Knowledge catalogue
arXiv:2506.10911v2 Announce Type: replace Abstract: Training large language models is generally done on clusters containing thousands of accelerators, communicating over a high-bandwidth interconnect.
arXiv:2609.05778v1 Announce Type: new Abstract: Elliptic homogenization is used to determine coarse-grained properties of materials with features on small scales. When these small scale features have
arXiv:2609.08554v1 Announce Type: new Abstract: In data-driven training, multivariate time-series forecasting is usually optimized with a scalar loss averaged over samples, variables, and horizons. Th
arXiv:2609.06074v1 Announce Type: new Abstract: Sparse optical flow provides stable inter-frame correspondence, playing a key role in Visual Odometry (VO) and Visual-Inertial Odometry (VIO). Classical
arXiv:2609.08106v1 Announce Type: new Abstract: MASTER's inter-stock multi-head attention -- the module responsible for modeling cross-sectional stock relationships -- accounts for 42.5% of model para
arXiv:2609.05962v1 Announce Type: new Abstract: A sound runtime admission gate executes only actions it can certify, and certifies only what its observations support. This paper asks how observations
arXiv:2609.06421v1 Announce Type: new Abstract: Batch normalization (BN) substantially improves sample efficiency in continuous-control actor-critic methods such as CrossQ, yet recent studies report p
arXiv:2410.11500v2 Announce Type: replace-cross Abstract: In this paper, we establish a collection of covering number bounds for linear function classes under various norm constraints on the inputs an
arXiv:2507.03404v3 Announce Type: replace Abstract: The z-transform of a sequence is a classical tool used within signal processing, control theory, computer science, and electrical engineering. It al
arXiv:2607.16769v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems. Their ability to gene
arXiv:2609.07078v1 Announce Type: new Abstract: For learning generalizable motion representations from large-scale unlabeled data, Self-supervised learning (SSL) has become a widely adopted methodolog
arXiv:2609.06253v1 Announce Type: new Abstract: Translating between imaging sonar and optical cameras is valuable for underwater perception, but supporting both directions with separate models duplica
arXiv:2609.07440v1 Announce Type: new Abstract: This paper proposes an open-set ego-noise separation framework for legged-robot audition via annotation-free adaptation and pretrained-model transfer. T
arXiv:2609.08671v1 Announce Type: cross Abstract: In this paper, we consider the scalar-on-function linear regression model under a realistic sampling scheme in which the functional covariates are obs
arXiv:2609.08172v1 Announce Type: cross Abstract: Slice sampling is a Markov chain Monte Carlo algorithm that draws its next state uniformly from a 'slice'---a super-level set of the target density fu
arXiv:2609.05676v1 Announce Type: new Abstract: Language models adapted on private text are often served through APIs, so privacy leakage occurs through generated outputs rather than exposed weights.
arXiv:2609.07455v1 Announce Type: new Abstract: How can vision-language models help video anomaly detection (VAD) when surveillance data remain distributed, weakly labeled, and resource-constrained? M
arXiv:2609.06947v1 Announce Type: new Abstract: Flow matching, together with classifier-free guidance (CFG), is widely used in generative modeling, yet much of the theoretical understanding remains di
arXiv:2607.02156v2 Announce Type: replace Abstract: Patient-specific anatomical models provide individualized context for surgical planning, image-guided intervention, and algorithm development. Howev
arXiv:2609.07300v1 Announce Type: new Abstract: Ground-penetrating radar (GPR) B-scan image synthesis is important for data augmentation, algorithm validation, and simulation acceleration, yet generat
arXiv:2609.06629v1 Announce Type: new Abstract: Recent advancements in deep learning allow robotic agents to interact with dynamic and unstructured environments. Of special interest is the integration
arXiv:2609.05542v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) provide a mesh-free framework for solving governing equations, but their application to granular avalanche dy
arXiv:2609.07061v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is unkno
arXiv:2609.09020v1 Announce Type: new Abstract: Implicit neural representation (INR) has achieved remarkable progress in novel view synthesis and image/video coding in recent years.Compared to convent
arXiv:2609.08101v1 Announce Type: cross Abstract: Protein-conditioned 3D molecule generation is a central challenge in structure-based drug design, requiring a balance between pocket compatibility, mo
arXiv:2609.09145v1 Announce Type: new Abstract: We introduce Point4D, a feed-forward model for 4D reconstruction of long-range video sequences. Point4D is able to reliably infer dense per-point 3D tra
arXiv:2609.06489v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) has demonstrated success in online planning for deterministic environments, yet significant challenges remain in adapting
arXiv:2609.06194v1 Announce Type: cross Abstract: Offshore wind turbines are widely used to generate renewable energy, but their maintenance can result in decreased efficiency due to forced shutdowns.
arXiv:2410.23667v2 Announce Type: replace Abstract: Neural differential equations offer a powerful approach for learning dynamical systems from data. However, they do not inherently respect known cons
arXiv:2609.05953v1 Announce Type: new Abstract: Few-shot fine-grained object detection (FGOD) in remote sensing imagery is challenging because limited annotations must support both object localization
arXiv:2609.06343v1 Announce Type: new Abstract: Multimodal image matching is a fundamental task for multi-source information fusion. However, geometric distortions and nonlinear radiometric difference
arXiv:2606.06295v2 Announce Type: replace Abstract: Path sampling methods generate ensembles of reactive trajectories connecting metastable states, but extracting mechanistic insight from these data r
arXiv:2609.07941v1 Announce Type: new Abstract: In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods rely
arXiv:2609.06746v1 Announce Type: cross Abstract: Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textual chains of thought. However,
arXiv:2609.06182v1 Announce Type: cross Abstract: In this paper, we develop and analyze techniques for recovering a linear image Bx of an unknown signal x from indirect noisy observation omega=Ax+xi.
arXiv:2609.06382v1 Announce Type: cross Abstract: In many scientific disciplines, weak signals of interest are obscured by dominant nuisance signals that are several orders of magnitude stronger. Reco
arXiv:2609.05507v1 Announce Type: cross Abstract: Indirect time-of-flight (iToF) cameras provide compact and cost-effective dense depth measurements, but their ranging accuracy is often degraded by se
arXiv:2609.08365v1 Announce Type: new Abstract: Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retrieval-Augmented Text-to-Motion (RAG
arXiv:2609.05738v1 Announce Type: new Abstract: We present 'RenderFormer-V2', a unified learned transformer-based neural rendering model, complementary to modern physics-based rendering systems, that
arXiv:2510.10681v2 Announce Type: replace-cross Abstract: High-quality data is a cornerstone of large language model (LLM) pretraining, yet its growth has not kept pace with the needs of frontier mode
arXiv:2609.06154v1 Announce Type: new Abstract: One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communicat
arXiv:2508.02184v3 Announce Type: replace Abstract: Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and re
arXiv:2609.07432v1 Announce Type: new Abstract: Kernel methods are widely used because of their strong theoretical guarantees and empirical performance. However, their high computational cost limits t
arXiv:2609.08044v1 Announce Type: new Abstract: Bone-selective digitally reconstructed radiograph (DRR) synthesis depends on high-resolution encoder detail, yet static skips cannot condition reuse on
arXiv:2609.08339v1 Announce Type: new Abstract: Bimanual manipulation policies require large and diverse training datasets, yet collecting demonstrations on physical robots is expensive and difficult
arXiv:2609.06284v1 Announce Type: cross Abstract: Conditional dimension reduction (cDR) learns low-dimensional latent coordinates while accounting for observed covariates that represent known sources
arXiv:2609.06346v1 Announce Type: new Abstract: Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However,
arXiv:2505.14486v3 Announce Type: replace Abstract: This paper presents an immersive bilateral teleoperation framework for beyond-human-scale manipulators, combining motion/force transparency with enh
arXiv:2609.05561v1 Announce Type: cross Abstract: Rollcast is a probabilistic forecasting method for univariate time series that combines a compact set of rolling statistical anchors rather than relyi
arXiv:2609.06685v1 Announce Type: cross Abstract: We derive an exact gradient-step representation of the RoPE-softmax forward pass. For every deterministic RoPE-softmax attention head with arbitrary a
arXiv:2602.01533v2 Announce Type: replace Abstract: Online handwritten character recognition leverages stroke order and dynamic features, which generally provide higher accuracy and robustness compare
arXiv:2509.23442v2 Announce Type: replace-cross Abstract: Convolutional Neural Networks have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial fe
arXiv:2609.05826v1 Announce Type: new Abstract: Dynamic programming for optimal classification trees becomes computationally expensive as the numbers of features and training samples increase. We deve
arXiv:2609.08280v1 Announce Type: new Abstract: In multi-robot collaboration, task handovers rely on downstream verifiers performing remote attestation, which inspects sensor telemetry to ensure a rob
arXiv:2609.08461v1 Announce Type: cross Abstract: Parametric PDEs can admit different boundary conditions with different accuracy and computational cost. We introduce a framework for learning when one
arXiv:2609.05859v1 Announce Type: cross Abstract: Learning with class-conditional label noise often relies on a transition model from latent clean classes to observed annotations. Forward correction e
arXiv:2609.07415v1 Announce Type: new Abstract: We present a self-supervised approach, Self-MVGTE, for estimating 3D gaze targets from multiple camera views. Unlike existing methods that independently
arXiv:2609.06419v1 Announce Type: new Abstract: Medical vision-language models (VLMs) require confidence that reflects both answer correctness and patient-specific visual evidence. Recent GRPO-based m
arXiv:2601.17090v3 Announce Type: replace Abstract: Partial differential equations (PDEs) govern complex systems, yet neural operators often struggle to efficiently capture the long-range, nonlocal in
arXiv:2609.07868v1 Announce Type: cross Abstract: We study the training dynamics of multiclass logistic regression on high-dimensional Gaussian mixture models with a large number of classes and establ