Knowledge catalogue
arXiv:2609.33131v1 Announce Type: new Abstract: Black-box Optimization (BO) is a powerful framework for optimizing expensive objective functions or unknown functions with a limited number of evaluatio
arXiv:2609.35726v1 Announce Type: new Abstract: Automated quality assessment of rehabilitation exercises relies heavily on accurate human pose estimation from video data. Although numerous RGB-based p
arXiv:2609.33038v1 Announce Type: cross Abstract: We propose DAST (Diversifying Arithmetic Sampling with TokenTour), a method that increases the diversity of LLM outputs without any change to the marg
arXiv:2609.32882v1 Announce Type: new Abstract: We present VSA2, a frontier trainable sparse attention for video DiTs. VSA2 includes a variety of new architectural features and training procedures tha
arXiv:2609.34798v1 Announce Type: cross Abstract: Recent medical multimodal models have benefited from larger corpora, broader modality coverage, and stronger reasoning-oriented training, yet effectiv
arXiv:2609.35743v1 Announce Type: new Abstract: World-space hand motion estimation from egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing appr
arXiv:2609.34731v1 Announce Type: cross Abstract: We develop an information-theoretic framework for generalization in next-token prediction under temporally dependent data. We consider independent tra
arXiv:2609.35516v1 Announce Type: new Abstract: Inspection planning seeks a minimum-length collision-free robot tour that observes a given set of points of interest (POIs). Sampling-based methods redu
arXiv:2609.34976v1 Announce Type: cross Abstract: The integration of artificial intelligence into computer-aided design frameworks has sparked a shift in the design of analog integrated circuits (ICs)
arXiv:2602.04952v2 Announce Type: replace-cross Abstract: We study the sample complexity of shadow tomography in the high-precision regime under realistic measurement constraints. Given an unknown d-d
arXiv:2609.31701v1 Announce Type: new Abstract: A Hybrid Residual Attention Network is proposed for accurately classifying silkworm images into six different classes, including healthy and diseased st
arXiv:2609.31997v1 Announce Type: new Abstract: Decoding imagined speech is an important goal for brain-computer interfaces but remains challenging due to weak neural responses, low signal-to-noise ra
arXiv:2603.14528v2 Announce Type: replace Abstract: In recent years, 3D visual foundation models, pioneered by pointmap-based approaches such as DUSt3R, have attracted a lot of interest, achieving imp
arXiv:2609.32539v1 Announce Type: cross Abstract: Deep learning models can achieve high accuracy for indoor localization, but their black-box nature limits interpretability and the reuse of learned in
arXiv:2609.35073v1 Announce Type: new Abstract: Graph visualization methods and agglomerative clustering have been frequently considered in data analysis and pattern recognition. Because these approac
arXiv:2609.34931v1 Announce Type: cross Abstract: Machine learning has made strong progress on music tasks, both as assistive tools and as creative partners. However, most systems train on multitrack
arXiv:2609.33906v1 Announce Type: cross Abstract: Generative models often suffer from mode collapse and limited sample diversity. While prior works attempt to mitigate this by jointly generating a bat
arXiv:2609.34381v1 Announce Type: new Abstract: Video and audio are perceived together, yet most generative models treat them in isolation. We examine methods that model the two modalities jointly, ge
arXiv:2609.34972v1 Announce Type: new Abstract: Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing
arXiv:2609.32182v1 Announce Type: new Abstract: Vision-language models are increasingly used to understand long videos and continuous streams. However, dense visual tokens accumulate with video durati
arXiv:2609.31888v1 Announce Type: cross Abstract: X-ray diffraction (XRD) is a experimental technique for determining the phase composition and structure of crystalline materials. However, interpretin
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:2609.33659v1 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