Abstract: The rapid development of the Internet of Things (IoT) has led to the generation of vast amounts of data from sensors, prompting the need for advanced learning models to analyze this data…
-
Bitcoin-IPC: Scaling Bitcoin with a Network of Proof-of-Stake Subnets
arXiv cs.DC (Distributed)
arXiv:2512.23439v5 Announce Type: replace Abstract: Despite holding over $1.7T in value, Bitcoin scales poorly: Layer-1 (L1) processes only a few transactions per second, and Layer-2 (L2) solutions suffer from operational and liquidity…
-
Exploring Adaptive Byzantine Quorum Systems to Improve Latency in the WAN
arXiv cs.DC (Distributed)
arXiv:2609.39715v1 Announce Type: new Abstract: Quorum systems enforce strict consistency in Byzantine fault-tolerant (BFT) state machine replication: Before a value is decided, a subset of replicas (called quorum) must exchange votes for…
-
About the Influence of Workflow Topology on Task Intensity Prediction through Graph Learning
arXiv cs.DC (Distributed)
arXiv:2609.39481v1 Announce Type: new Abstract: Efficient resource provisioning for large-scale workflows on cloud infrastructures is a critical performance engineering challenge. These workflows are often structured as directed acyclic…
-
Vectorized Dynamic Histograms for Sparse Oblique Forests
arXiv cs.DC (Distributed)
arXiv:2603.00326v2 Announce Type: replace-cross Abstract: Sparse oblique (SPO), part of the top-ranked configuration of Google's Yggdrasil Decision Forests (YDF), improve the accuracy while maintaining interpretability of Random Forests…
-
Local Relaxation Hierarchies for Quantum Ground State Energies: Convergence Guarantees and Message Passing Algorithms
arXiv cs.DC (Distributed)
arXiv:2609.40336v1 Announce Type: cross Abstract: Convex relaxation hierarchies provide lower bounds to the ground state energy of quantum many-body systems that can be computed in polynomial time on a classical computer, at any fixed…
-
MQSS-Selector: RL-Guided Pass Selection for an MLIR Compilation Pipeline
arXiv cs.DC (Distributed)
arXiv:2609.30104v2 Announce Type: replace-cross Abstract: High Performance Computing (HPC) and Quantum Computing (QC) systems are increasingly converging towards unified High Performance Computing-Quantum Computing (HPCQC) infrastructures…
-
HAPMoE: Heterogeneity-Aware Automatic Parallelism Planning for Mixture-of-Experts Models Training
arXiv cs.DC (Distributed)
arXiv:2609.39350v1 Announce Type: new Abstract: As model sizes continue to scale, distributed training has become inevitable. Automatic parallelization techniques can derive efficient training parallelism strategies at low cost while…
-
An Island-Based Parallel Biased Random-Key Genetic Algorithm for the Three-Dimensional Trailer Loading Problem
arXiv cs.DC (Distributed)
arXiv:2609.39272v1 Announce Type: cross Abstract: The Three-Dimensional Trailer Loading Problem (3D-TLP) involves determining the optimal placement and orientation of heterogeneous items within the confined space of a trailer while…
-
MoEless: Efficient MoE LLM Serving with Serverless Experts
arXiv cs.DC (Distributed)
arXiv:2603.06350v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale efficiently under stringent resource constraints. However, MoE's sparse activation causes…
-
SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation
arXiv cs.DC (Distributed)
arXiv:2609.32391v2 Announce Type: replace-cross Abstract: Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with…
-
GeoFP8: Geometry-Aware FP8 Gradient Compression for Distributed LLM Training
arXiv cs.DC (Distributed)
arXiv:2607.07494v2 Announce Type: replace Abstract: Gradient communication is a primary scaling bottleneck in large language model (LLM) pretraining. Communicating gradients in low-precision formats, such as FP8 and NVFP4, can…
-
Many Processors, Still One Computer: The Nested Parallel von Neumann Architecture and Nested BSP
arXiv cs.DC (Distributed)
arXiv:2609.16787v2 Announce Type: replace Abstract: The contest in large-scale AI computing is no longer whether one processor can be made stronger, but whether a million of them can still behave as a single computer. This paper argues…
-
Vosti: Specifying, Implementing, and Verifying Deterministic LLM Inference
arXiv cs.DC (Distributed)
arXiv:2609.38981v1 Announce Type: new Abstract: LLM inference systems may vary batch composition, prompt chunking, prefill/decode execution, and KV-cache reuse, eviction, or recomputation. These optimizations should not affect system…
-
From Pilots to Production: Lessons in Cross-Institutional Federated Training and Artificial Intelligence for Science
arXiv cs.DC (Distributed)
arXiv:2609.39803v1 Announce Type: new Abstract: Many of the most valuable scientific datasets cannot be centralized: they are proprietary, export-controlled, classified, or bound by data-sovereignty restrictions. This inverts the usual…
-
Characterizing High Bandwidth Flash for LLM Serving
arXiv cs.DC (Distributed)
arXiv:2609.39131v1 Announce Type: cross Abstract: Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, memory capacity and bandwidth…
-
Towards Efficient HPC Systems for Agents: Challenges and Opportunities
arXiv cs.DC (Distributed)
arXiv:2609.38723v1 Announce Type: new Abstract: Coding agents have become real users of high-performance computing (HPC) systems, yet today's HPC abstractions, interfaces, and policies remain designed for human-driven workflows. In our…
-
Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning
arXiv cs.DC (Distributed)
arXiv:2609.39250v1 Announce Type: cross Abstract: Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have…
-
Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs
arXiv cs.DC (Distributed)
arXiv:2609.40093v1 Announce Type: new Abstract: Expert parallelism (EP) enables inference of large Mixture-of-Experts (MoE) models by placing their experts across multiple GPUs, but requires substantial communication between GPUs at every…
-
Taming Speculative Search for Test-Time Scaling in LLM Serving
arXiv cs.DC (Distributed)
arXiv:2609.39334v1 Announce Type: new Abstract: Test-time scaling has recently emerged as a powerful approach for improving LLM reasoning by allocating additional computation during inference, substantially enhancing accuracy on…
-
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
arXiv cs.DC (Distributed)
arXiv:2607.04085v2 Announce Type: replace-cross Abstract: Routing-prediction federated learning has emerged as a new paradigm that reframes inter-client heterogeneity as a resource for system-level intelligence: at inference time, the…
-
Argus: A Real-EKS Study of When Predicting Spot Interruptions Beats Simple Checkpointing
arXiv cs.DC (Distributed)
arXiv:2609.39067v1 Announce Type: cross Abstract: Elastic Compute Cloud (EC2) Spot is 60% to 90% cheaper than On-Demand but can be reclaimed on just a 2-minute notice; for expensive multi-node training this loss can be severe, with one…
-
Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda
arXiv cs.DC (Distributed)
arXiv:2604.17227v2 Announce Type: replace Abstract: The rapid rise of Large Language Models (LLMs) has revolutionized various artificial intelligence (AI) applications, from natural language processing to code generation. However, the…
-
When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
arXiv cs.DC (Distributed)
arXiv:2609.38275v1 Announce Type: new Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or memory states evolve. Existing work…
-
Deterministic Self-Stabilizing BFS Construction in Constant Space
arXiv cs.DC (Distributed)
arXiv:2505.06596v2 Announce Type: replace Abstract: In this paper, we resolve a long-standing question in self-stabilization by demonstrating that it is indeed possible to construct a spanning tree in a semi-uniform network using constant…
-
XIM: The XDC Interledger Messaging Protocol
arXiv cs.DC (Distributed)
arXiv:2609.39310v1 Announce Type: cross Abstract: Distributed ledgers, privacy-preserving institutional networks, and conventional payment systems increasingly need to exchange authenticated messages and settle assets across heterogeneous…
-
Kirin: Cloud-native WebAssembly Service Orchestration
arXiv cs.DC (Distributed)
arXiv:2609.39631v1 Announce Type: new Abstract: Modern cloud computing infrastructure relies heavily on virtualization to provide workload isolation and resource efficiency. While containers have become the dominant deployment primitive…
-
Reinforcement Learning-Guided Graph Transformations for SpTRSV Optimization
arXiv cs.DC (Distributed)
arXiv:2609.40159v1 Announce Type: new Abstract: Sparse triangular solve (SpTRSV) is a fundamental kernel in numerous scientific and engineering applications. However, the data dependencies inherent in sparse triangular matrices…
-
Quantifying Teleportation Overhead in Distributed Unitary Coupled-Cluster Ans\"atze
arXiv cs.DC (Distributed)
arXiv:2609.36266v2 Announce Type: replace-cross Abstract: Distributed quantum computing (DQC) has been proposed as a way to scale quantum algorithms for practical applications beyond monolithic quantum processor architectures. Among these…
-
Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple
arXiv cs.DC (Distributed)
arXiv:2601.16294v3 Announce Type: replace Abstract: General Matrix Multiplication (GEMM) is the cornerstone of HPC workloads and Deep Learning. State-of-the-art (SOTA) vendor libraries tune tensor layouts, parallelization schemes and cache…
-
EPR Count for Runtime Prediction in Distributed Quantum Computing
arXiv cs.DC (Distributed)
arXiv:2609.39851v1 Announce Type: new Abstract: EPR-pair consumption is commonly used as a communication-cost objective in distributed quantum computing, but minimizing EPR cost does not necessarily minimize distributed execution time…
-
Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs
arXiv cs.DC (Distributed)
arXiv:2609.38266v1 Announce Type: cross Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside the effect. Janus puts the record on the…
-
Distributed Stochastic Momentum Tracking with Local Updates: Achieving Optimal Communication Complexities
arXiv cs.DC (Distributed)
arXiv:2510.24155v3 Announce Type: replace-cross Abstract: We propose Local Momentum Tracking (LMT), a novel distributed stochastic gradient method for solving distributed optimization problems over networks. To reduce communication…
-
Communication-Efficient $(1+\varepsilon)\Delta$-Edge Coloring and Lov\'asz Local Lemma
arXiv cs.DC (Distributed)
arXiv:2609.39359v1 Announce Type: new Abstract: We study edge coloring in the two-party edge-partition model, where Alice and Bob each know part of the edge set and must jointly produce a proper coloring with little communication. Previous…
-
FissionReady: Joint Workload and Power Scheduling for Data Centers Powered by Small Modular Reactors
arXiv cs.DC (Distributed)
arXiv:2609.39422v1 Announce Type: new Abstract: Data centers are increasingly exploring small modular nuclear reactors (SMRs) as a carbon-free power source, but variable datacenter demand and negative grid prices require the SMR plant to…
-
TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training
arXiv cs.DC (Distributed)
arXiv:2604.09107v2 Announce Type: replace Abstract: Modern LLM reinforcement learning (RL) workloads require a high-performance weight transfer system to scale training across heterogeneous compute resources. However, efficiently…