Knowledge catalogue
arXiv:2604.12431v1 Announce Type: cross Abstract: Organisations increasingly outsource privacy-sensitive data transformations to cloud providers, yet no practical mechanism lets the data owner verify
arXiv:2602.22394v2 Announce Type: replace Abstract: Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, art
arXiv:2604.12044v1 Announce Type: cross Abstract: Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Devia
arXiv:2510.21697v2 Announce Type: replace Abstract: In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by wo
arXiv:2604.12358v1 Announce Type: new Abstract: Recently, visual token pruning has been studied to handle the vast number of visual tokens in Multimodal Large Language Models. However, we observe that
arXiv:2604.12140v1 Announce Type: new Abstract: We present XANE(3), a physics-based E(3)-equivariant graph neural network for predicting X-ray absorption near-edge structure (XANES) spectra directly f
'Young, anxious followers, looking for purpose, can be radicalized by apocalyptic AI rhetoric […] The real question is how long the people fueling AI panic expect to avoid responsibility for where tha
arXiv:2604.11302v1 Announce Type: cross Abstract: We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS)
arXiv:2604.11211v1 Announce Type: new Abstract: Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this
arXiv:2604.10246v1 Announce Type: new Abstract: Photogrammetric 3D reconstruction has long relied on traditional Structure-from-Motion (SfM) and Multi-View Stereo (MVS) methods, which provide high acc
arXiv:2604.10241v1 Announce Type: new Abstract: Identifying the trajectories of rigid bodies and of interaction forces is essential for a wide range of tasks in robotics, biomechanics, and related dom
arXiv:2604.10650v1 Announce Type: cross Abstract: While the manifold hypothesis is widely adopted in modern machine learning, complex data is often better modeled as stratified spaces -- unions of man
arXiv:2604.10116v1 Announce Type: cross Abstract: Major depressive disorder (MDD) is a prevalent mental disorder associated with complex neurobiological changes that cannot be fully captured using a s
arXiv:2604.11064v1 Announce Type: cross Abstract: Continual Learning (CL) aims to train neural networks on a dynamic stream of tasks without forgetting previously learned knowledge. Among optimization
arXiv:2604.09752v1 Announce Type: cross Abstract: During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces seve
arXiv:2510.03989v2 Announce Type: replace-cross Abstract: The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models
arXiv:2604.09979v1 Announce Type: cross Abstract: Self-supervised representation learning is central to modern machine learning because it extracts structured latent features from unlabeled data and e
arXiv:2604.10177v1 Announce Type: cross Abstract: We study the piecewise-stationary restless multi-armed bandit (PS-RMAB) problem, where each arm evolves as a Markov chain but mean rewards may change
arXiv:2604.10957v1 Announce Type: cross Abstract: Writing systems are cultural replicators whose evolution has never been studied quantitatively at global scale. We compile the Global Script Database
arXiv:2604.10248v1 Announce Type: new Abstract: Complex systems such as aircraft engines, turbines, and industrial machinery often operate under dynamically changing conditions. These varying operatin
arXiv:2604.10506v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reason
arXiv:2604.10873v1 Announce Type: new Abstract: We propose an operational, quantitative definition of intelligence for arbitrary physical systems. The intelligence density of a system is the ratio of
arXiv:2604.10368v1 Announce Type: new Abstract: Media narratives wield tremendous power in shaping public opinion, yet computational approaches struggle to capture the nuanced storytelling structures
arXiv:2604.11048v1 Announce Type: cross Abstract: Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capa
arXiv:2604.10149v1 Announce Type: cross Abstract: Graph attention networks (GATs) provide one of the best frameworks for learning node representations in relational data; but, existing variants such a
arXiv:2604.11582v1 Announce Type: cross Abstract: Standard subword tokenization methods fragment numbers inconsistently, causing large language models (LLMs) to lose positional and decimal structure -
arXiv:2604.10210v1 Announce Type: new Abstract: Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyrami
arXiv:2507.12475v2 Announce Type: replace-cross Abstract: The St. Petersburg paradox presents a longstanding challenge in decision theory: its classical expected value diverges, yet no correspondingly
arXiv:2511.16164v2 Announce Type: replace Abstract: In a growing renewable based energy system, accurate and reliable wind power forecasts are crucial for grid stability, balancing supply and demand a
arXiv:2604.11410v1 Announce Type: new Abstract: We present a framework for bridging the gap between sensor attack detection and recovery in cyber-physical systems. The proposed framework models modern
arXiv:2604.09673v1 Announce Type: cross Abstract: The mirror self-recognition test evaluates whether a subject touches a mark on its own body that is visible only in a mirror, and is widely used as an
arXiv:2604.10607v1 Announce Type: cross Abstract: H-EFT-VA established a physics-informed solution to the Barren Plateau (BP) problem via a hierarchical EFT UV-cutoff, guaranteeing gradient variance i
arXiv:2604.10335v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong performance in math reasoning benchmarks, but their performance varies inconsistently across problems wi
arXiv:2407.11764v2 Announce Type: replace Abstract: Existing studies have shown that Message-Passing Graph Neural Networks (MPNNs) are highly susceptible to adversarial attacks. In contrast, despite t
arXiv:2508.06964v3 Announce Type: replace Abstract: Thanks to the development of cross-modal models, text-to-video retrieval (T2VR) is advancing rapidly, but its robustness remains largely unexamined.
arXiv:2602.17071v2 Announce Type: replace-cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topolo
arXiv:2604.09565v1 Announce Type: cross Abstract: This paper introduces a unified, hardware-independent baremetal runtime architecture designed to enable high-performance machine learning (ML) inferen
arXiv:2601.09211v2 Announce Type: replace Abstract: This paper addresses the problem of affordance grounding from RGBD images of an object, which aims to localize surface regions corresponding to a te
arXiv:2604.09576v1 Announce Type: new Abstract: Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolvin
arXiv:2604.10290v1 Announce Type: new Abstract: AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that
arXiv:2604.10529v1 Announce Type: cross Abstract: We develop a high-precision classifier to measure artificial intelligence (AI) patents by fine-tuning PatentSBERTa on manually labeled data from the U
arXiv:2604.11730v1 Announce Type: new Abstract: Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits
arXiv:2308.04977v4 Announce Type: replace-cross Abstract: We consider the configuration space of ordered points on the two-dimensional sphere that satisfy a specific system of quadratic equations. We
arXiv:2406.11290v3 Announce Type: replace-cross Abstract: Relevance and utility are two frequently used measures to evaluate the effectiveness of an information retrieval (IR) system. Relevance emphas
arXiv:2504.09484v2 Announce Type: replace Abstract: In this paper, we provide an overview of a common phenomenon, condensation, observed during the nonlinear training of neural networks: During the no
arXiv:2604.10805v1 Announce Type: new Abstract: Accurate distance estimation from monocular cameras is essential for intelligent monitoring systems. In many deployments, image coordinates are mapped t
arXiv:2604.10312v1 Announce Type: new Abstract: In CT angiography, the accurate segmentation of abdominal aortic aneurysms (AAAs) is difficult due to large anatomical variability, low-contrast vessel
arXiv:2604.11754v1 Announce Type: cross Abstract: In this work, we study angle-based localization and rigidity maintenance control for multi-robot networks under sensing constraints. We establish the
arXiv:2604.11331v1 Announce Type: new Abstract: 3D scene generation has long been dominated by 2D multi-view or video diffusion models. This is due not only to the lack of scene-level 3D latent repres
ARC-AGI-3 Human Baseline Dataset Today we're open-sourcing the ARC-AGI-3 Human Baseline. This is the most exhaustive human testing study in the ARC-AGI series Every environment was solved by at least
arXiv:2604.10217v1 Announce Type: new Abstract: Cross-modal optical-SAR (Synthetic Aperture Radar) registration is a bottleneck for disaster-response via remote sensing, yet modern image matchers are
arXiv:2604.09695v1 Announce Type: cross Abstract: The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently
arXiv:2604.10078v1 Announce Type: new Abstract: Student engagement is crucial for improving learning outcomes in group activities. Highly engaged students perform better both individually and contribu
arXiv:2604.09700v1 Announce Type: cross Abstract: Constructing high-resolution 3D geological models from sparse 1D borehole and 2D surface data is a highly ill-posed inverse problem. Traditional heuri
arXiv:2604.10697v1 Announce Type: new Abstract: Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context.
arXiv:2301.01864v2 Announce Type: replace-cross Abstract: We derive an exact, prediction-specific instance-attribution method for fitted gradient boosting machines (GBMs) trained with squared-error lo
arXiv:2604.11628v1 Announce Type: new Abstract: Existing conversational memory systems rely on complex hierarchical summarization or reinforcement learning to manage long-term dialogue history, yet re
arXiv:2604.10362v1 Announce Type: new Abstract: Accurate battery health prognosis using State of Health (SOH) estimation is essential for the reliability of multi-scale battery energy storage, yet exi
arXiv:2510.12460v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems often fail to maintain contextual faithfulness, generating responses that conflict with the provided co
arXiv:2604.11665v1 Announce Type: cross Abstract: This paper reports an unexpected finding: in a deterministic hyperdimensional computing (HDC) architecture based on Galois-field algebra, a path-depen