arXiv:2601.10722v1 Announce Type: new Abstract: The Robot Operating System 2 (ROS~2) has emerged as a relevant middleware framework for robotic applications, offering modularity, distributed execution, and communication. In the last six years, ROS~2 has drawn increasing attention from the real-time systems community and industry. This survey presents a comprehensive overview of research efforts that analyze, enhance, and extend ROS~2 to support real-time execution. We first provide a detailed description of the internal scheduling mechanisms of ROS~2 and its […]

Ver mais

arXiv:2510.02291v2 Announce Type: replace-cross Abstract: While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, finer control, and principled training-free guidance, making it well-suited for posterior sampling. Existing approaches to posterior sampling using discrete diffusion face severe challenges: derivative-free guidance yields sparse signals, continuous relaxations limit applicability, and split Gibbs samplers suffer from the curse of dimensionality. To overcome these limitations, […]

Ver mais

TorchMetrics is a really nice and convenient library that lets us compute the performance of models in an iterative fashion. It’s designed with PyTorch (and PyTorch Lightning) in mind, but it is a general-purpose library compatible with other libraries and workflows. This iterative computation is useful if we want to track a model during iterative training or evaluation on minibatches (and optionally across on multiple GPUs). In deep learning, that’s essentially *all the time*. However, when using TorchMetrics, […]

Ver mais

The volume of scientific submissions continues to climb, outpacing the capacity of qualified human referees and stretching editorial timelines. At the same time, modern large language models (LLMs) offer impressive capabilities in summarization, fact checking, and literature triage, making the integration of AI into peer review increasingly attractive—and, in practice, unavoidable. Yet early deployments and informal adoption have exposed acute failure modes. Recent incidents have revealed that hidden prompt injections embedded in manuscripts can steer AI-generated reviews toward […]

Ver mais

arXiv:2601.12023v1 Announce Type: new Abstract: Semi-implicit variational inference (SIVI) enhances the expressiveness of variational families through hierarchical semi-implicit distributions, but the intractability of their densities makes standard ELBO-based optimization biased. Recent score-matching approaches to SIVI (SIVI-SM) address this issue via a minimax formulation, at the expense of an additional lower-level optimization problem. In this paper, we propose kernel semi-implicit variational inference (KSIVI), a principled and tractable alternative that eliminates the lower-level optimization by leveraging kernel methods. We show […]

Ver mais

The widespread deployment of autonomous driving systems critically depends on guaranteeing safety, especially in complex, dynamic environments. Traditional reactive approaches often fall short in highly uncertain or rapidly evolving situations, leaving minimal margins for error and lacking transparency. To address these limitations, we propose textit{Proactive-Scene}, a novel framework that transitions autonomous driving from passive reaction to active prevention, providing both safety and transparency. Our framework comprises two core components: the Multi-Agent Risk Prediction Network (MARP-Net), which leverages Graph […]

Ver mais

In this edition of our Haskell in Production series, we feature NoRedInk – an EdTech product that helps students become better writers through its online, adaptive writing curriculum. The questions in the article were answered collaboratively by four representatives of NoRedInk – Blake Thomas, Christoph Hermann, Richard Feldmann, and Juliano Solanho. Read further to learn more about how they use Haskell at NoRedInk, why they decided to adopt it, and what is their approach to trying out new […]

Ver mais

Keey Highlights: Earlier this month, OpenAI shared some shocking data claiming that nearly 40 million people are using ChatGPT to get their health queries answered daily. So, it’s quite clear that people are not just using AI for boosting their productivity or as a creativity tool. Healthcare was always the next frontier. After OpenAI launched ChatGPT Health, Anthropic followed the move and made a similar announcement. A few days back, the company announced Claude for Healthcare. The company […]

Ver mais

Hi everyone, I’m a Senior Machine Learning Engineer planning a focused transition into Reinforcement Learning research over the next 12–18 months, and I’d really value advice from people who’ve done this alongside full-time work. Background (brief): • B.Tech + M.Tech (strong math/PDEs) • ~2+ years in ML/DS (forecasting, optimization, CNNs) • Currently building LLM-based agents & multi-agent systems in fintech (orchestration, tools, OpenAI/Anthropic, knowledge graphs),via AI automation I’m comfortable with Python, PyTorch, probability, linear algebra, and optimization. Why […]

Ver mais