Distributed Systems & Hardware

MLQENABLER allows secure machine learning queries on encrypted databases, striking a balance between data privacy and ML performance.

PGD-NO breaks the memory barrier for neural PDE solvers, enabling high-fidelity simulations on meshes with over 10 million nodes.

Even with just one-bit communications, agents can perform complex global computations in dynamic networks, challenging assumptions about communication limits.

GPU frequency behavior reveals inter-kernel dependencies that could revolutionize latency-prediction models in machine learning.

zkComposer achieves up to 6.84x faster proof generation for zero-knowledge machine learning, revolutionizing the scalability of private model inference.

gspDAG-FL achieves near-optimal learning quality with significantly reduced coordination costs, even in the presence of Byzantine and lazy participants.

Federated learning can significantly boost cardiovascular disease risk prediction accuracy without compromising patient privacy, achieving a C-statistic increase of 0.011 in a challenging data-sharing environment.

Poisoning attacks can severely undermine autonomous vehicle systems, but a new framework effectively filters out malicious influences to ensure safer decision-making.

System-aware optimizations in KV cache design could dramatically reduce the memory footprint and costs of serving large language models.

Balancing session-centric scheduling can boost LLM cluster throughput by up to 16% without sacrificing token reuse.

Predicting user scheduling states can recover up to 73% of the sum rate loss caused by backhaul delays in coordinated beamforming systems.

FedOPAL achieves state-of-the-art accuracy in federated learning without incurring server-side training costs, revolutionizing edge intelligence collaboration.

Even with a majority of compromised keys, adversaries can't forge authorization seals, revolutionizing digital asset custody security.

Naive verification methods for PLCs can produce 44% false alarms due to unrealistic sensor models, but a new hardware-faithful approach eliminates these errors entirely.

DeepCORD adapts solver parameters in real-time, outperforming traditional methods in distributed optimization across complex geometric scenarios.

Achieving near-centralized localization performance in multi-robot systems without the need for extensive communication could revolutionize how teams of robots operate in real-world environments.

Aggressive sampling can significantly enhance performance in asynchronous Kaczmarz methods, but only if tuned just right—too much can lead to instability.

Coded offloading not only boosts performance but also reveals a surprising delay-energy-privacy trade-off that challenges conventional task execution strategies.

Fiber Memory can slash weight-delivery energy by over 70% while eliminating redundant storage across thousands of AI accelerators.

Pre-processing error vectors with Singular Value Decomposition can drastically enhance the efficiency of quantum error correction in distributed systems.

Efficient self-stabilizing algorithms for local symmetry breaking problems can now be executed in a truly uniform distributed model, challenging previous limitations in computational expressivity.

Log-Insight transforms incident diagnosis from a manual, time-consuming process into an efficient automated workflow, achieving over 90% accuracy in identifying root causes within a minute.

Migrating large-model inference to non-GPU accelerators like Huawei Ascend reveals eight critical limitations that could derail performance and reliability.

Mispredictions in power savings can occur, but they never lead to incorrect outputs, making Stochastic Activity Prediction a game-changer for tensor accelerator efficiency.

Quantization errors in speech enhancement models can be largely mitigated by robust spatial filtering, enabling efficient deployment on low-resource devices.

Unifying GPU communication semantics could eliminate the fragmentation in OpenSHMEM implementations across different vendors.

TRM-Raft keeps malicious leader influence under 5% even with a significant presence of Byzantine nodes, offering a robust solution for decentralized systems.

Hidden Decoding achieves unprecedented performance improvements in large language models by scaling computation along the sequence length without modifying the Transformer architecture.

FeLiX slashes the time-to-target accuracy in federated learning by over 2X, making models far more responsive to real-time user data.

Bypassing database drivers can lead to up to 27x speedups in analytical workloads by directly reading storage files with LLM-assisted code synthesis.

Legacy paper ECGs can now be transformed into actionable diagnostic tools in under 30 seconds, even in resource-constrained settings.

Achieving formal privacy in federated learning without sacrificing model performance, FedKT-CSD outperforms traditional methods even under stringent privacy constraints.

Concentrating model capacity on delegation roles can yield substantial performance gains in hierarchical search agents, revealing a critical bottleneck in task decomposition.

Existing vulnerability assessment tools miss critical operating system flaws in software-defined vehicles, exposing a vast landscape of security threats.

Autonomous validator management using fuzzy inference can significantly reduce resource waste and improve blockchain efficiency under varying workloads.

Current Trojan detection methods overlook the stealthy risks posed by compromised standard-cell libraries, revealing a critical vulnerability in zero-trust IC design.

Achieving 99.60% accuracy with a model that requires only 2,370 FLOPS could redefine the landscape of IoT security solutions.

eBIM redefines blockchain infrastructure management by integrating RISC-V to reclaim trust and flexibility lost in traditional BaaS models.

Voters can now securely cast and verify their ballots without relying on a trusted key dealer, dramatically enhancing the integrity of electronic voting systems.

A revolutionary authentication protocol that slashes authentication bandwidth by 99.2% while ensuring complete vehicle-level data sovereignty.

Federated learning can be exploited to encode and extract private training data, revealing a surprising vulnerability in multi-client environments.

Achieving 99.94% of the theoretical maximum for entanglement certification reveals a new frontier in the efficiency of quantum software development.

Voltron boosts LLM accuracy by 16.5% by harnessing the power of multiple edge devices, transforming how we think about local AI execution.

Transforming gradients into a near-isotropic space can cut LLM pretraining time by 7.6% while enhancing downstream task performance.

Achieving up to 31.8% lower latency in multi-GPU systems could redefine how we optimize Large Language Model serving under strict latency constraints.

Achieving efficient multiple double arithmetic on NVIDIA tensor cores could significantly boost performance in high-precision applications.

The cost gap between new AI entrants and established incumbents is set to widen, with incumbents enjoying a 3-4x advantage by 2029-30.

Achieving a 2.52x speedup in quantum circuit execution could redefine efficiency benchmarks in scalable quantum computing.

A miter-aware mapping framework can slash SAT solving times by over 92% by aligning circuit structures with solver needs.

Achieving a 3.5x boost in Energy-Delay-Inverse-Yield, ThermoDSE redefines the optimization landscape for chiplet-based DNN accelerators under thermal constraints.