Knowledge catalogue
arXiv:2511.08409v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) frequently suffer from unfaithfulness, generating reasoning chains that drift from visual evidence or contr
arXiv:2604.07350v1 Announce Type: cross Abstract: Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates rem
arXiv:2601.21708v2 Announce Type: replace Abstract: Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing accelerat
arXiv:2408.09369v3 Announce Type: replace-cross Abstract: As the rapid development of computer vision and the emergence of powerful network backbones and architectures, the application of deep learnin
arXiv:2604.08485v1 Announce Type: cross Abstract: The purpose of this paper is two-fold. First we show that Kim's building-up construction of binary self-dual codes is equivalent to Chinburg-Zhang's H
arXiv:2512.21602v2 Announce Type: replace-cross Abstract: Millions of patients pass through emergency departments and intensive care units each year, where clinicians must make high-stakes decisions u
arXiv:2604.06262v1 Announce Type: cross Abstract: Contextual clinical reasoning demands robust inference grounded in complex, heterogeneous clinical records. While state-of-the-art fine-tuning, in-con
arXiv:2604.06448v1 Announce Type: cross Abstract: Prime Video regularly conducts load tests to simulate the viewer traffic spikes seen during live events such as Thursday Night Football as well as vid
arXiv:2604.07323v1 Announce Type: cross Abstract: In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak-Ruppert averaged iterates generated by the asyn
arXiv:2604.07728v1 Announce Type: new Abstract: High-fidelity interactive digital assets are essential for embodied intelligence and robotic interaction, yet articulated objects remain challenging to
arXiv:2604.07928v1 Announce Type: new Abstract: While AI-based numerical weather prediction (NWP) enables rapid forecasting, generating high-resolution outputs remains computationally demanding due to
arXiv:2604.06989v1 Announce Type: cross Abstract: We present the first generative approach to photomosaic creation. Traditional photomosaic methods rely on a large number of tile images and color-base
Great to see this on X. This is something I created during my PhD time 20 years ago. This is a healing grid by Japanese artist Ryota Kanai. If you stare at the center, the irregularities start to heal
arXiv:2604.08301v1 Announce Type: new Abstract: The performance of visual anomaly inspection in industrial quality control is often constrained by the scarcity of real anomalous samples. Consequently,
arXiv:2604.06195v1 Announce Type: cross Abstract: Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated
arXiv:2604.07937v1 Announce Type: new Abstract: Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approache
arXiv:2511.09170v2 Announce Type: replace Abstract: This article presents HOTFLoc++, an end-to-end hierarchical framework for LiDAR place recognition, re-ranking, and 6-DoF metric localisation in fore
arXiv:2604.07233v1 Announce Type: new Abstract: We provide a computational complexity lens to understand the power of machine learning models, particularly their ability to model complex systems. Mach
arXiv:2604.08435v1 Announce Type: new Abstract: It remains challenging to assess driver fatigue from untrimmed videos under constrained computational budgets, due to the difficulty of modeling long-ra
arXiv:2604.06481v1 Announce Type: cross Abstract: This study introduces a hybrid deep learning model for intrusion detection in Industrial IoT (IIoT) systems, combining ResNet-1D, BiGRU, and Multi-Hea
arXiv:2604.07795v1 Announce Type: new Abstract: Recent generative models can create visually plausible 3D representations of objects. However, the generation process often allows for implicit control
arXiv:2405.03420v2 Announce Type: cross Abstract: This paper introduces a novel approach to enhance the performance of pre-trained neural networks in medical image segmentation using gradient-based Ne
arXiv:2402.08267v3 Announce Type: replace Abstract: Image coding for machines (ICM) aims to compress images for machine analysis using recognition models rather than human vision. Hence, in ICM, it is
arXiv:2604.06495v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alo
arXiv:2604.07958v1 Announce Type: new Abstract: Current video editing models often rely on expensive paired video data, which limits their practical scalability. In essence, most video editing tasks c
arXiv:2604.06356v1 Announce Type: cross Abstract: In-Context Learning (ICL) has been extensively studied in text-only Language Models, but remains largely unexplored in the speech domain. Here, we inv
arXiv:2604.06263v1 Announce Type: cross Abstract: Generative advertising in large language model (LLM) responses requires optimizing sponsorship configurations under two strict constraints: the strate
arXiv:2604.06485v1 Announce Type: cross Abstract: 'Best-of-N' selection is a popular inference-time scaling method for code generation using Large Language Models (LLMs). However, to reliably identify
arXiv:2507.09309v4 Announce Type: replace Abstract: Optimal path planning in nonconvex free spaces poses substantial computational challenges. A common approach formulates such problems as mixed-integ
arXiv:2602.22545v2 Announce Type: replace Abstract: Tau positron emission tomography (tau-PET) is an important in vivo biomarker of Alzheimer's disease, but its cost, limited availability, and acquisi
arXiv:2603.11090v2 Announce Type: replace Abstract: Prior-data fitted networks (PFNs) have emerged as powerful foundation models for tabular causal inference, yet their extension to time series remain
arXiv:2505.13126v3 Announce Type: replace-cross Abstract: Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve
arXiv:2507.13662v2 Announce Type: replace Abstract: This paper presents a scalable and adaptive control framework for legged robots that integrates Iterative Learning Control (ILC) with a biologically
arXiv:2604.08475v1 Announce Type: new Abstract: Human-like generalization in open-world remains a fundamental challenge for robotic manipulation. Existing learning-based methods, including reinforceme
arXiv:2602.13235v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a gi
arXiv:2604.07802v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) pe
arXiv:2511.17844v4 Announce Type: replace-cross Abstract: Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., sh
arXiv:2604.07467v1 Announce Type: new Abstract: Discrete speech units (DSUs) are derived by quantising representations from models trained using self-supervised learning (SSL). They are a popular repr
arXiv:2604.06171v1 Announce Type: cross Abstract: Communications networks now form the backbone of our digital world, with fast and reliable connectivity. However, even with appropriate redundancy and
arXiv:2510.13907v3 Announce Type: replace Abstract: Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth ref
arXiv:2604.07092v2 Announce Type: replace Abstract: In this work, we present LIANet (Location Is All You Need Network), a coordinate-based neural representation that models multi-temporal spaceborne E
arXiv:2502.17421v4 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingl
arXiv:2604.07822v1 Announce Type: new Abstract: We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models
arXiv:2604.08333v1 Announce Type: new Abstract: The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However
arXiv:2601.11471v3 Announce Type: replace Abstract: The key-value (KV) cache is a primary memory bottleneck in Transformers. We propose Low-Rank Key-Value (LRKV) attention, which reduces KV cache memo
arXiv:2512.17489v2 Announce Type: replace Abstract: Text-to-image (T2I) models have demonstrated remarkable progress in creative image generation, yet they still lack precise control over scene illumi
arXiv:2604.07574v1 Announce Type: new Abstract: Image matching is a fundamental problem in Computer Vision with direct applications in robotics, remote sensing, and geospatial data analysis. We presen
arXiv:2604.08364v1 Announce Type: new Abstract: In this paper, we introduce MegaStyle, a novel and scalable data curation pipeline that constructs an intra-style consistent, inter-style diverse and hi
arXiv:2604.06881v1 Announce Type: new Abstract: Neural operators have emerged as powerful surrogates for dynamical systems due to their grid-invariant properties and computational efficiency. However,
arXiv:2604.06473v1 Announce Type: new Abstract: Multivariate forecasting with Transformers faces a core scalability challenge: modeling cross-channel dependencies via attention compounds attention's q
arXiv:2604.07914v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable success across cross-modal tasks but remain hindered by hallucinations, producing textual
arXiv:2603.20654v4 Announce Type: replace-cross Abstract: Classical Amdahl's Law conceptualized the limit of speedup for an era of fixed serial-parallel decomposition and homogeneous replication. Mode
arXiv:2604.07030v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures are increasingly popular for frontier large language models (LLM) but they introduce training challenges d
arXiv:2509.07673v4 Announce Type: replace Abstract: Deep neural networks have exhibited impressive performance in image classification tasks but remain vulnerable to adversarial examples. Standard adv
arXiv:2604.01204v2 Announce Type: replace-cross Abstract: Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstru
arXiv:2507.09503v2 Announce Type: replace-cross Abstract: This paper proposes a neural stochastic optimization method for efficiently solving the two-stage stochastic unit commitment (2S-SUC) problem
A study published in *Science* (April 2026) by researchers from the Chinese Academy of Sciences challenges the long-held view that Yellowstone's supervolcano is powered by a deep mantle plume, inst...
arXiv:2501.10806v4 Announce Type: replace-cross Abstract: Two-time-scale stochastic approximation algorithms are iterative methods used in applications such as optimization, reinforcement learning, an
arXiv:2604.07254v1 Announce Type: cross Abstract: Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those
arXiv:2411.19653v2 Announce Type: replace-cross Abstract: We study the kernel instrumental variable (KIV) algorithm, a kernel-based two-stage least-squares method for nonparametric instrumental variab