technocracy

arXiv:2603.06698v1 Announce Type: new Abstract: Knowledge distillation between asymmetric architectures often induces severe geometric constraints on the learned representation space. In this work, we investigate the Dimensional Collapse phenomenon when distilling a 500M parameter global Vision Transformer (CLIP ViT-B/32) into strictly capacity-constrained, local-receptive-field CNNs (0.5M to 8.0M parameters) on the CIFAR-10 dataset. By employing strictly centered Singular Value Decomposition (SVD) and Variance-based Shannon Entropy Effective Rank, we isolate true structural variance from mean-vector artifacts. Our empirical results demonstrate […]

Ver mais

1. Introduction: Beyond the Hype The rise of AI agents represents a seismic shift in technology. We’re moving beyond basic chatbots that simply respond to prompts, into an era of autonomous systems capable of independent planning, logical reasoning, and executing complex tasks. These advances promise to revolutionize how businesses operate. However, beneath the surface of polished demonstrations and enthusiastic predictions, real-world implementation tells a more nuanced story. This deep dive cuts through the speculation to reveal crucial insights […]

Ver mais

The design and reliability assurance of embedded systems is a complex issue, since they need to handle not only digital behavior but also physical quantities such as time, cost, and sometimes randomness. In addition, since many embedded systems, such as networks and automobiles, have systems in which errors can be fatal, design verification for reliability assurance is an important research topic. With the above background, we adopt the approach of specifying and verifying embedded systems by formal models. […]

Ver mais

arXiv:2602.08307v1 Announce Type: cross Abstract: In this paper, we study Interaction-Grounded Learning (IGL) [Xie et al., 2021], a paradigm designed for realistic scenarios where the learner receives indirect feedback generated by an unknown mechanism, rather than explicit numerical rewards. While prior work on IGL provides efficient algorithms with provable guarantees, those results are confined to single-step settings, restricting their applicability to modern sequential decision-making systems such as multi-turn Large Language Model (LLM) deployments. To bridge this gap, we […]

Ver mais

arXiv:2601.03430v1 Announce Type: new Abstract: Open Source Software for Social Good (OSS4SG) projects aim to address critical societal challenges, such as healthcare access and community safety. Understanding the community dynamics and contributor patterns in these projects is essential for ensuring their sustainability and long-term impact. However, while extensive research has focused on conventional Open Source Software (OSS), little is known about how the mission-driven nature of OSS4SG influences its development practices. To address this gap, we conduct a […]

Ver mais

arXiv:2604.25984v1 Announce Type: new Abstract: The marginal likelihood, also known as the evidence, is regarded as a mathematical embodiment of Occam’s razor, enabling model selection that avoids overfitting. The evidence lower bound (ELBO) objective from variational inference has also been used for similar purposes. Prior work has shown that restricting the approximate posterior family via a mean-field approximation can lead the ELBO to underfit. In this paper, we show how ELBO-based hyperparameter learning in a simple over-parameterized regression […]

Ver mais

Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises the question of how well models generalize under performativity. For example, how well can we draw insights about new app users based on existing users when both of them react to the app’s predictions? We address this question by embedding performative predictions […]

Ver mais

Machine learning interatomic potentials (MLIPs) have proven to be wildly useful for molecular dynamics simulations, powering countless drug and materials discovery applications. However, MLIPs face two primary bottlenecks preventing them from reaching realistic simulation scales: inference time and memory consumption. In this work, we address both issues by challenging the long-held belief that the cutoff radius for the MLIP must be held to a fixed, constant value. For the first time, we introduce a dynamic cutoff formulation that […]

Ver mais