technocracy

Paper: https://arxiv.org/abs/2602.15950 TL;DR: Vision-Language Models achieve ~84% F1 reading binary grids rendered as text characters (. and #) but collapse to 29-39% F1 when the exact same grids are rendered as filled squares, despite both being images through the same visual encoder. The 34-54 point F1 gap replicates across Claude Opus, ChatGPT 5.2, and Gemini 3 Thinking. Hi everyone, I ran a simple experiment: generate fifteen 15×15 binary grids at varying density, render each as both text symbols […]

Ver mais

Internet of Things (IoT) deployments operate in nonstationary, dynamic environments where factors such as sensor drift, evolving user behavior, and heterogeneous user privacy requirements can affect application utility. Continual learning (CL) addresses this by adapting models over time without catastrophic forgetting. Meanwhile, contrastive learning has emerged as a powerful representation-learning paradigm that improves robustness and sample efficiency in a self-supervised manner. This paper reviews the usage of emph{contrastive continual learning} (CCL) for IoT, connecting algorithmic design (replay, regularization, […]

Ver mais

arXiv:2602.21307v1 Announce Type: new Abstract: Symbolic distillation replaces neural networks, or components thereof, with interpretable, closed-form mathematical expressions. This approach has shown promise in discovering physical laws and mathematical relationships directly from trained deep learning models, yet adoption remains limited due to the engineering barrier of integrating symbolic regression into deep learning workflows. We introduce SymTorch, a library that automates this distillation by wrapping neural network components, collecting their input-output behavior, and approximating them with human-readable equations via […]

Ver mais

The shape of a planet’s orbit around a star is an ellipse. To put it another way, a plot of the position of a planet’s orbit over time forms an ellipse. What about the velocity? Is it’s plot also an ellipse? Surprisingly, a plot of the velocity forms a circle even if a plot of the position is an ellipse. If an object is in a circular orbit, it’s velocity vector traces out a circle too, with the […]

Ver mais

arXiv:2505.21791v4 Announce Type: replace Abstract: Overparameterized neural networks can interpolate a given dataset in many different ways, prompting the fundamental question: which among these solutions should we prefer, and what explicit regularization strategies will provably yield these solutions? This paper addresses the challenge of finding the sparsest interpolating ReLU network–i.e., the network with the fewest nonzero parameters or neurons–a goal with wide-ranging implications for efficiency, generalization, interpretability, theory, and model compression. Unlike post hoc pruning approaches, we propose […]

Ver mais

In recent years, multi-view multi-label learning (MVML) has attracted extensive attention due to its close alignment to real-world scenarios. Information-theoretic methods have gained prominence for learning nonlinear correlations. However, two key challenges persist: first, features in real-world data commonly exhibit high-order structural correlations, but existing information-theoretic methods struggle to learn such correlations; second, commonly relying on heuristic optimization, information-theoretic methods are prone to converging to local optima. To address these two challenges, we propose a novel method called […]

Ver mais

Long before “engineering” became a formal career path, it was already part of Will Jiang’s daily life. Growing up in China, Jiang was the student teacher whom a classmate turned to when a laptop froze minutes before class. By high school, he was maintaining his school’s network infrastructure by diagnosing connectivity issues, keeping systems online, and supporting hundreds of users. What stayed with him wasn’t just the technical challenge, but the idea that thoughtfully built systems could quietly […]

Ver mais

arXiv:2502.03174v2 Announce Type: replace-cross Abstract: In this paper, we investigate the label shift quantification problem. We propose robust estimators of the label distribution which turn out to coincide with the Maximum Likelihood Estimator. We analyze the theoretical aspects and derive deviation bounds for the proposed method, providing optimal guarantees in the well-specified case, along with notable robustness properties against outliers and contamination. Our results provide theoretical validation for empirical observations on the robustness of Maximum Likelihood Label Shift.

Ver mais

The proliferation of large-scale low Earth orbit (LEO) satellite constellations is driving the need for intelligent routing strategies that can effectively deliver data to terrestrial networks under rapidly time-varying topologies and intermittent gateway visibility. Leveraging the global control capabilities of a geostationary (GEO)-resident software-defined networking (SDN) controller, we introduce opportunistic routing, which aims to minimize delivery delay by forwarding packets to any currently available ground gateways rather than fixed destinations. This makes it a promising approach for achieving […]

Ver mais