Knowledge catalogue
arXiv:2407.20737v3 Announce Type: cross Abstract: This study explores the application of Kolmogorov-Arnold networks (KANs) in predicting nuclear binding energies, leveraging their ability to decompose
arXiv:2609.33350v1 Announce Type: new Abstract: Learning population dynamics from temporally sparse, unpaired distribution snapshots is a fundamental challenge in developmental biology. Recent approac
arXiv:2609.35710v1 Announce Type: new Abstract: We introduce LHFM, a geometric framework for learning image dynamics. Drawing on structures central to classical mechanics, symplectic geometry, and geo
arXiv:2609.35288v1 Announce Type: cross Abstract: Joint-embedding self-supervised learning typically combines an invariance objective across augmented views with additional mechanisms to prevent repre
arXiv:2609.32556v1 Announce Type: cross Abstract: Based on an analysis of the role of language in thought and communication, this article proposes a new concept for designing corporate knowledge bases
arXiv:2609.33423v1 Announce Type: new Abstract: Large Language Models (LLMs) can contribute useful engineering knowledge to robot design, but directly generated designs may rely on implicit assumption
arXiv:2609.35260v1 Announce Type: new Abstract: Spiking neural networks are attractive for low-power speech command recognition, yet their latency has received far less attention than their energy eff
arXiv:2609.32132v1 Announce Type: new Abstract: In cross-silo split learning, Parallel Split Learning with Global Sampling forms representative pooled batches when class distributions differ across cl
arXiv:2609.32794v1 Announce Type: new Abstract: Latent generative models make 3D medical image synthesis computationally practical by generating in a compressed space. However, we show that the common
arXiv:2609.35598v1 Announce Type: cross Abstract: We introduce the Functional Spectral-Newton Method (FSNM) for learning the leading singular structure of a conditional expectation operator without fi
arXiv:2609.32958v1 Announce Type: new Abstract: In many teleoperation applications, collecting a large number of demonstrations as required for traditional probabilistic learning from demonstration (L
arXiv:2609.33659v1 Announce Type: new Abstract: Multimodal large language models can expose task-relevant evidence through generation, but producing useful evidence does not by itself determine how it
arXiv:2609.35767v1 Announce Type: new Abstract: Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong,
arXiv:2609.34614v1 Announce Type: new Abstract: Managing water resources in mountainous regions depends heavily on reliable Snow Water Equivalent (SWE) and Snow Height (HS) data, yet these variables r
arXiv:2609.32820v1 Announce Type: cross Abstract: This paper studies learning of shuffle ideals with membership queries as well as with contrastive queries---a form of membership query that reveals no
arXiv:2609.32613v1 Announce Type: new Abstract: Graph neural networks lose much of their advantage on heterophilic graphs, where connected nodes often carry different labels. Graph rewiring is a popul
arXiv:2609.35541v1 Announce Type: new Abstract: We propose a distributionally robust learning framework where parameters defining the robustness mechanism are learned from held-out data instead of ext
arXiv:2609.34205v1 Announce Type: new Abstract: Optimization modeling is central to many decision-making scenarios, but traditionally requires extensive domain expertise. While Large Language Models (
arXiv:2609.35539v1 Announce Type: new Abstract: Video segmentation models maintain object identities by carrying instance information across frames. Under prolonged occlusion, reappearance, or interac
arXiv:2609.34677v1 Announce Type: cross Abstract: World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic
arXiv:2506.19065v3 Announce Type: replace Abstract: We propose Legato, a new end-to-end model for optical music recognition (OMR), a task of converting music score images to machine-readable documents
arXiv:2609.32447v1 Announce Type: new Abstract: Learning robust and scalable finite-state tracking is fundamental to sequence processing. While linear recurrent neural networks (RNNs), linear attentio
arXiv:2609.35573v1 Announce Type: new Abstract: Feed-forward novel view synthesis reconstructs a scene from many input images in a single forward pass, yet more views do not necessarily improve perfor
arXiv:2609.35528v1 Announce Type: new Abstract: Rectified linear unit (ReLU) networks can suffer from dying neurons, where units with persistently negative pre-activations produce zero outputs, blocki
arXiv:2609.33663v1 Announce Type: cross Abstract: Discovering underlying symmetries from data has emerged as a crucial challenge in scientific discovery. Existing data-driven methods for symmetry disc
arXiv:2605.06332v2 Announce Type: replace Abstract: Constructive neural routing solvers usually score the next action by matching a decoder context to candidate embeddings, leaving deterministic one-s
arXiv:2609.32854v1 Announce Type: new Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) offer a promising approach for very low power inference due to their us
arXiv:2609.33593v1 Announce Type: new Abstract: Color enhancement of 4K images must meet a quality target under a tight compute budget. Three-dimensional lookup tables (3D LUTs) dominate real-time enh
arXiv:2609.31941v1 Announce Type: new Abstract: This engineering study assesses gaze-assisted data acquisition during visual screening with a Gaze Quest implementation via webcam and GC308 near infrar
arXiv:2609.35700v1 Announce Type: new Abstract: We propose a hierarchical control framework to address severe dynamic instabilities and navigational drift that arise when a two-wheeled inverted pendul
arXiv:2609.34014v1 Announce Type: new Abstract: Short-term turning-movement forecasts can support signal control and corridor operations, but unconstrained neural networks may produce physically impos
arXiv:2609.33028v1 Announce Type: new Abstract: A feed-forward neural network whose weights are integers and whose activation is the truncated identity implements, neuron by neuron, the connectives of
arXiv:2609.31736v1 Announce Type: new Abstract: Acute Lymphoblastic Leukemia (ALL) patients require early, accurate detection to enable timely treatment and effective patient management. A Convolution
arXiv:2609.33769v1 Announce Type: new Abstract: Quantitative evaluation of generative models for radiology remains challenging. Clinically relevant structures are often small and infrequent, feature s
arXiv:2609.33683v1 Announce Type: new Abstract: When should multimodal foundation models generate tokens, and when should they directly output a decision? We present MAD-Guard, a controlled study of o
arXiv:2609.34442v1 Announce Type: new Abstract: While an unlearned language model may no longer recall a fact directly, the fact often remains recoverable through multi-hop reasoning over related know
arXiv:2609.34309v1 Announce Type: new Abstract: Executable programs offer explicit control over how images and videos are constructed, but generating runnable code is only the beginning of visual crea
arXiv:2609.35454v1 Announce Type: new Abstract: Flow matching (FM) learns generative dynamics through velocity regression. Geometric FM variants commonly assume a prior supported on the data manifold,
arXiv:2609.34409v1 Announce Type: new Abstract: Naturally irregular time series combine asynchronous observations, missing values, unequal lengths, and nonuniform sampling, while dense adapters can di
arXiv:2609.33486v1 Announce Type: cross Abstract: Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to
arXiv:2609.31646v1 Announce Type: cross Abstract: Low-cost indoor air-quality sensors could support personalized asthma prevention, but their nonlinear measurement error, delayed exposure effects, tim
arXiv:2609.32889v1 Announce Type: new Abstract: Frozen EEG representations retain acquisition signatures as well as neural activity. Source predictability alone does not identify what should be remove
arXiv:2609.31734v1 Announce Type: new Abstract: The rise of computer vision and artificial intelligence has made possible new forms of large-scale computational measurement. We apply these techniques
arXiv:2609.31992v1 Announce Type: new Abstract: Decoding covert speech, such as mimed or imagined, from brain activity is harder than decoding vocalized speech. Cross-modal transfer, where information
arXiv:2609.32839v1 Announce Type: cross Abstract: Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measure
arXiv:2609.35701v1 Announce Type: new Abstract: The success of large language models (LLMs) has been accompanied by continued growth in model size and pretraining costs. Muon offers high accuracy and
arXiv:2609.34330v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated impressive performance in multimodal understanding, but processing large numbers of visual to
arXiv:2609.35708v1 Announce Type: new Abstract: Reference-guided diffusion editors struggle to faithfully reproduce user-provided references. We identify a potential bottleneck in diffusion editors: m
arXiv:2609.34656v1 Announce Type: new Abstract: We study last-iterate convergence in unknown two-player zero-sum matrix games with bandit payoff feedback and observed opponent actions. For games with
arXiv:2609.35043v1 Announce Type: new Abstract: In open-set recognition (OSR), a probe must either be identified as one of the known gallery classes or rejected as unknown, so three error types coexis
arXiv:2609.31960v1 Announce Type: new Abstract: Time series out-of-distribution generalization requires forecasters to remain reliable when deployment dynamics differ from training conditions due to c
arXiv:2609.34451v1 Announce Type: new Abstract: Due to the gigapixel-scale nature of whole-slide images (WSIs), weakly supervised WSI analysis is commonly formulated as a multiple instance learning (M
arXiv:2609.31700v1 Announce Type: new Abstract: Compressed-domain video captioning avoids full video decoding by operating directly on I-frames, motion vectors and residuals, trading a small amount of
arXiv:2609.33431v1 Announce Type: new Abstract: We release MoGround, a vision-language dataset spanning four visual domains in which the answer to every question is guaranteed to be available from exa
arXiv:2609.34280v1 Announce Type: cross Abstract: Predicting molecular profiles from histopathology remains challenging because whole-slide images contain spatially organized, heterogeneous tissue pat
arXiv:2609.34190v1 Announce Type: new Abstract: Recent advances in diffusion and flow models have substantially improved text-driven human motion generation. Yet most methods generate in low-dimension
arXiv:2609.33790v1 Announce Type: cross Abstract: Conventional reflectance photoplethysmography (PPG) typically reduces tissue optical responses to one or a few detector channels. Matrix Pinhole Image
arXiv:2609.35274v1 Announce Type: new Abstract: Recurrent and equilibrium graph neural networks (GNNs) often enforce a unique fixed point or use one training target per graph. Yet many combinatorial a
arXiv:2609.33138v1 Announce Type: new Abstract: Recovering physical properties of unknown objects through non-prehensile interaction is challenging because no single manipulation primitive reveals all
arXiv:2609.33347v1 Announce Type: new Abstract: World models can be studied as experimental systems with response laws of their own. We introduce MultiEcho, a framework for estimating these laws throu