arXiv:2607.14304v1 Announce Type: new Abstract: We study sparse random geometric graphs generated by connecting pairs of high-dimensional vectors whose inner product exceeds a threshold. The latent…
arXiv:2607.15018v1 Announce Type: new Abstract: High-dimensional categorical data arise in genetics, biomedicine, and the social sciences, yet visualization tools for such data remain far less developed…
arXiv:2607.13891v1 Announce Type: cross Abstract: Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based on Poisson…
arXiv:2607.15196v1 Announce Type: new Abstract: We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead…
arXiv:2604.25202v2 Announce Type: replace-cross Abstract: Lower and upper errors of a two-sided conformal prediction interval can have different scientific consequences. The division of target miscoverage between…
arXiv:2105.07610v5 Announce Type: replace Abstract: Building trustworthy machine learning algorithms for biological applications requires adapting to data heterogeneity from different sources, batches, distributions, or studies. We…
arXiv:2607.15208v1 Announce Type: cross Abstract: Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally…
arXiv:2511.14441v2 Announce Type: replace Abstract: To distinguish Markov equivalent graphs in causal discovery, it is necessary to restrict the structural causal model. Crucially, we need to…
arXiv:2607.14278v1 Announce Type: new Abstract: The paper develops the approach to the runtime analysis of evolutionary algorithms on the basis of limit theorems from probability theory.…
arXiv:2607.14630v1 Announce Type: new Abstract: Layer-wise post-training quantization of large language models minimizes each layer's reconstruction error in isolation, allowing quantization errors to accumulate across depth…
arXiv:2607.14936v1 Announce Type: new Abstract: Real-world optimization problems often involve black-box functions and uncertainties in their evaluation, widely referred to as noisy optimization problems (NOPs). Evolutionary…
arXiv:2607.15217v1 Announce Type: new Abstract: We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of…
arXiv:2607.14520v1 Announce Type: cross Abstract: Nonlinear thermodynamic computers based on Langevin dynamics exploit thermal fluctuations as a physical substrate for computation. Recent work has shown that…
arXiv:2607.15003v1 Announce Type: cross Abstract: The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.e., policies) that are not only performant but…
arXiv:2607.14747v1 Announce Type: cross Abstract: Cardiovascular diseases are the leading cause of death worldwide, and conditions such as arrhythmia often require long-term monitoring for effective detection…
arXiv:2604.27031v2 Announce Type: replace-cross Abstract: In a continual learning setting, we require a model to be plastic enough to learn a new task and stable enough…
arXiv:2601.07944v2 Announce Type: replace-cross Abstract: Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle…
arXiv:2607.14200v1 Announce Type: new Abstract: Imitation learning is an appealing way to scale game-playing agents to complex 3D environments by training policies to map visual observations…
arXiv:2607.14192v1 Announce Type: new Abstract: As recommender systems mature in the past few years, their optimization objectives have evolved from a primary focusing on short-term behavioral…
arXiv:2607.14191v1 Announce Type: new Abstract: Pediatric electronic health records capture developmentally structured clinical trajectories, yet their potential for generative healthcare foundation models remains largely unexplored. Here…
arXiv:2508.00923v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to answer health-related questions and support healthcare workflows, yet evidence for their safety still…
arXiv:2607.14190v1 Announce Type: new Abstract: Amyotrophic lateral sclerosis (ALS) is a progressive and heterogeneous neurodegenerative disease in which predicting clinically meaningful milestones, such as assistive device…
arXiv:2607.15200v1 Announce Type: cross Abstract: Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs)…
arXiv:2607.14185v1 Announce Type: new Abstract: Feedback-driven loops support iterative improvement in large language models, reinforcement learning, and autonomous discovery, yet their gains often diminish under repeated…