Knowledge catalogue
arXiv:2605.14090v1 Announce Type: cross Abstract: We put forth a critical theoretical framework for analyzing generative models both descriptively and normatively. Our thesis is that generative models
arXiv:2605.14167v1 Announce Type: new Abstract: Every AI benchmark operationalizes theoretical assumptions about the capability it claims to assess. When assumptions function as unexamined commitments
arXiv:2605.15134v1 Announce Type: new Abstract: Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely l
arXiv:2605.11410v2 Announce Type: replace Abstract: Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, e.g., band power, connectivity, complexit
arXiv:2605.13046v1 Announce Type: new Abstract: Mental health disorders affect millions worldwide, and healthcare systems are increasingly overwhelmed by the volume of clinical data generated from ele
arXiv:2605.13383v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) perform computations on graphs by routing the signal between graph regions using a graph shift operator or a message passin
arXiv:2605.13642v1 Announce Type: cross Abstract: Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without cl
arXiv:2605.13337v1 Announce Type: cross Abstract: Security Information and Event Management (SIEM) systems aggregate log data from heterogeneous sources to detect coordinated attacks. Traditional rule
arXiv:2605.12968v1 Announce Type: cross Abstract: Do large language models internally encode ontological relations in a formally verifiable algebraic structure? We introduce Algebraic Ontology Project
arXiv:2605.13077v1 Announce Type: cross Abstract: Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analy
arXiv:2605.13612v1 Announce Type: new Abstract: Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We
arXiv:2605.13345v1 Announce Type: new Abstract: Emergency departments (ED) face challenges in patient care and resource management. We propose to explore optimization strategies in a realistic and fle
Mythos, a security researcher or team, successfully exploited macOS security vulnerabilities in a five-day timeframe, demonstrating the relative speed at which determined actors can compromise Apple's
arXiv:2605.13366v1 Announce Type: new Abstract: Accurate forward modelling is essential for non-invasive cardiac electrophysiology, particularly in atrial fibrillation, where electrical activation is
New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter de
arXiv:2605.13370v1 Announce Type: new Abstract: For over a decade, explicit memory architectures like the Neural Turing Machine have remained theoretically appealing yet practically intractable for la
arXiv:2605.12674v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly used in safety-critical applications because of their broad reasoning capabilities and ability to general
arXiv:2605.12651v1 Announce Type: new Abstract: Runtime monitoring of autonomous systems traditionally relies on mapping continuous sensor observations to discrete logical propositions defined over lo
arXiv:2510.12837v3 Announce Type: replace-cross Abstract: Cultural evolution allows ideas and technologies to accumulate across generations, reaching their most complex and open-ended form in humans.
arXiv:2601.19667v2 Announce Type: replace-cross Abstract: We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in
arXiv:2605.13601v1 Announce Type: new Abstract: As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concern
arXiv:2605.11558v1 Announce Type: new Abstract: Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations ha
arXiv:2605.11091v1 Announce Type: new Abstract: Automated ASD screening tools remain limited by single-architecture evaluations, axis-restricted assessment, and near-exclusive focus on adult cohorts,
arXiv:2605.11460v1 Announce Type: new Abstract: System identification (SysID) is critical for modeling dynamical systems from experimental data, yet traditional approaches often fail to capture nonlin
arXiv:2605.11972v1 Announce Type: new Abstract: Collisions at non-line-of-sight (NLOS) intersections remain a major safety concern because drivers have limited visibility of approaching traffic. V2X b
arXiv:2605.11463v1 Announce Type: new Abstract: Learning and representing the subjectivities of agents has become a challenging but crucial problem in the trajectory prediction task. Such subjectiviti
arXiv:2605.12017v1 Announce Type: new Abstract: Deep Learning has revolutionized machine learning, reaching unprecedented levels of accuracy, but at the cost of reduced interpretability. Especially in
This post outlines a framework for progressively automating AI workflows through three levels of increasing autonomy: using preset prompts for consistency, refining inputs with human judgment to impro
arXiv:2605.12361v1 Announce Type: new Abstract: Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain dis
arXiv:2503.09051v2 Announce Type: replace Abstract: We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reco
arXiv:2605.11742v1 Announce Type: new Abstract: Online Continual Learning (OCL) aims to learn from endless nonext{-}stationary data streams, yet most existing methods assume a flat label space and ove
arXiv:2605.12313v1 Announce Type: new Abstract: Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple s
arXiv:2605.11363v1 Announce Type: cross Abstract: Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal med
arXiv:2605.11887v1 Announce Type: new Abstract: Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, li
arXiv:2605.12059v1 Announce Type: cross Abstract: Computational thinking (CT) is increasingly promoted as a core literacy, yet learners and teachers face challenges in connecting abstract program logi
arXiv:2512.20865v2 Announce Type: replace Abstract: The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that
arXiv:2605.11919v1 Announce Type: new Abstract: Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node
arXiv:2505.20754v3 Announce Type: replace-cross Abstract: Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integratio
Databases have introduced new AI-powered SQL functions which take natural language instructions as input and are evaluated using LLMs. They leverage the power of LLMs to answer new kinds of queries: W
arXiv:2605.11963v1 Announce Type: new Abstract: This paper examines what it means for a medical AI system to be right by grounding the question in a specific clinical context: the automatic classifica
arXiv:2605.12090v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-
arXiv:2605.11743v1 Announce Type: new Abstract: Learning latent representations that capture both semantic and spatial information is central to efficient spatio-semantic reasoning. However, many exis
arXiv:2605.08513v1 Announce Type: cross Abstract: Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expr
arXiv:2605.10370v1 Announce Type: new Abstract: Scientific knowledge on the Web is published as passive assertions and cannot decide when to validate evidence, reconcile contradictions, or update conf
arXiv:2605.09662v1 Announce Type: new Abstract: Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-leve
arXiv:2603.16964v2 Announce Type: replace Abstract: Approval of ADS depends on evaluating its behavior within representative real-world traffic scenarios. A common way to obtain such scenarios is to e
arXiv:2605.10794v1 Announce Type: cross Abstract: Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidd
arXiv:2605.10817v1 Announce Type: new Abstract: Clinical EEG interpretation requires reasoning over full EEG sessions and integrating signal patterns with clinical context. Existing EEG foundation mod
arXiv:2605.09675v1 Announce Type: new Abstract: Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tra
arXiv:2605.10887v1 Announce Type: new Abstract: Open-world object counting remains brittle: despite rapid advances in vision-language models (VLMs), reliably counting the objects a user intends is far
arXiv:2605.08218v1 Announce Type: cross Abstract: This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimiz
arXiv:2410.02543v3 Announce Type: replace-cross Abstract: In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms. By considering evolution as a d
arXiv:2407.07639v2 Announce Type: replace-cross Abstract: Similarity search is a fundamental task for exploiting information in various applications dealing with graph data, such as citation networks
arXiv:2603.00166v2 Announce Type: replace-cross Abstract: Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a 'Paradox of Simplicity
arXiv:2605.09438v1 Announce Type: new Abstract: Many features in pretrained Transformers span multiple layers: they emerge through stages of inference, persist in the residual stream, or are built joi
arXiv:2602.01687v2 Announce Type: replace-cross Abstract: Large language models (LLMs) were invented for natural language tasks such as translation, but they have proved that they can perform highly c
arXiv:2512.19115v2 Announce Type: replace Abstract: Despite the remarkable success of multimodal large language models (MLLMs) in generative tasks, we observe that they exhibit a counterintuitive defi
arXiv:2508.20325v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted si
arXiv:2605.08295v1 Announce Type: cross Abstract: While random demonstration labels barely hurt in-context learning (Min et al., 2022), we show that homogeneous labels--even semantically valid ones--c
arXiv:2605.10627v1 Announce Type: cross Abstract: Coreference resolution is typically evaluated using aggregate statistical metrics such as CoNLL-F1, which measure structural overlap between predicted