arXiv:2604.07494v1 Announce Type: new Abstract: Context: AI coding agents route every task to a single frontier large language model (LLM), paying premium inference cost even when many tasks are routine. Objectives: We propose Triage, a framework that uses code health metrics — indicators of software maintainability — as a routing signal to assign each task to the cheapest model tier whose output passes the same verification gate as the expensive model. Methods: Triage defines three capability tiers (light, […]

Ver mais

arXiv:2602.03851v1 Announce Type: new Abstract: The mastery of Hijaiyah letters is a crucial foundation for reading and comprehending the Quran, yet conventional pedagogical approaches based on repetitive memorization frequently struggle to maintain the engagement of young learners in contemporary educational contexts. This research presents the design and implementation of an innovative gamification-based methodology for Hijaiyah literacy acquisition, systematically developed through the ADDIE framework (Analysis, Design, Development, Implementation, Evaluation) to optimize student motivation, participation, and educational outcomes. The resulting […]

Ver mais

arXiv:2601.14339v1 Announce Type: new Abstract: Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique challenges of open-ended urban spaces characterized by rich semantics, complex geometries, and view variations. To address this, we introduce CityCube, a systematic benchmark designed to probe cross-view reasoning capabilities of current VLMs in urban settings. CityCube integrates four viewpoint dynamics to mimic camera movements […]

Ver mais

arXiv:2601.18984v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful framework for improving the reasoning capabilities of large language models (LLMs). However, most existing RL approaches rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions. Process reward models (PRMs) offer fine-grained step-level supervision, but their scores are often noisy and difficult to evaluate. As a result, recent PRM benchmarks focus on a more objective capability: detecting the first […]

Ver mais

arXiv:2601.04342v1 Announce Type: new Abstract: Recent advances in video diffusion models have shifted towards transformer-based architectures, achieving state-of-the-art video generation but at the cost of quadratic attention complexity, which severely limits scalability for longer sequences. We introduce ReHyAt, a Recurrent Hybrid Attention mechanism that combines the fidelity of softmax attention with the efficiency of linear attention, enabling chunk-wise recurrent reformulation and constant memory usage. Unlike the concurrent linear-only SANA Video, ReHyAt’s hybrid design allows efficient distillation from existing […]

Ver mais

arXiv:2601.03332v1 Announce Type: new Abstract: Kolmogorov–Arnold Networks (KAN) replace scalar weights by learnable univariate functions, often implemented with B-splines. This design can be accurate and interpretable, but it makes inference expensive on CPU because each layer requires many spline evaluations. Standard quantization toolchains are also hard to apply because the main computation is not a matrix multiply but repeated spline basis evaluation. This paper introduces LUT-KAN, a segment-wise lookup-table (LUT) compilation and quantization method for PyKAN-style KAN layers. […]

Ver mais

arXiv:2602.23365v1 Announce Type: new Abstract: Organisations face polycrisis uncertainty yet overlook embedded knowledge. We show how generative AI can operate as a serendipity engine and knowledge transducer to discover, classify and mobilise reusable components (models, frameworks, patterns) from existing documents. Using 206 papers, our pipeline extracted 711 components (approx 3.4 per paper) and organised them into a repository aligned to Beer’s Viable System Model (VSM). We contribute i) conceptually, a theory of planned serendipity in which GenAI lowers […]

Ver mais

Movement Network Foundation is building a modular blockchain framework that integrates the security-focused Move language with Ethereum’s liquidity to enable safer smart contracts and scalable decentralized applications. By combining the Move VM, modular rollups, and decentralized governance tools like Snapshot and Tally, the project aims to create a high-throughput infrastructure for Web3 builders while advancing its broader mission of democratizing digital ownership.

Ver mais