arXiv:2601.10850v1 Announce Type: new Abstract: Context: Self-admitted technical debt (SATD) occurs when developers acknowledge shortcuts in code. In scientific software (SSW), such debt poses unique risks to the validity and reproducibility of results. Objective: This study aims to identify, categorize, and evaluate scientific debt, a specialized form of SATD in SSW, and assess the extent to which traditional SATD categories capture these domain-specific issues. Method: We conduct a multi-artifact analysis across code comments, commit messages, pull requests, and […]

Ver mais

arXiv:2601.12518v1 Announce Type: cross Abstract: Cooperative MARL often assumes frequent access to global information in a data buffer, such as team rewards or other agents’ actions, which is typically unrealistic in decentralized MARL systems due to high communication costs. When communication is limited, agents must rely on outdated information to estimate gradients and update their policies. A common approach to handle missing data is called importance sampling, in which we reweigh old data from a base policy to […]

Ver mais

arXiv:2602.06195v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference labels presents a severe cost and scalability bottleneck. To overcome this, We propose a semi-supervised framework augmenting limited human data with a large corpus of unlabeled pairs annotated via cost-effective synthetic AI feedback. Our paper introduces Debiased DPO (DeDPO), which uniquely integrates a debiased […]

Ver mais

Clark Packard Last week, Disney+ released a restored version of The Beatles Anthology, the landmark 1995 ABC eight-part documentary series that remains the closest thing to a definitive account of the band’s extraordinary journey. I binge-watched the updated Anthology over the Thanksgiving holiday weekend, which brought back memories of watching the original with my parents 30 years ago. Now I’m the parent, though my wife and four-year-old son were less enthusiastic about the marathon viewing sessions. Last year, I […]

Ver mais

arXiv:2602.02519v1 Announce Type: new Abstract: The importance of managing feedback practices in higher education has been widely recognised, as they play a crucial role in enhancing teaching, learning, and assessment processes. In today’s educational landscape, feedback practices are increasingly influenced by technological advancements, particularly artificial intelligence (AI). Understanding the impact of AI on feedback generation is essential for identifying its potential benefits and establishing effective implementation strategies. This study examines how AI-generated feedback supports student learning using a […]

Ver mais

arXiv:2603.26707v1 Announce Type: new Abstract: This paper documents and theorises a self-reinforcing dynamic between two measurable trends: the exponential expansion of large language model (LLM) context windows and the secular contraction of human sustained-attention capacity. We term the resulting asymmetry the Cognitive Divergence. AI context windows have grown from 512 tokens in 2017 to 2,000,000 tokens by 2026 (factor ~3,906; fitted lambda = 0.59/yr; doubling time ~14 months). Over the same period, human Effective Context Span (ECS) — […]

Ver mais

arXiv:2510.10000v2 Announce Type: replace-cross Abstract: Wasserstein distributionally robust optimization (WDRO) provides a framework for adversarial robustness, yet existing methods based on global Lipschitz continuity or strong duality often yield loose upper bounds or require prohibitive computation. We address these limitations with a primal approach and adopt a notion of exact Lipschitz certificates to tighten this upper bound of WDRO. For ReLU networks, we leverage the piecewise-affine structure on activation cells to obtain an exact tractable characterization of the […]

Ver mais

Reinforcement learning (RL) in mobile edge computing (MEC) faces critical challenges of data heterogeneity, communication overhead, and limited generalization across diverse preferences and system configurations. We propose Adaptive Reinforcement Learning Offloading (ARLO), a unified framework integrating adaptive dissimilarity measures for federated learning with generalizable multi-objective optimization for computation offloading. The Adaptive Dissimilarity Measure module leverages parameter dissimilarity with Lagrangian multipliers to mitigate model drift under Non-IID data and loss dissimilarity to reduce communication overhead via adaptive aggregation. The […]

Ver mais