arXiv:2602.06053v1 Announce Type: new Abstract: Recent advances in duplex speech models have enabled natural, low-latency speech-to-speech interactions. However, existing models are restricted to a fixed role and voice, limiting their ability to support structured, role-driven real-world applications and personalized interactions. In this work, we introduce PersonaPlex, a duplex conversational speech model that incorporates hybrid system prompts, combining role conditioning with text prompts and voice cloning with speech samples. PersonaPlex is trained on a large-scale synthetic dataset of paired […]

Ver mais

arXiv:2601.14501v1 Announce Type: new Abstract: Quadratic unconstrained binary optimization (QUBO) is a field of operations research that is attracting growing interest due to the recent availability of quantum hardware targeted at solving QUBO problems. However, practical adoption is hindered by mathematical intricacy, hardware constraints, and a lack of sound software engineering processes for QUBO development. This work presents AQUA (Agile QUantum Annealing), an agile lifecycle for QUBO/QA development created through an industry-academia partnership between NetService S.p.A and the […]

Ver mais

arXiv:2602.09181v1 Announce Type: new Abstract: Exploiting the analogy between Gaussian Distributions and Gaussian Processes’ posterior, we present how the weighted Wasserstein Barycenter of Gaussian Processes (W2BGP) can be used to unify, under a common framework, different exotic Bayesian Optimization (BO) tasks. Specifically, collaborative/federated BO, (synchronous) batch BO, and multi-fidelity BO are considered in this paper. Our empirical analysis proves that each one of these tasks requires just an appropriate weighting schema for the W2BGP, while the entire framework […]

Ver mais

The primary focus of multi-agent reinforcement learning (MARL) has been to study interactions among a fixed number of agents embedded in an environment. However, in the real world, the number of agents is neither fixed nor known a priori. Moreover, an agent can decide to create other agents (for example, a cell may divide, or a company may spin off a division). In this paper, we propose a framework that allows agents to create other agents; we call […]

Ver mais

In this quiz, you’ll test your understanding of Python SQL Libraries. Work through this quiz to connect to databases with Python, interact with SQLite, MySQL, and PostgreSQL, run SQL queries, and write scripts that work across databases. Reinforce your practical skills for building Python apps backed by databases. [ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn […]

Ver mais

Reconfigurable Intelligent Surfaces promise to transform wireless environments, yet practical deployment is hindered by the prohibitive overhead of Channel State Information (CSI) estimation and the dimensionality explosion inherent in centralized optimization. This paper proposes a Hierarchical Multi-Agent Reinforcement Learning (HMARL) framework for the control of mechanically reconfigurable reflective surfaces in millimeter-wave (mmWave) systems. We introduce a "CSI-free" paradigm that substitutes pilot-based channel estimation with readily available user localization data. To manage the massive combinatorial action space, the proposed […]

Ver mais

arXiv:2601.03397v1 Announce Type: new Abstract: We present PIVONet (Physically-Informed Variational ODE Neural Network), a unified framework that integrates Neural Ordinary Differential Equations (Neuro-ODEs) with Continuous Normalizing Flows (CNFs) for stochastic fluid simulation and visualization. First, we demonstrate that a physically informed model, parameterized by CNF parameters {theta}, can be trained offline to yield an efficient surrogate simulator for a specific fluid system, eliminating the need to simulate the full dynamics explicitly. Second, by introducing a variational model with […]

Ver mais

In this code I have used pytorch & math to make all the blocks of the transformer as a seperate class and then calling them into the original transformer class . I have used all the parameters as suggested in the original paper , encoding size 512, 6 layers and 8 multi head layers. My question- Is there any better way to optimize this before I train this Also what dataset is good for T4 gpu (google colab) […]

Ver mais