technocracy

arXiv:2603.03304v1 Announce Type: new Abstract: We present a concise architecture for joint training on sentences and structured data while keeping knowledge and language representations separable. The model treats knowledge graphs and hypergraphs as structured instances with role slots and encodes them into a key-value repository that a language transformer can attend over. Attention is conditioned by journey-based role transport, which unifies edge-labeled KG traversal, hyperedge traversal, and sentence structure. We outline a dual-stream architecture, hierarchical layer groups with […]

Ver mais

The integrity of behavioral and social-science surveys depends on detecting inattentive respondents who provide random or low-effort answers. Traditional safeguards, such as attention checks, are often costly, reactive, and inconsistent. We propose a unified, label-free framework for inattentiveness detection that scores response coherence using complementary unsupervised views: geometric reconstruction (Autoencoders) and probabilistic dependency modeling (Chow-Liu trees). While we introduce a "Percentile Loss" objective to improve Autoencoder robustness against anomalies, our primary contribution is identifying the structural conditions that […]

Ver mais

arXiv:2604.02457v1 Announce Type: new Abstract: Automatic license plate reader (ALPR) systems are widely deployed to identify and track vehicles. While prior work has demonstrated vulnerabilities in ALPR systems, far less attention has been paid to their legality and physical-world practicality. We investigate whether low-resourced threat actors can engineer a successful adversarial attack against a modern open-source ALPR system. We introduce the Street-legal Physical Adversarial Rim (SPAR), a physically realizable white-box attack against the popular ALPR system fast-alpr. SPAR […]

Ver mais

Next-generation IoT applications increasingly span across autonomous administrative entities, necessitating silo-cooperative scheduling to leverage diverse computational resources while preserving data privacy. However, realizing efficient cooperation faces significant challenges arising from infrastructure heterogeneity, Non-IID workload shifts, and the inherent risks of adversarial environments. Existing approaches, relying predominantly on centralized coordination or independent learning, fail to address the incompatibility of state-action spaces across heterogeneous silos and lack robustness against malicious attacks. This paper proposes DeFRiS, a Decentralized Federated Reinforcement Learning […]

Ver mais

Quantum federated learning (QFL) emerges as a powerful technique that combines quantum computing with federated learning to efficiently process complex data across distributed quantum devices while ensuring data privacy in quantum networks. Despite recent research efforts, existing QFL frameworks struggle to achieve optimal model training performance primarily due to inherent heterogeneity in terms of (i) quantum noise where current quantum devices are subject to varying levels of noise due to varying device quality and susceptibility to quantum decoherence, […]

Ver mais

Hey guys, I am an undergrad researcher finalizing a preprint on multi-timescale temporal credit assignment, and I am looking for an arXiv endorsement for cs.LG (or cs.AI). Title: Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO TL;DR: We investigated why dynamically routing multi-timescale advantages inside an Actor-Critic architecture often leads to policy collapse. We formally diagnosed two pathologies: 1.Surrogate Objective Hacking: Differentiable routing allows the PPO policy gradient to hijack attention weights, artificially minimizing the clipped surrogate […]

Ver mais

Agentic reinforcement learning (RL) has emerged as a transformative workload in cloud clusters, enabling large language models (LLMs) to solve complex problems through interactions with real world. However, unlike traditional RL, agentic RL demands substantial external cloud resources, e.g., CPUs for code execution and GPUs for reward models, that exist outside the primary training cluster. Existing agentic RL framework typically rely on static over-provisioning, i.e., resources are often tied to long-lived trajectories or isolated by tasks, which leads […]

Ver mais

arXiv:2602.06045v1 Announce Type: new Abstract: Doppler-resilient complementary sequence (DRCS) sets play a vital role in modern communication and sensing systems, particularly in high-mobility environments. This work makes two primary contributions. First, we refine the definition of quasi-Florentine rectangles to a more general form,termed generalized quasi-Florentine rectangles, and propose a systematic method for their construction. Second, we propose several sets of aperiodic DRCS based on generalized quasi Florentine rectangles and Butson-type Hadamard matrices. The proposed aperiodic DRCS sets are […]

Ver mais

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which limits their understanding of environmental dynamics and their ability to generalize to unseen tasks. To address this limitation, we propose Visual-Language Knowledge-Guided Offline Reinforcement Learning (VLGOR), a framework that integrates visual and language knowledge to generate imaginary rollouts, thereby enriching the interaction data. The core premise of […]

Ver mais

arXiv:2603.20655v2 Announce Type: replace-cross Abstract: We introduce Exponential Family Discriminant Analysis (EFDA), a unified generative framework that extends classical Linear Discriminant Analysis (LDA) beyond the Gaussian setting to any member of the exponential family. Under the assumption that each class-conditional density belongs to a common exponential family, EFDA derives closed-form maximum-likelihood estimators for all natural parameters and yields a decision rule that is linear in the sufficient statistic, recovering LDA as a special case and capturing nonlinear decision […]

Ver mais