arXiv:2601.16323v1 Announce Type: new Abstract: Immersive applications such as eXtended Reality (XR), cloud gaming, and real-time video streaming are central to the vision of 6G networks. These applications require not only low latency and high data rates, but also consistent and high-quality User Experience (UX). Traditional rate allocation and congestion control mechanisms in wireless networks treat users uniformly based on channel conditions, rely only on network-centric Key Performance Indicators (KPIs), and ignore the content diversity, which can lead […]

Ver mais

arXiv:2601.09873v1 Announce Type: new Abstract: Code smells are symptoms of potential code quality problems that may affect software maintainability, thus increasing development costs and impacting software reliability. Large language models (LLMs) have shown remarkable capabilities for supporting various software engineering activities, but their use for detecting code smells remains underexplored. However, unlike the rigid rules of static analysis tools, LLMs can support flexible and adaptable detection strategies tailored to the unique properties of code smells. This paper evaluates […]

Ver mais

arXiv:2601.09725v1 Announce Type: new Abstract: Punctuation plays a critical role in resolving semantic and structural ambiguity in written language. Machine Translation (MT) systems are now widely applied across diverse domains and languages, including many low-resource settings. In this work, we focus on Marathi, a low- to middle-resource language. We introduce Vir=am, the first diagnostic benchmark for assessing punctuation robustness in English-to-Marathi machine translation, consisting of 54 manually curated, punctuation-ambiguous instances. We evaluate two primary strategies for enhancing reliability: […]

Ver mais

Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-quality trajectories, especially under limited resources. Existing methods typically scale up rollout sizes and indiscriminately allocate computational resources among intermediate steps. Such attempts inherently waste substantial computation budget on trivial steps while failing to guarantee sample quality. To address this, we propose textbf{Spark} (textbf{S}trategic textbf{P}olicy-textbf{A}ware explotextbf{R}ation via textbf{K}ey-state dynamic branching), a novel framework […]

Ver mais

There is a dirty secret in product management. Most features that get shipped do nothing. Absolutely nothing. These features might sound great, sound fancy, and get a lot of praise internally. But when it comes to impacting the business, they do F all. They do nothing, not because they aren’t designed well, but because they don’t drive your business model in any meaningful way. The only way to impact your business is to have sustained focus on the […]

Ver mais

arXiv:2604.18816v1 Announce Type: new Abstract: Principal Component Analysis (PCA) is a fundamental tool for representation learning, but its global linear formulation fails to capture the structure of data supported on curved manifolds. In contrast, manifold learning methods model nonlinearity but often sacrifice the spectral structure and stability of PCA. We propose emph{Geodesic Tangent Space Aggregation PCA (GTSA-PCA)}, a geometric extension of PCA that integrates curvature awareness and geodesic consistency within a unified spectral framework. Our approach replaces the […]

Ver mais

Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise in enabling stable advantage estimation without reliance on process-level annotations. However, these methods rely on advantage gaps induced by high-quality samples within the same batch, which makes the training process fragile and inefficient when intra-group advantages collapse under challenging tasks. To address these problems, we propose a reinforcement learning mechanism named emph{textbf{R^3}} that along […]

Ver mais

arXiv:2510.04970v2 Announce Type: replace Abstract: We present FLOP (Fast Learning of Order and Parents), a score-based causal discovery algorithm for linear models. It pairs fast parent selection with iterative Cholesky-based score updates, cutting run-times over prior algorithms. This makes it feasible to fully embrace discrete search, enabling iterated local search with principled order initialization to find graphs with scores at or close to the global optimum. The resulting structures are highly accurate across benchmarks, with near-perfect recovery in […]

Ver mais

arXiv:2509.13805v3 Announce Type: replace-cross Abstract: Foundation models have revolutionized natural language processing through a “train once, deploy anywhere” paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be transformative – democratizing access to high-fidelity simulations, accelerating scientific discovery, and eliminating the need for specialized solver development. Yet current physics-aware machine learning approaches remain fundamentally limited to single, narrow domains and require retraining for each new system. […]

Ver mais

Introduction Disclaimer: This article is a cross post from Pytorch Medium Blog Post. One of the most exciting advancements, that has pushed the frontier of the Artificial Intelligence (AI) in recent years, is Deep Reinforcement Learning (DRL). DRL belongs to the family of machine learning algorithms. It assumes that intelligent machines can learn from their actions similar to the way humans learn from experience. Over the recent years we could witness some impressive real-world applications of DRL. The […]

Ver mais