arXiv:2602.13200v1 Announce Type: new Abstract: The purpose of this paper is to model traffic in Ad Hoc network of Unmanned Aerial Vehicles and demonstrate a way for adapting communication channel using Artificial Intelligence. The modeling was based on the original model of Ad Hoc network including 20 Unmanned Aerial Vehicles. The dependences of packet loss on the packet size for different transmission powers, on the packet size for different frequencies, on Unmanned Aerial Vehicles flight area and on […]

Ver mais

AI video generation has quietly become one of the most powerful creative tools on the internet. What once required a studio, expensive software, and professional editors can now be accomplished with prompts, reference images, and a browser tab. At the center of this shift is DomoAI, a complete AI Video Generator that combines animation, editing, upscaling, and stylization into one seamless workflow. For creators who want speed, flexibility, and visual impact, learning this platform can completely reshape how […]

Ver mais

Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon accounting, yet models must generalize to ecosystems underrepresented in sparse eddy covariance observations. Despite this challenge being a natural instance of zero-shot spatial transfer learning for time series regression, no standardized benchmark exists to rigorously evaluate model performance across geographically distinct locations with different climate regimes and vegetation types. We introduce CarbonBench, the first benchmark for zero-shot spatial transfer in carbon flux upscaling. CarbonBench comprises over […]

Ver mais

Medical time-series data captures the dynamic progression of patient conditions, playing a vital role in modern clinical decision support systems. However, real-world clinical data is highly heterogeneous and inconsistently formatted. Furthermore, existing machine learning tools often have steep learning curves and fragmented workflows. Consequently, a significant gap remains between cutting-edge AI technologies and clinical application. To address this, we introduce mtslearn, an end-to-end integrated toolkit specifically designed for medical time-series data. First, the framework provides a unified data […]

Ver mais

If general intelligence is on the horizon, simply making one model larger won’t get us there. We need to create networks of specialized models that can communicate, debate, and share their knowledge. Here’s a HumanEval test result that keeps coming back to us. Take GPT-3.5 and put it in a simple agent loop where it can call tools, critique itself, and bounce ideas off other instances of itself. It ends up beating GPT-4 run standalone. Run the same […]

Ver mais

arXiv:2506.01502v3 Announce Type: replace-cross Abstract: Learning population dynamics involves recovering the underlying process that governs particle evolution, given evolutionary snapshots of samples at discrete time points. Recent methods frame this as an energy minimization problem in probability space and leverage the celebrated JKO scheme for efficient time discretization. In this work, we introduce $texttt{iJKOnet}$, an approach that combines the JKO framework with inverse optimization techniques to learn population dynamics. Our method relies on a conventional $textit{end-to-end}$ adversarial training […]

Ver mais

arXiv:2606.23691v1 Announce Type: new Abstract: Second order derivatives of model outputs with respect to input parameters are key to several applications in ice sheet modelling. For example, the ability to compute Hessian-vector products broadens the list of available optimisation methods, and facilitates certain kinds of parametric uncertainty quantification. Some modern ice sheet models are built on frameworks supporting algorithmic differentiation (AD), allowing for the computation of higher order derivatives with relative ease. However, many of our most widely-used […]

Ver mais

arXiv:2601.15334v1 Announce Type: new Abstract: Whether language models possess sentience has no empirical answer. But whether they believe themselves to be sentient can, in principle, be tested. We do so by querying several open-weights models about their own consciousness, and then verifying their responses using classifiers trained on internal activations. We draw upon three model families (Qwen, Llama, GPT-OSS) ranging from 0.6 billion to 70 billion parameters, approximately 50 questions about consciousness and subjective experience, and three classification […]

Ver mais

arXiv:2604.09702v1 Announce Type: new Abstract: Precise segmentation of objects with highly similar shapes remains a challenging problem in dense prediction, especially in scenarios with ambiguous boundaries, overlapping instances, and weak inter-instance visual differences. While conventional segmentation models are effective at localizing object regions, they often lack the discriminative capacity required to reliably distinguish a target object from morphologically similar distractors. In this work, we study fine-grained object segmentation from an identity-aware perspective and propose Identity-Aware U-Net (IAU-Net), a […]

Ver mais

arXiv:2602.20216v1 Announce Type: new Abstract: Robot-assisted endovascular intervention offers a safe and effective solution for remote catheter manipulation, reducing radiation exposure while enabling precise navigation. Reinforcement learning (RL) has recently emerged as a promising approach for autonomous catheter steering; however, conventional methods suffer from sparse reward design and reliance on static vascular models, limiting their sample efficiency and generalization to intraoperative variations. To overcome these challenges, this paper introduces a sample-efficient RL framework with online expert correction for […]

Ver mais