| Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment 7 de agosto de 2026 | Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under… | Aerospace Engineering | UAV Applications and Optimization |
| Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning 7 de agosto de 2026 | Goal-conditioned reinforcement learning (GCRL) offers a unified way to pursue diverse tasks, yet most existing methods rely on state- or position-based goal representations that… | Building and Construction | Smart Parking Systems Research |
| CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis 7 de agosto de 2026 | This study proposes the Cognitive Pairwise Comparison Classification Model Selection (CPC-CMS) framework for document-level sentiment analysis. The CPC, based on expert knowledge… | IA | Sentiment Analysis and Opinion Mining |
| A Reverse-BSDE Diffusion Sampler 7 de agosto de 2026 | Diffusion-based generative models have renewed interest in stochastic differential equation methods for sampling from complex distributions. We study a setting in which the target… | Visión | Generative Adversarial Networks and Image Synthesis |
| Latent Utility Q-Learning for Preference-Adaptive Dynamic Treatment Regimes 7 de agosto de 2026 | Optimizing individualized treatment sequences for patients who weigh multiple, competing outcomes differently poses a challenge for dynamic treatment regime (DTR) methods, which… | Economics and Econometrics | Health Systems, Economic Evaluations, Quality of Life |
| Optimal or Greedy Decision Trees? Revisiting their Objectives, Tuning, and Performance 7 de agosto de 2026 | Recently there has been a surge of interest in optimal decision tree (ODT) methods that globally optimize accuracy directly, in contrast to traditional approaches that locally… | Sist. de info. | Data Mining Algorithms and Applications |
| Scalable estimation of VARMA models 7 de agosto de 2026 | Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is… | IA | Bayesian Methods and Mixture Models |
| Optimal Rates for Learning with Monotone Adversaries 7 de agosto de 2026 | A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis.… | IA | Machine Learning and Algorithms |
| Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning 7 de agosto de 2026 | Persistence diagrams (PDs) provide stable and interpretable summaries of multiscale topological structure. While substantial progress has been made in the statistical analysis of… | Computational Theory and Mathematics | Topological and Geometric Data Analysis |
| OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations 7 de agosto de 2026 | The development of deep learning over the past decade has revolutionized medical imaging segmentation, allowing the extraction of precise descriptors from large volumes to… | Visión | Medical Image Segmentation Techniques |
| Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification 7 de agosto de 2026 | In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent (GD) on the logistic… | IA | Stochastic Gradient Optimization Techniques |
| Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation 7 de agosto de 2026 | Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dynamics, reducing reliance on… | Control and Systems Engineering | Robot Manipulation and Learning |
| Muon on the Stiefel Manifold Admits an Exact Closed-Form Update 7 de agosto de 2026 | We study Muon, a recently proposed matrix-aware optimization method, in the context of the Stiefel manifold. This manifold consists of matrices with orthonormal columns and is… | Mechanics of Materials | Muon and positron interactions and applications |
| Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction 7 de agosto de 2026 | Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific… | Statistics and Probability | Statistical Methods and Inference |
| Handling Missing Data in Probabilistic Regression Trees 7 de agosto de 2026 | Probabilistic Regression Trees (PRTrees) are a smooth and consistent alternative to classical regression trees, producing continuous predictions through probabilistic split… | Control and Systems Engineering | Fault Detection and Control Systems |
| On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities 7 de agosto de 2026 | We study stochastic extragradient (SEG) methods for solving monotone variational inequality problems (VIPs) over a feasible set. Although extragradient is a foundational algorithm… | Computational Theory and Mathematics | Optimization and Variational Analysis |
| Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators 7 de agosto de 2026 | Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and machine learning, appearing in… | Mathematical Physics | Numerical methods in inverse problems |
| ML-for-ML 7 de agosto de 2026 | AI training workloads are growing rapidly, making their time, energy, and infrastructure costs increasingly important. In shared cloud clusters, training and fine-tuning jobs… | Redes | Software-Defined Networks and 5G |
| Operating Multi-Node Full Fine-Tuning on NVIDIA B300: A Field Report on Telemetry-Based Triage, Negative Results, and Operational Hardening 7 de agosto de 2026 | We report operational experience full-fine-tuning a 32.76B-parameter dense model (Qwen3-32B) on 16 x NVIDIA B300 (two nodes, FSDP / ZeRO-3) -- among the first published field… | Hardware and Architecture | Parallel Computing and Optimization Techniques |
| MirrorNet: Can Medical Image Anonymization Really Protect Patient Identity? 7 de agosto de 2026 | Medical images are routinely de-identified---names, dates, and other metadata removed---and then shared for research, teaching, and public benchmarks under the assumption that… | Biomedical Engineering | Medical Imaging and Analysis |
| Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data 7 de agosto de 2026 | The experience sampling method (ESM) is a longitudinal research design where participants report their thoughts, emotional states and behaviours multiple times a day. Our work is… | IA | Bayesian Methods and Mixture Models |
| A neural operator view on U-Nets for inverse imaging problems 7 de agosto de 2026 | Deep neural networks have shown great empirical success in the solution of a wide variety of ill-posed inverse problems in imaging. Yet, very few works have studied their behavior… | Radiology, Nuclear Medicine and Imaging | Medical Imaging Techniques and Applications |
| On-Policy Delta Distillation for Multilingual Math Reasoning 7 de agosto de 2026 | On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains… | IA | Natural Language Processing Techniques |
| KVAE: Family of Tokenizers for Multimodal Generative Models 7 de agosto de 2026 | Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral… | Visión | Generative Adversarial Networks and Image Synthesis |
| VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation 7 de agosto de 2026 | Wearable human activity recognition (HAR) is often limited by the scarcity of labeled sensor data, especially in low-resource, class-imbalanced, and subject-generalization… | Visión | Context-Aware Activity Recognition Systems |
| SR-JEPA: Learning Predictive Latent State in 3D Scenes 7 de agosto de 2026 | Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders… | Computational Mechanics | 3D Shape Modeling and Analysis |
| Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams 7 de agosto de 2026 | Reference-based event-to-video reconstruction aims to recover target RGB frames from a reference frame and the event stream captured over the reference-to-target interval.… | Visión | Human Pose and Action Recognition |
| LILAC: An Idempotent Neural Speech Codec 7 de agosto de 2026 | Neural Audio Codecs are widely adopted in speech generation and editing. However, existing neural audio codecs are not idempotent: across the paper's twelve baseline systems,… | IA | Speech Recognition and Synthesis |
| Sparse Mutual Information Graph Averaging for Improving Random Indexing Embeddings 7 de agosto de 2026 | Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on sparse global corpus… | Visión | Graph Theory and Algorithms |
| A Low-Power Wearable Respiratory Sensor for Non-Invasive Stress Monitoring 7 de agosto de 2026 | Respiration provides a continuously available window into physiological state and behavior. However, monitoring it outside controlled settings remains challenging because a… | Biomedical Engineering | Non-Invasive Vital Sign Monitoring |
