Knowledge catalogue
arXiv:2610.05780v1 Announce Type: cross Abstract: High-dimensional Bayesian optimization (BO) often fits Gaussian process (GP) surrogates from far fewer observations than input dimensions. Modern Vani
arXiv:2610.04396v1 Announce Type: cross Abstract: Split Computing (SC) enables efficient deployment of Deep Neural Networks (DNNs) by partitioning inference between edge devices and cloud servers. How
arXiv:2610.05967v1 Announce Type: new Abstract: Image compression, restoration, and generation all require a way to measure how different two images look to a person. Pixel error ignores how people se
arXiv:2610.06234v1 Announce Type: new Abstract: Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classifi
arXiv:2610.05549v1 Announce Type: new Abstract: We formulate joint estimation of common-slope decay rates and amplitudes from room impulse responses (RIRs) as parameterized nonnegative matrix factoriz
arXiv:2610.06023v1 Announce Type: new Abstract: Exploiting meaningful latent structures from data to solve downstream tasks is a fundamental challenge in signal processing and machine learning. While
arXiv:2610.04786v1 Announce Type: cross Abstract: Time-series foundation models buy zero-shot forecasting with large temporal corpora; a vision model needs none, since a natural image implicitly embed
arXiv:2610.05608v1 Announce Type: new Abstract: We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video
arXiv:2610.06588v1 Announce Type: new Abstract: Long-horizon camera-controlled video generation relies on persistent memory to maintain scene consistency. Existing systems follow two strategies to ach
arXiv:2610.04152v1 Announce Type: new Abstract: Video world models aim to preserve scene structure and predict how dynamic objects evolve beyond visual observations. We present Kepler4D, a framework f
arXiv:2610.06434v1 Announce Type: cross Abstract: Predicting patient-specific survival functions is crucial for clinicians in making informed decisions about patient care and treatment strategies. Amo
arXiv:2610.05306v1 Announce Type: new Abstract: Sign language-text alignment remains a fundamental challenge for text-driven sign language understanding. Existing methods predominantly rely on appeara
arXiv:2610.06349v1 Announce Type: new Abstract: Embodied world models predict the visual consequences of candidate actions before execution. However, existing action-conditioned world models often ado
arXiv:2505.17919v2 Announce Type: replace Abstract: Residual connections are foundational to modern neural networks, yet the standard additive update provides no explicit mechanism for structured inte
arXiv:2610.04721v1 Announce Type: new Abstract: Structural diagrams are widely used to represent complex systems and relational information across scientific, engineering, procedural, and spatial doma
arXiv:2610.05250v1 Announce Type: new Abstract: Kolmogorov--Arnold Networks (KANs) have attracted increasing attention in recent years, with applications across a wide range of AI tasks. In this paper
arXiv:2610.03842v1 Announce Type: new Abstract: Knowledge distillation is crucial for deploying vision-language models on resource-constrained devices. However, existing methods typically impose unifo
arXiv:2610.04544v1 Announce Type: cross Abstract: Many groups now delegate label ontology and metadata harmonization to agentic LLM pipelines. We built one and audited it. Our aggregate scores looked
arXiv:2610.05987v1 Announce Type: new Abstract: Computational pathology has the potential to improve clinical outcomes through a demonstrated increase in diagnostic and prognostic accuracy. However, t
arXiv:2610.05998v1 Announce Type: new Abstract: Molecular dynamics simulations proceed by integrating the Langevin equations over many small femtosecond timesteps. This poses a challenge for estimatin
arXiv:2610.04183v1 Announce Type: cross Abstract: Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like lin
arXiv:2610.05915v1 Announce Type: new Abstract: This paper revisits the distributed learning problem for training a multinomial logistic regression model with the Federated Averaging (exttt{FedAvg}) a
arXiv:2610.04385v1 Announce Type: cross Abstract: Many decision trees fit the same data almost equally well, yet they can route a query point to different leaves and induce different local empirical d
arXiv:2610.06070v1 Announce Type: cross Abstract: Normalized gradient descent is a widely studied adaptive optimization method. Most existing analyses focus on the best iterate or a weighted average o
arXiv:2610.06468v1 Announce Type: new Abstract: Modern graph generative models typically operate directly in the discrete graph space, explicitly generating node and edge variables, which can become c
arXiv:2610.04723v1 Announce Type: cross Abstract: This work proposes a latent Lagrangian-based framework for reduced-order modelling of forced nonlinear dynamical systems. In contrast with conventiona
arXiv:2610.04297v1 Announce Type: cross Abstract: Latent safety filters certify safety on a learned low-dimensional representation of the state, enabling constraints that resist analytic description.
arXiv:2610.03956v1 Announce Type: cross Abstract: We propose a data-driven framework for estimating the Bayesian Cramer-Rao bound (CRB) in high-dimensional imaging systems with complex, analytically i
arXiv:2610.06355v1 Announce Type: cross Abstract: Forecasting suicide risk is difficult due to the high heterogeneity of patients and the low base rate of suicide-related events (SREs). We present Lat
arXiv:2610.04034v1 Announce Type: new Abstract: Data assimilation combines model forecasts with noisy, incomplete observations to estimate the evolving state of a dynamical system. Existing methods fa
arXiv:2610.05349v1 Announce Type: new Abstract: We introduce CNP-Flow, a flow matching framework for temporal generation that learns conditional source distributions through flow reversal. Whereas sta
arXiv:2610.05677v1 Announce Type: new Abstract: Multi-robot imitation learning, particularly in settings where visuomotor policies are deployed in a communication-free, onboard decentralised style, re
arXiv:2610.04703v1 Announce Type: cross Abstract: Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation. However,
arXiv:2510.19138v2 Announce Type: replace Abstract: Granger causality characterizes directed predictive dependencies in multivariate time series, but recovering such dependencies becomes challenging i
arXiv:2610.05428v1 Announce Type: cross Abstract: We study learning in continuous games when players receive only pairwise preference feedback, revealing which of two actions is preferred but neither
arXiv:2505.23615v2 Announce Type: replace Abstract: Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be
arXiv:2508.17512v2 Announce Type: replace Abstract: Differentiable logic networks (DLNs) have shown promising results in tabular domains by combining accuracy, interpretability, and computational effi
arXiv:2610.03978v1 Announce Type: new Abstract: Autoregressive transformers remain comparatively weak for protein sequence and structure generation. We study the role of target representation: amino a
arXiv:2610.06397v1 Announce Type: new Abstract: We propose MOSEL (Multi-Objective Stackelberg Efficient Learning), a framework for a posteriori multi-objective optimization (MOO) in deep neural networ
arXiv:2610.04028v1 Announce Type: new Abstract: Clinical MRI routinely acquires multiple contrast-weighted images of the same anatomy for complementary tissue characterization. However, current accele
arXiv:2610.04771v1 Announce Type: cross Abstract: Long-horizon mobile manipulation requires a task plan and the motion that executes it. Generative planners trained on demonstration produce both in on
arXiv:2606.14222v2 Announce Type: replace Abstract: The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form
arXiv:2610.05879v1 Announce Type: cross Abstract: We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic
arXiv:2610.06844v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the
arXiv:2606.14737v2 Announce Type: replace-cross Abstract: Modern protein representation models support tasks such as enzyme design and drug discovery, but their reliance on static data such as sequenc
arXiv:2610.04936v1 Announce Type: new Abstract: Class-imbalance methods implicitly assume that the minority class is uniformly undersampled relative to the majority class. However, in many real-world
arXiv:2610.06671v1 Announce Type: new Abstract: Small language models are often post-trained as students on reasoning traces from stronger teacher models to efficiently learn new skills. However, toke
arXiv:2610.06006v1 Announce Type: new Abstract: We study contextual queueing bandits, where a learner schedules jobs while learning unknown service rates modeled by logistic functions of job-server fe
arXiv:2610.05200v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) of large language models (LLMs) has demonstrated the ability to improve reasoning capabilities while preserving previ
arXiv:2510.18643v3 Announce Type: replace Abstract: Control Barrier Functions (CBFs) can provide provable safety guarantees for dynamic systems. However, finding a valid CBF for a system of interest i
arXiv:2610.03812v1 Announce Type: cross Abstract: A time-series forecast is scored on a future value of the series. A representation loss that regresses the next latent, as in LeNEPA, is a different l
arXiv:2610.06226v1 Announce Type: cross Abstract: Prior audio-visual self-supervised learning methods rely on mechanisms such as EMA target encoders, prediction heads, reconstruction decoders, and con
arXiv:2610.05564v1 Announce Type: cross Abstract: Text embedding models trained with contrastive learning learn to follow task instructions from instruction-paired data, while instruction-tuned LLMs a
arXiv:2610.04518v1 Announce Type: new Abstract: Length generalization is the ability of sequential models to perform well on context lengths unseen during training. In this work, we show that the chal
arXiv:2610.06611v1 Announce Type: new Abstract: Existing 3D large language models often overlook fine-grained attributes and less visually salient objects and parts, even when relevant evidence is pre
arXiv:2610.05497v1 Announce Type: new Abstract: Geographic information systems increasingly rely on sophisticated spatial representation learning techniques to extract meaningful patterns from complex
arXiv:2610.06813v1 Announce Type: new Abstract: Recent progress in 3D foundation models has enabled rapid 3D reconstruction and camera calibration by leveraging learned 3D priors from vast amount of s
arXiv:2610.05816v1 Announce Type: new Abstract: Image and video diffusion models allocate equal computation to every region, even when the intended scene calls for varying levels of detail. The spatia
arXiv:2610.04565v1 Announce Type: new Abstract: Engaging K-12 students in authentic scientific research remains a significant challenge, particularly at the intersection of environmental science and r
arXiv:2610.04744v1 Announce Type: new Abstract: When a team of robots delegates planning and mutual trust to LLM agents, a single compromised robot can corrupt the shared outcome. We study this threat