Knowledge catalogue
arXiv:2608.18106v1 Announce Type: cross Abstract: Large language models tend to overconfidence, giving assertive answers when the evidence suggests hedging or abstention. Using controlled reasoning sc
arXiv:2608.19067v1 Announce Type: cross Abstract: The empirical success of diffusion models in generative modelling has motivated theoretical work, including quantitative error bounds and qualitative
arXiv:2608.18816v1 Announce Type: cross Abstract: AI hallucinations - that is, outputs which are made up, cannot be verified, or contradict the source material - are generally regarded as an engineeri
arXiv:2608.19084v1 Announce Type: new Abstract: S-JEPA uses soft Gaussian mixture model (GMM) posteriors instead of hard cluster labels to preserve uncertainty. It remains unclear whether the probabil
arXiv:2608.18182v1 Announce Type: new Abstract: Small NLP models, especially BERT-family encoders, remain important in industrial workloads such as classification, ranking, and retrieval even in the e
arXiv:2608.18762v1 Announce Type: new Abstract: Graph autoencoders (GAEs) are widely used for learning representations of dynamic graphs. However, their optimisation objectives typically do not take s
arXiv:2608.19117v1 Announce Type: new Abstract: Quantitative microstructural characterization of Li-ion battery electrode materials using electron backscatter diffraction (EBSD) has been proven as a c
arXiv:2608.18539v1 Announce Type: cross Abstract: The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes
arXiv:2608.18624v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are becoming a powerful tool for many environmental monitoring and transport applications. Yet, their reliance on Global
arXiv:2608.18181v1 Announce Type: cross Abstract: Selecting a small, diverse subset from a large candidate pool often means balancing several incompatible notions of diversity. In trademark curation,
arXiv:2608.18803v1 Announce Type: cross Abstract: Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely
arXiv:2608.18445v1 Announce Type: cross Abstract: We present the first mechanised formalisation of Romanov's Triplet Logic (TLS) in the Rocq proof assistant. TLS is a triplet-based combinatorial frame
arXiv:2512.05092v2 Announce Type: replace-cross Abstract: Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom
arXiv:2608.18679v1 Announce Type: new Abstract: Structured documents such as invoices, forms, reports, and scientific articles derive meaning from the interplay between spatial layout, textual content
arXiv:2608.18969v1 Announce Type: new Abstract: We consider the problem of classification of skin tone using photoplethysmography (PPG) signals with labels of the ordinal six-class Fitzpatrick skin to
arXiv:2608.18522v1 Announce Type: cross Abstract: Large antenna arrays allow wireless systems to serve more users and achieve higher data rates, but they also make channel feedback expensive: the rece
arXiv:2608.18849v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and
arXiv:2503.08484v2 Announce Type: replace Abstract: With the rapid development of image synthesis techniques, AI-generated images have become increasingly realistic, which heightens the potential risk
arXiv:2608.19141v1 Announce Type: cross Abstract: Neural audio codecs based on Residual Vector Quantization (RVQ) have become the dominant discrete representation for token-based general audio generat
arXiv:2608.18767v1 Announce Type: new Abstract: Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface
arXiv:2608.18936v1 Announce Type: cross Abstract: Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall
arXiv:2607.10476v2 Announce Type: replace Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advan
arXiv:2607.16094v2 Announce Type: replace Abstract: Compositional visual question answering requires Vision-Language Models (VLMs) to execute multiple reasoning operations like object selection, spati
arXiv:2608.18184v1 Announce Type: new Abstract: Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet i
arXiv:2608.18821v1 Announce Type: cross Abstract: The logical reconstruction of argument graphs from natural language text is challenging because of the prevalence of enthymemes (i.e., arguments with
arXiv:2607.18197v2 Announce Type: replace Abstract: Seamless human-robot interaction (HRI) requires a number of perceptual and motor abilities from the robot, one of them being the imitation of human
arXiv:2608.18409v1 Announce Type: new Abstract: Combinatorial scheduling poses a significant challenge for language models, requiring them to identify feasible solutions within exponentially large sea
arXiv:2608.18374v1 Announce Type: cross Abstract: We address two open questions in streaming PCA via Oja's algorithm: sharp operator-norm convergence for general rank under sub-Gaussian data, and dist
arXiv:2608.18592v1 Announce Type: new Abstract: Whether distinct neural architectures develop common collective dynamics remains an open question. Recent analysis of Transformer language models reveal
arXiv:2608.18957v1 Announce Type: new Abstract: Historical book collections contain rich visual elements - such as illustrations, photographs, engravings, and decorative art - that are frequently unde
arXiv:2502.02891v2 Announce Type: replace-cross Abstract: Recent advances in implicit neural representations have made them a popular choice for modeling 3D geometry. However, directly editing these r
arXiv:2608.19124v1 Announce Type: cross Abstract: Astrolinguistics -- communication with minds that categorize reality differently from ours -- has been purely speculative since Freudenthal's Lincos (
arXiv:2608.19163v1 Announce Type: cross Abstract: Seasonal precipitation anomalies are largely regulated by atmospheric circulation, which dynamical models predict with greater reliability than precip
arXiv:2502.16445v4 Announce Type: replace-cross Abstract: Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for ente
arXiv:2603.17566v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) with high-quality knowledge has been shown to enhance their performance effectively. However, there is a pa
arXiv:2608.18138v1 Announce Type: cross Abstract: In recent years, the rapid development of language models has transformed the field of Natural Language Processing through a wide range of application
arXiv:2608.19127v1 Announce Type: cross Abstract: A gradient-boosted ensemble predicts by summing one leaf value per tree. Read those values as coordinates rather than as intermediate results, and eve
arXiv:2608.18765v1 Announce Type: new Abstract: Register automata are finite automata equipped with memory that recognize data languages over infinite alphabets. In this work, we investigate active le
arXiv:2608.19082v1 Announce Type: cross Abstract: We present a new data-driven learning of a Random Geometric Graph (RGG) of a multivariate dataset, where the graph is drawn in a probabilistic metric
arXiv:2608.19171v1 Announce Type: new Abstract: Deep models for irregularly-sampled time series answer queries at arbitrary continuous timestamps, yet report nothing about how far each answer should b
arXiv:2510.03115v2 Announce Type: replace Abstract: Speech-to-Text Translation (S2TT) systems built from Automatic Speech Recognition (ASR) and Text-to-Text Translation (T2TT) modules face two major l
arXiv:2608.18215v1 Announce Type: new Abstract: Existing 3D relighting methods operate through either explicit material decomposition, diffusion-based view-space generation, or a combination of both,
arXiv:2608.18810v1 Announce Type: new Abstract: An optimizer is usually chosen before training a deep neural network and then kept fixed. Treating optimizer choice as a hyperparameter could boost perf
arXiv:2608.18827v1 Announce Type: cross Abstract: Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, ex
arXiv:2608.18982v1 Announce Type: new Abstract: Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data gen
arXiv:2608.18448v1 Announce Type: cross Abstract: More context does not require a larger retrieval budget. Under the same ceiling, a retrieval system can recover more of the evidence a question requir
arXiv:2608.18558v1 Announce Type: cross Abstract: The prediction of equilibrium beach profiles under tidal influence is of fundamental importance for sustainable coastal development, informing shoreli
arXiv:2608.18851v1 Announce Type: new Abstract: Convolution integrals widely exist in applications, and to enable fast and accurate computations, this paper introduces two general multi-stage neural o
arXiv:2608.18094v1 Announce Type: cross Abstract: Large pretrained language models have demonstrated remarkable capabilities across diverse languages, yet critically underrepresented low-resource lang
arXiv:2608.18597v1 Announce Type: new Abstract: Protein language models are widely used priors for protein sequence design, and a growing body of work controls them at inference time as an alternative
arXiv:2608.18910v1 Announce Type: new Abstract: Hard combinatorial optimization problems, many of which are NP-hard, present fundamental algorithmic challenges. Average-case analysis on random instanc
arXiv:2608.18194v1 Announce Type: new Abstract: This paper presents new theoretical results on generalizing the Jaccard distance for lattices and real valuations. We demonstrate that when the valuatio
arXiv:2608.18130v1 Announce Type: cross Abstract: We study online bipartite matching with reusable server capacity and non-stationary rewards. Jobs arrive sequentially, reveal compatible servers, rewa
arXiv:2603.25954v2 Announce Type: replace Abstract: The use of satellite networks has increased significantly in recent years due to their advantages over purely terrestrial systems, such as higher av
arXiv:2608.18109v1 Announce Type: new Abstract: Narrative Entropy (S_n) is a proposed quantitative descriptor within the Bulut Doctrine, intended to capture the rate at which a narrative text imposes
arXiv:2608.19021v1 Announce Type: new Abstract: Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recogn
arXiv:2608.18820v1 Announce Type: new Abstract: Arguments often omit premises or claims, forming enthymemes. We study pairwise logical selection between two candidates for the omitted component. Exist
arXiv:2608.18622v1 Announce Type: new Abstract: Automatic portrait retouching has advanced rapidly, yet its objective is inherently subjective: the same portrait admits multiple professionally valid r
arXiv:2608.18484v1 Announce Type: cross Abstract: Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable
arXiv:2608.18625v1 Announce Type: cross Abstract: Cable-suspended payload transport by multirotor UAVs is flexible but generates periodic swing disturbance that degrades tracking and risks instability