Knowledge catalogue
arXiv:2604.19052v1 Announce Type: new Abstract: Understanding a discourse requires tracking entities and the relations that hold between them. While Large Language Models (LLMs) perform well on relati
arXiv:2604.18589v1 Announce Type: cross Abstract: Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transpar
arXiv:2507.06321v2 Announce Type: replace Abstract: Collecting and annotating images for the purpose of training segmentation models is often cost prohibitive. In the domain of wildland fire science,
arXiv:2511.06168v3 Announce Type: replace Abstract: This paper primarily demonstrates a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models
arXiv:2604.18715v1 Announce Type: cross Abstract: Earth observation foundation models encode land surface information into dense embedding vectors, yet the geometric structure of these representations
arXiv:2604.19667v1 Announce Type: cross Abstract: At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and co
arXiv:2602.12851v3 Announce Type: replace-cross Abstract: Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered
arXiv:2604.18883v1 Announce Type: cross Abstract: Current AI-assisted programming tools are predominantly linear and chat-based, which deviates from the iterative and branching nature of programming i
arXiv:2604.19741v1 Announce Type: new Abstract: We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video
arXiv:2604.19211v1 Announce Type: new Abstract: Current AI agent frameworks have made remarkable progress in automating individual tasks, yet all existing systems serve a single user. Human productivi
arXiv:2602.20409v2 Announce Type: replace Abstract: Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these
arXiv:2510.26782v3 Announce Type: replace-cross Abstract: A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical
arXiv:2604.19309v1 Announce Type: cross Abstract: Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes o
arXiv:2604.19648v1 Announce Type: cross Abstract: SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary s
arXiv:2604.19488v1 Announce Type: new Abstract: Large language models (LLMs) have achieved substantial advances in logical reasoning, yet they continue to lag behind human-level performance. In-contex
arXiv:2604.19636v1 Announce Type: new Abstract: Synthesizing human--object interaction (HOI) videos has broad practical value in e-commerce, digital advertising, and virtual marketing. However, curren
arXiv:2604.18912v1 Announce Type: new Abstract: Discovering optimal designs through sequential data collection is essential in many real-world applications. While Bayesian Optimization (BO) has achiev
arXiv:2604.18725v1 Announce Type: new Abstract: The correlation between insect morphological traits and climate has been documented in physiological studies, but such studies remain limited by the tim
arXiv:2503.07259v2 Announce Type: replace-cross Abstract: The goal of creating intelligent, human-centered wearable systems for continuous activity understanding faces a fundamental trade-off: Egocent
arXiv:2508.14170v2 Announce Type: replace Abstract: The increasing deployment of large language models (LLMs) in natural language processing (NLP) tasks raises concerns about energy efficiency and sus
arXiv:2604.18920v1 Announce Type: cross Abstract: We test whether Speech Articulatory Coding (SPARC) features can linearly predict surface electromyography (sEMG) envelopes across aloud, mimed, and su
arXiv:2604.18587v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates pr
arXiv:2509.04072v2 Announce Type: replace-cross Abstract: Recent advances in text-to-speech (TTS) have been driven by large, multi-domain speech corpora, yet the expressive potential of audiobook data
arXiv:2604.19323v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label
arXiv:2510.17414v2 Announce Type: replace Abstract: Accurate prediction of lithium-ion battery capacity and its associated uncertainty is essential for reliable battery management but remains challeng
arXiv:2410.16431v4 Announce Type: replace Abstract: The semantic similarity between sample expressions measures the distance between their latent 'meaning'. These meanings are themselves typically rep
arXiv:2604.19137v1 Announce Type: new Abstract: Knowledge Graph (KG) can effectively integrate valuable information from massive data, and thus has been rapidly developed and widely used in many field
arXiv:2512.16059v2 Announce Type: replace-cross Abstract: In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-spe
arXiv:2604.18856v1 Announce Type: new Abstract: Hyperspectral image (HSI) classification remains challenging due to high spectral dimensionality, redundancy, and limited labeled data. Although convolu
arXiv:2604.02923v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), particularly those employing Mixture-of-Experts (MoE) architectures, have achieved remarkable capabilities acros
arXiv:2603.16091v2 Announce Type: replace-cross Abstract: In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet
arXiv:2604.19431v1 Announce Type: cross Abstract: Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been propose
arXiv:2604.19632v1 Announce Type: new Abstract: Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce raste
arXiv:2602.19991v2 Announce Type: replace Abstract: Speakers of under-represented languages face both a language barrier, as most online knowledge is in a few dominant languages, and a modality barrie
arXiv:2604.19598v1 Announce Type: cross Abstract: This study compared repeated generation consistency of exercise prescription outputs across three large language models (LLMs), specifically GPT-4.1,
arXiv:2604.18797v1 Announce Type: new Abstract: Automatic pancreas segmentation is fundamental to abdominal MRI analysis, yet deep learning models trained on one MRI sequence often fail catastrophical
arXiv:2604.19262v1 Announce Type: cross Abstract: Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities.
arXiv:2604.18701v1 Announce Type: cross Abstract: Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error acros
arXiv:2604.18816v1 Announce Type: cross Abstract: Principal Component Analysis (PCA) is a fundamental tool for representation learning, but its global linear formulation fails to capture the structure
arXiv:2604.19533v1 Announce Type: cross Abstract: We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of th
arXiv:2501.10258v2 Announce Type: replace-cross Abstract: We present a novel universal gradient method for solving convex optimization problems. Our algorithm, Dual Averaging with Distance Adaptation
arXiv:2604.18648v1 Announce Type: cross Abstract: Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent diffi
arXiv:2604.19351v1 Announce Type: new Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-contex
arXiv:2304.02296v2 Announce Type: replace Abstract: In our study, we conducted a comprehensive analysis of three widely used datasets in the domain of building footprint extraction using deep neural n
arXiv:2604.18853v1 Announce Type: new Abstract: This paper presents DDF2Pol, a lightweight dual-domain convolutional neural network for PolSAR image classification. The proposed architecture integrate
arXiv:2604.19005v1 Announce Type: new Abstract: Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on expli
arXiv:2604.19296v1 Announce Type: new Abstract: Neural operators are widely used to approximate solution maps of complex physical systems. In many applications, however, the goal is not to recover the
arXiv:2602.18571v2 Announce Type: replace-cross Abstract: While significant progress has been made in automating various aspects of software development through coding agents, there is still significa
arXiv:2604.19000v1 Announce Type: cross Abstract: Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into f
arXiv:2511.22099v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained sett
arXiv:2604.19176v1 Announce Type: cross Abstract: We study the deep image prior (DIP) framework applied to photoacoustic tomography (PAT) as an unsupervised reconstruction approach to mitigate limited
arXiv:2604.19480v1 Announce Type: new Abstract: While foundation models drive steady progress in image segmentation and diffusion algorithms compose always more realistic images, the seemingly simple
arXiv:2604.19477v1 Announce Type: cross Abstract: The intonational structure of Seoul Korean has been defined with discrete tonal categories within the Autosegmental-Metrical model of intonational pho
arXiv:2604.18745v1 Announce Type: new Abstract: Automated segmentation of structural defects from visual inspection imagery remains challenging due to the diversity of damage types, extreme class imba
arXiv:2604.19141v1 Announce Type: new Abstract: Diffusion- and flow-based models usually allocate compute uniformly across space, updating all patches with the same timestep and number of function eva
arXiv:2604.19106v1 Announce Type: cross Abstract: Extreme-edge scientific applications use machine learning models to analyze sensor data and make real-time decisions. Their stringent latency and thro
arXiv:2604.19561v1 Announce Type: new Abstract: Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Att
arXiv:2604.19565v1 Announce Type: cross Abstract: Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods typically rely on gold-standard out
arXiv:2604.19365v1 Announce Type: new Abstract: Face recognition systems are often used for biometric authentication. Nevertheless, it is known that without any protective measures, face recognition s
arXiv:2604.19124v1 Announce Type: new Abstract: Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity