arXiv:2602.15840v1 Announce Type: new Abstract: Over the past decade, extended reality (XR), including virtual, augmented, and mixed reality, gained attention as a research instrument in human-robot interaction studies, but remains underexplored in empirical investigations of social robotics. To map the field, we systematically reviewed empirical studies from 2015 to 2025. Of 6,527 peer-reviewed articles, only 33 met strict inclusion criteria. We examined (1) how XR and virtual social robots are used and in which contexts, (2) data collection […]

Ver mais

A designer friend recently told me she spent three days trying to figure out why her company’s checkout flow made users confirm their email address twice. It seemed obviously redundant—just bad UX someone forgot to clean up. She asked the PM. She asked the engineer who built it. She even dug through old PRs looking for context. The best answer she got was: “There was something with the vendor API, but I don’t remember the details. Maybe check […]

Ver mais

arXiv:2603.15568v1 Announce Type: new Abstract: Staged tree models enhance Bayesian networks by incorporating context-specific dependencies through a stage-based structure. In this study, we present a new framework for estimating staged trees using hierarchical clustering on the probability simplex, utilizing simplex basesd divergences. We conduct a thorough evaluation of several distance and divergence metrics including Total Variation, Hellinger, Fisher, and Kaniadakis; alongside various linkage methods such as Ward.D2, average, complete, and McQuitty. We conducted the simulation experiments that reveals […]

Ver mais

arXiv:2603.02337v1 Announce Type: new Abstract: Flow matching and score-based diffusion train vector fields under intermediate distributions $p_t$, whose geometry can strongly affect their optimization. We show that the covariance $Sigma_t$ of $p_t$ governs optimization bias: when $Sigma_t$ is ill-conditioned, and gradient-based training rapidly fits high-variance directions while systematically under-optimizing low-variance modes, leading to learning that plateaus at suboptimal weights. We formalize this effect in analytically tractable settings and propose reversible, label-conditional emph{preconditioning} maps that reshape the geometry of […]

Ver mais

Artificial intelligence has rapidly become a default expectation in modern mobile applications, yet its integration often remains superficial. Many applications label features as “AI-powered” while relying on basic heuristics or overusing cloud-based APIs without architectural consideration. On iOS, where performance, privacy, and responsiveness are critical, integrating AI effectively requires more than attaching a model to a feature. It demands careful decisions around execution environments, data flow, lifecycle management, and user experience. When implemented correctly, AI becomes an invisible […]

Ver mais

arXiv:2603.22446v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR’s distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, (2) the impact of token-level distributional shifts on sequence-level reasoning performance through cross-sampling interventions, and (3) fine-grained mechanics of these shifts at the […]

Ver mais

Equalizer parameter optimization is critical for signal integrity in high-speed memory systems operating at multi-gigabit data rates. However, existing methods suffer from computationally expensive eye diagram evaluation, optimization of expected rather than worst-case performance, and absence of uncertainty quantification for deployment decisions. In this paper, we propose a distributional risk-sensitive reinforcement learning framework integrating Information Bottleneck latent representations with Conditional Value-at-Risk optimization. We introduce rate-distortion optimal signal compression achieving 51 times speedup over eye diagrams while quantifying epistemic […]

Ver mais

With this latest $5 billion deal, the company is making a huge statement in the global AI race. According to reports, Amazon had already put around $8 billion into Anthropic, so the total could hit $25 billion if certain targets are met. Meanwhile, Anthropic has locked itself into spending more than $100 billion over the next decade on Amazon Web Services (AWS) which is way more than a usual start up investment. These two companies are now deeply […]

Ver mais

arXiv:2604.16865v1 Announce Type: new Abstract: In this paper, we consider the problem of extraction of most informative features from time series that are regarded as observed values of stochastic processes satisfying the It{^{o}} stochastic differential equations with unknown random drift and diffusion coefficients. We do not attract any additional information and use only the information contained in the time series as it is. Therefore, as additional features, we use the parameters of statistically adjusted mixture-type models of the […]

Ver mais

arXiv:2602.07081v1 Announce Type: new Abstract: This paper introduces a generalized federated prompt-tuning framework for practical scenarios where local datasets are multi-modal and exhibit different distributional patterns of missing features at the input level. The proposed framework bridges the gap between federated learning and multi-modal prompt-tuning which have traditionally focused on either uni-modal or centralized data. A key challenge in this setting arises from the lack of semantic alignment between prompt instructions that encode similar distributional patterns of missing […]

Ver mais