Knowledge catalogue
arXiv:2608.09948v1 Announce Type: cross Abstract: No single AI weather model excels at all variables, pressure levels, and lead times. Rather than building yet another architecture, we reframe the for
arXiv:2608.10806v1 Announce Type: new Abstract: Reliability estimation of large language models is in many cases as crucial as their accuracy, as reliable models are more trustworthy, robust, and suit
arXiv:2608.10744v1 Announce Type: new Abstract: 4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a sepa
arXiv:2608.10010v1 Announce Type: new Abstract: Low-precision datatypes reduce language-model cost, but most formats optimize scalar fidelity while leaving the arithmetic induced by their products unc
arXiv:2608.10756v1 Announce Type: cross Abstract: Embodied mobile manipulation requires language, visual observations, three-dimensional scene structure, and action feasibility to be aligned before ex
arXiv:2608.10857v1 Announce Type: new Abstract: Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particul
arXiv:2509.13211v4 Announce Type: replace Abstract: The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. Whi
arXiv:2608.10393v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks. However, their adversarial r
arXiv:2510.12947v3 Announce Type: replace-cross Abstract: Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices. Because conventional VADs respond to sp
Sometimes you have tasks that are outside of your expertise and the idea is this workflow automation could be leveraged to manage to have local AI figure it out using research from his workflow gather
arXiv:2602.15159v2 Announce Type: replace Abstract: Electronic health records (EHR) arrive masked. Clinicians order measurements selectively, and any patient table thus contains only a subset of the v
arXiv:2608.10002v1 Announce Type: cross Abstract: Hierarchical Phase-Contrast Tomography (HiP-CT) is a synchrotron based X-ray imaging technique that enables non-destructive, volumetric imaging of int
arXiv:2608.10170v1 Announce Type: new Abstract: Patient motion remains a source of image degradation in brain MRI, leading to signal loss, blurring, and geometric distortion that compromise quantitati
arXiv:2607.15779v2 Announce Type: replace Abstract: We present a multimodal framework for Ambivalence/Hesitancy (A/H) recognition in video, developed for the ABAW11 challenge at ECCV 2026. The propose
arXiv:2608.11045v1 Announce Type: cross Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (
arXiv:2608.10670v1 Announce Type: new Abstract: At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-reso
arXiv:2608.11030v1 Announce Type: cross Abstract: Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex
arXiv:2608.10682v1 Announce Type: new Abstract: Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing
arXiv:2608.10359v1 Announce Type: cross Abstract: As information increasingly traverses linguistic boundaries, users require concise cross-lingual representations of long-form content. Nevertheless, l
arXiv:2608.10878v1 Announce Type: new Abstract: Accurate and responsive turn-taking is essential for spoken dialogue systems, which must distinguish in real time between user interruptions, backchanne
arXiv:2608.08648v1 Announce Type: new Abstract: Whole-slide visual reasoning requires identifying sparse diagnostic evidence in gigapixel pathology slides and integrating observations across spatial s
arXiv:2608.09908v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries f
arXiv:2608.08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs. We study wheth
arXiv:2608.09302v1 Announce Type: new Abstract: Hysteroscopic surgical scene segmentation plays a pivotal role in understanding the hysteroscopic intraoperative environment as well as computer-assiste
arXiv:2608.08135v1 Announce Type: cross Abstract: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions, yet the field remains constrained by two coupled limitatio
arXiv:2506.02791v4 Announce Type: replace-cross Abstract: In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread
arXiv:2608.09266v1 Announce Type: new Abstract: Medical world models commonly learn from multimodal recordings synchronized onto a fixed-rate grid. This preprocessing resamples each native stream onto
arXiv:2608.07767v1 Announce Type: new Abstract: Accurate aneurysm segmentation in 3D rotational angiography (3DRA) is hindered by extreme class imbalance, morphological similarity to vessels, and abse
arXiv:2608.09047v1 Announce Type: cross Abstract: Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very l
arXiv:2508.16085v2 Announce Type: replace Abstract: Histopathology is essential for cancer diagnosis and treatment selection, and pathology foundation models learn visual representations from whole-sl
arXiv:2603.26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space,
arXiv:2608.09369v1 Announce Type: cross Abstract: Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extract
arXiv:2505.16941v4 Announce Type: replace-cross Abstract: Foundation models (FMs) promise to address core limitations of traditional supervised machine learning: (i) reliance on large amounts of label
arXiv:2608.08307v1 Announce Type: cross Abstract: Medical Visual Question Answering (VQA) requires aligning subtle visual evidence, including lesion texture, boundary sharpness, and diffuse density ch
arXiv:2506.00633v3 Announce Type: replace-cross Abstract: Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language
arXiv:2608.08888v1 Announce Type: new Abstract: Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth. Dense attention gives each
arXiv:2608.08010v1 Announce Type: cross Abstract: Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pre
arXiv:2608.08989v1 Announce Type: cross Abstract: Public infant cry corpora are small, label-incompatible, and almost always evaluated one corpus at a time. We ask what this practice hides and what fi
arXiv:2608.09385v1 Announce Type: cross Abstract: Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator
arXiv:2608.09348v1 Announce Type: new Abstract: Density estimation underlies many unsupervised tasks on tabular data such as anomaly detection, out-of-distribution detection, and data augmentation. Al
arXiv:2608.08460v1 Announce Type: new Abstract: Given textual task instructions, generating step-by-step visual instructions as an image sequence requires the simultaneous satisfaction of multiple pro
arXiv:2608.08976v1 Announce Type: new Abstract: Parkinson's disease (PD) is the second most common neurodegenerative disorder. Typical machine learning screening methods require PD labels, but the ava
arXiv:2608.08418v1 Announce Type: new Abstract: Leveraging textual information for image clustering has emerged as a promising direction, largely owing to the powerful representations learned by Visio
arXiv:2608.09083v1 Announce Type: new Abstract: Estimating human joint torques from visual observations is a key step toward bringing biomechanical analysis from controlled laboratories to real-world
arXiv:2604.05695v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in 2D visual tasks but still struggle to understand physical space in rea
arXiv:2608.07746v1 Announce Type: new Abstract: Long-horizon humanoid loco-manipulation requires composing versatile whole-body skills and reliable high-level decision making. Existing methods often c
arXiv:2608.09593v1 Announce Type: cross Abstract: Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a real
arXiv:2608.09405v1 Announce Type: new Abstract: Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods
arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each spar
arXiv:2608.08567v1 Announce Type: new Abstract: A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure. Su
arXiv:2608.08696v1 Announce Type: new Abstract: 3D occupancy prediction is fundamental to scene understanding, yet existing 3D semantic occupancy methods are typically specialized to fixed scene types
arXiv:2608.09223v1 Announce Type: new Abstract: AI-generated image detectors generalize poorly when their training and test images originate from different generators or datasets. Despite the rich spa
arXiv:2608.07582v1 Announce Type: new Abstract: Unplanned network hardware malfunctions can interrupt services and result in expensive downtime in data centers. A deep learning-based predictive mainte
arXiv:2608.07816v1 Announce Type: cross Abstract: Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate r
arXiv:2608.09834v1 Announce Type: new Abstract: Financial sentiment analysis converts unstructured financial news into quantitative signals that can support market analysis and decision-making. Existi
arXiv:2608.08555v1 Announce Type: new Abstract: Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images. Diffusion models are prom
arXiv:2608.08075v1 Announce Type: cross Abstract: Most video-retrieval systems assume a bounded corpus and return ranked files or timestamps. Agents operating over cameras, screens, streams, and archi
arXiv:2608.07916v1 Announce Type: new Abstract: Image demosaicing reconstructs a full-color image from incomplete color measurements produced by a sensor covered with a color filter array (CFA). Most
arXiv:2608.08685v1 Announce Type: new Abstract: Reliable semi-dense matching is essential for modern geometric vision systems. Designed under a coarse-to-fine paradigm, it achieves an optimal balance
arXiv:2607.28069v2 Announce Type: replace Abstract: Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders. Prefix