arXiv:2603.02368v1 Announce Type: new Abstract: We introduce RO-N3WS, a benchmark Romanian speech dataset designed to improve generalization in automatic speech recognition (ASR), particularly in low-resource and out-of-distribution (OOD) conditions. RO-N3WS comprises over 126 hours of transcribed audio collected from broadcast news, literary audiobooks, film dialogue, children’s stories, and conversational podcast speech. This diversity enables robust training and fine-tuning across stylistically distinct domains. We evaluate several state-of-the-art ASR systems (Whisper, Wav2Vec 2.0) in both zero-shot and fine-tuned settings, and […]

Ver mais

The compliance industrial complex is selling a new product. Having peddled GDPR checklists and SOC2 reports for years, the same vendors are offering AI governance frameworks with the promises of making your neural networks ethical, safe, and compliant. While the policies sound reasonable, with impressive documentation and an expensive consultant, none of it is stopping breaches. As a cybersecurity ghostwriter who has collaborated with several Silicon Valley Startups and tech founders in the APAC region, I’ve watched hundreds […]

Ver mais

arXiv:2601.12296v1 Announce Type: new Abstract: An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic design. In this study, we find that one such reason lies in the distribution shift across training domains. A large degree of distribution shift can lead to better performance even under ERM. Specifically, we derive several theoretical and empirical findings demonstrating that distribution shift plays […]

Ver mais

Bandit algorithms are concerned with trading exploration with exploitation where a number of options are available but we can only learn their quality by experimenting with them. We consider the scenario in which the reward distribution for arms is modeled by a Gaussian process and there is no noise in the observed reward. Our main result is to bound the regret experienced by algorithms relative to the a posteriori optimal strategy of playing the best arm throughout based […]

Ver mais

In-Context Learning (ICL) in transformers acts as an online associative memory and is believed to underpin their high performance on complex sequence processing tasks. However, in gated linear attention models, this memory has a fixed capacity and is prone to interference, especially for long sequences. We propose Palimpsa, a self-attention model that views ICL as a continual learning problem that must address a stability-plasticity dilemma. Palimpsa uses Bayesian metaplasticity, where the plasticity of each attention state is tied […]

Ver mais

arXiv:2602.07158v1 Announce Type: new Abstract: Passive dynamic walkers are widely adopted as a mathematical model to represent biped walking. The stable locomotion of these models is limited to tilted surfaces, requiring gravitational energy. Various techniques, such as actuation through the ankle and hip joints, have been proposed to extend the applicability of these models to level ground and rough terrain with improved locomotion efficiency. However, most of these techniques rely on impulsive energy injection schemes and torsional springs, […]

Ver mais

arXiv:2602.11324v1 Announce Type: new Abstract: A key principle in string processing is local consistency: using short contexts to handle matching fragments of a string consistently. String synchronizing sets [Kempa, Kociumaka; STOC 2019] are an influential instantiation of this principle. A $tau$-synchronizing set of a length-$n$ string is a set of $O(n/tau)$ positions, chosen via their length-$2tau$ contexts, such that (outside highly periodic regions) at least one position in every length-$tau$ window is selected. Among their applications are faster […]

Ver mais

This study develops a Constraint-Driven Model of Intelligence to explain the emergence of structured meaning in complex systems, reconciling probability and cybernetics. Building on Émile Borel’s Infinite Monkey Theorem, which illustrates the theoretical inevitability of order through unbounded stochastic processes, and Gregory Bateson’s principle of negative explanation, which frames structure as the consequence of systematically eliminated alternatives, the analysis formalizes how constraints break ergodicity and generate asymmetry. Shannon’s entropy quantifies the informational effects of constraints, while Simon’s bounded […]

Ver mais

arXiv:2602.02616v1 Announce Type: new Abstract: Simulating flow problems is at the core of many engineering applications but often requires high computational effort, especially when dealing with complex models. This work presents a novel approach for resolving flow problems using the LATIN-PGD solver. In this contribution, we place ourselves within the framework of Newtonian compressible and laminar flows. This specific and relatively simple case enables focusing on flows for which a state equation provides a direct relation between pressure […]

Ver mais

arXiv:2602.12315v1 Announce Type: new Abstract: The proliferation of e-commerce has made web shopping platforms key gateways for customers navigating the vast digital marketplace. Yet this rapid expansion has led to a noisy and fragmented information environment, increasing cognitive burden as shoppers explore and purchase products online. With promising potential to alleviate this challenge, agentic systems have garnered growing attention for automating user-side tasks in web shopping. Despite significant advancements, existing benchmarks fail to comprehensively evaluate how well agentic […]

Ver mais