Aligning human-interpretable concepts with the internal representations learned by modern machine learning systems remains a central challenge for interpretable AI. We introduce a geometric framework for comparing supervised human concepts with unsupervised intermediate representations extracted from foundation model embeddings. Motivated by the role of conceptual leaps in scientific discovery, we formalise the notion of concept frustration: a contradiction that arises when an unobserved concept induces relationships between known concepts that cannot be made consistent within an existing ontology. […]

Ver mais

Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental reasons behind misclassifications remain poorly understood. In this work, we take a novel perspective by examining recurring inductive subgraphs, empirically and theoretically showing that they act as spurious shortcuts that mislead GNNs and reinforce non-causal correlations […]

Ver mais

arXiv:2602.03992v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems have been popular for generative applications, powering language models by injecting external knowledge. Companies have been trying to leverage their large catalog of documents (e.g. PDFs, presentation slides) in such RAG pipelines, whose first step is the retrieval component. Dense retrieval has been a popular approach, where embedding models are used to generate a dense representation of the user query that is closer to relevant content embeddings. More recently, […]

Ver mais

By the end of this tutorial, you will clearly understand: Why RL looks similar to supervised learning—but behaves completely differently, Why unsupervised learning is closer philosophically, yet still not the right definition, When RL is the right tool, and when supervised is faster, cheaper, safer, and better, How cost, risk, and feedback shape the correct choice, How hybrid pipelines (Behavioral Cloning (BC) –> RL) work in the real world, How to test your problem using a simple decision […]

Ver mais

arXiv:2601.02385v1 Announce Type: new Abstract: As 5G networks rapidly expand and 6G technologies emerge, characterized by dense deployments, millimeter-wave communications, and dynamic beamforming, the need for scalable simulation tools becomes increasingly critical. These tools must support efficient evaluation of key performance metrics such as coverage and radio-frequency electromagnetic field (RF-EMF) exposure, inform network design decisions, and ensure compliance with safety regulations. Moreover, base station (BS) placement is a crucial task in the network design, where satisfying coverage requirements […]

Ver mais

The Quantum Darwinist Theory of Consciousness (QDT) and the Prototime Interpretation (PT) characterize localized conscious basins in terms of spectral integration, PT-participation, recursive coherence, witness redundancy, and temporally ordered record formation [7–9]. An upstream question has remained largely implicit in that program: what sort of morphology makes such dynamics structurally plausible? This paper argues that morphology constitutes the architectural precondition of basin formation, and that the Morphological Participation Index (MPI; Montes 5) can make that precondition operational. Architecture, […]

Ver mais

arXiv:2601.19926v1 Announce Type: new Abstract: We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models, reporting on 1,015 model results from a range of syntactic phenomena and interpretability methods. Our analysis shows that the state of the art presents a healthy variety of methods and data, but an over-focus on a single language (English), a single model (BERT), and phenomena that are easy to get at (like part of speech and agreement). […]

Ver mais

arXiv:2603.15636v1 Announce Type: new Abstract: As AI-driven document understanding and processing tools become increasingly prevalent in real-world applications, the need for rigorous evaluation standards has grown increasingly urgent. Existing benchmarks and evaluations often focus on isolated capabilities or simplified scenarios, failing to capture the end-to-end task effectiveness required in practical settings. To address this gap, we introduce AIDABench, a comprehensive benchmark for evaluating AI systems on complex data analytics tasks in an end-to-end manner. AIDABench encompasses 600+ diverse […]

Ver mais