The world modelling newswire

Stochastic MPC robust to errors in disturbance statistics

Adaptive clustering for robust distributed MPC of coupled multi-agent systems

Neural approximation of NMPC without expert demonstrations

An operational model for a trusted data space in vocational education

Роман Венедиктов («Эмерджентные мультиагентные системы»): «Сегодня сам факт использования ИИ стал обычной частью корпоративной ИТ-среды»

Совместное предприятие Selectel и ИТМО «Эмерджентные мультиангентные системы» занимается технологиями для создания и эксплуатации мультиагентных систем: не столько созданием ещё одного отдельного ИИ-ассистента, сколько тем, как сделать эксплуатацию большого количества агентов управляемой, надежной…

A High-Fidelity Cardiac Digital Twin for Assessing Rate-Dependent Responses: A Comparative Multi-scale Study of TT2 and Tomek Models in Stratified 3D Ventricles

Cardiac digital twins (CDTs) provide a computational platform for personalized cardiac modeling, but their predictive behavior depends strongly on the selected ionic model and the representation of transmural electrophysiological heterogeneity.

Janus: One Agent, Two Roles for Digital Twin Construction and Network Orchestration

Next-generation wireless networks are increasingly large-scale, heterogeneous, and dynamic, posing significant challenges to network modeling and control. Digital twins offer a promising solution, but existing approaches typically rely on static models and decouple twin construction from network…

Агентная система для тех, кто вкатывается: собираем агента поддержки от одного файла до Temporal, саги и circuit breaker

Тысяча классификаций обращений стоит $0,23 на Claude Haiku 5.5 и $4,50 на Sonnet 5.5. Почти двадцать раз, и это не самое дорогое место в системе, где агент поддержки возвращает клиентам деньги.

Online digital twin: data assimilation and control in a mean-field formulation

Survey of digital twin networks for 6G: architecture, technologies and AI control

Sampling-based MPC unified as a single sequential Monte Carlo algorithm

5G NR neural receiver trained on corridor digital twin data

Neural multipath fields for 6G FR3 digital twins with sparse-data adaptation

OpenIDE и «Астра ИИ Код»: суверенная среда для агентной разработки

«Группа Астра» интегрировала профессиональную среду разработки OpenIDE и агентную систему «Астра ИИ Код». Возможности...

Generative Reconstruction of Full-Field Sensor States for Safety-Critical Digital Twins

arXiv:2611.08499v1 Announce Type: cross Abstract: Accurate reconstruction of incomplete sensor fields is critical for state awareness in safety-critical digital twins (DTs). Thermocouples in high-temperature and radiation environments may drift, fail, or become intermittently unavailable, causing…

Optical Network Digital Twin -- Practical Use Cases and Architecture

arXiv:2511.06368v3 Announce Type: replace Abstract: With the widespread adoption of AI, machine-to-machine communications are rapidly increasing, reshaping the requirements for optical networks.

A Realistic Discrete Event Simulation model for Ambulance Location and Deployment within a regional Emergency Medical Service

arXiv:2604.24394v3 Announce Type: replace Abstract: The objective of Emergency Medical Services (EMSs) is to promptly respond to calls from citizens for first aid, providing pre-hospital care and, if necessary, to transfer patients to an appropriate Emergency Department (ED) by ambulance.

Grid-Oriented Probabilistic Load Forecasting for AI Data Centers

arXiv:2611.08929v1 Announce Type: new Abstract: Probabilistic load forecasts for AI data centers need to represent both uncertainty under changing workloads and temporal dependence to support grid operations.

Real-Time Nonlinear Mixed-Integer Model Predictive Control With Horizon-Tail Relaxations

arXiv:2611.09187v1 Announce Type: cross Abstract: Model predictive control (MPC) of nonlinear systems with discrete decisions leads to mixed-integer nonlinear programs (MINLPs) whose combinatorial complexity often prevents real-time deployment.

Feel My Focus: Gaze-Triggered Digital Twin Creation for Remote Collaboration

We present Feel My Focus, a gaze-triggered mixed reality (MR) demonstration that enables rapid creation and sharing of lightweight 3D digital twins during remote collaboration. Unlike systems that use gaze primarily as a referential pointer, Feel My Focus treats sustained visual attention as a…

Differentiable Agent-Based Modeling for Multi-Echelon Supply Chains: Gradient-Based Optimization of Heterogeneous Policies at Scale

Global supply chains rely on the interactions of thousands of heterogeneous agents, posing significant challenges for optimization. While traditional optimization often assumes homogeneity to ensure tractability, Reinforcement Learning struggles with sample inefficiency when scaling to…

Digital Twins for Clinical Development: A Five-Level Framework from Prognostic Adjustment to In-Silico Trials

Digital twins are increasingly discussed in drug development, often narrowly as virtual control arms or synthetic data. We propose a broader framework for data-driven clinical digital twins, organized into five levels according to how much of the trial data matrix of baseline covariates, treatment…

Differentiable Digital Twins for Quantum Computer Optimization

A software toolset models atomic quantum systems and simulates qubit gate dynamics. Automatic differentiation combined with quantum optimal control and benchmarking enables gradient-based optimization to improve gate fidelity limited by noise and hardware imperfections.

Patient Digital Twin Updates Forecasts Without Retraining

ICare-DT, a Transformer-based twin, updates a latent patient state hourly from new measurements without retraining. Trained on 140,473 eICU-CRD stays, its later forecasts beat earlier ones in all 12 settings, with gains confirmed on a second database and traced to the patient's own measurements.