technocracy

arXiv:2601.07855v1 Announce Type: new Abstract: For 3D perception systems to be practical in real-world applications — from autonomous driving to embodied AI — models must adapt to continuously evolving object definitions and sensor domains. Yet, research on continual and transfer learning in 3D point cloud perception remains underexplored compared to 2D vision — particularly under simultaneous domain and label shifts. To address this gap, we propose the RObust Autonomous driving under Dataset shifts (ROAD) benchmark, a comprehensive evaluation […]

Ver mais

Australia’s banking, financial services, and insurance (BFSI) sector is undergoing a significant transformation as organisations accelerate the adoption of digital technologies. This shift is enhancing operational efficiency, improving customer experiences, and enabling institutions to remain competitive in an evolving financial landscape. From the rise of fintech innovation and digital banking platforms to advancements in artificial intelligence, automation, and cloud computing, technology continues to redefine how financial institutions deliver services and manage risks. The rapid pace of technology adoption, […]

Ver mais

Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as node classification, link prediction, and signal reconstruction. A key goal is to design node embeddings whose dot products capture meaningful notions of node similarity induced by the graph. Graph kernels offer a principled way to define such similarities, but their direct computation is often prohibitive for large networks. Inspired by random feature methods for kernel approximation in Euclidean […]

Ver mais

arXiv:2604.14324v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typically partition datasets directly based on response accuracy, causing models to suffer from severe label noise near the decision boundaries and consequently exhibit high rates of abstentions or hallucinations. This paper adopts a latent space representation perspective, revealing a “gray zone” near the decision hyperplane where internal belief ambiguity constitutes the […]

Ver mais

arXiv:2308.14555v4 Announce Type: replace-cross Abstract: Mathematical methods are developed to characterize the asymptotics of recurrent neural networks (RNN) as the number of hidden units, data samples in the sequence, hidden state updates, and training steps simultaneously grow to infinity. In the case of an RNN with a simplified weight matrix, we prove the convergence of the RNN to the solution of an infinite-dimensional ODE coupled with the fixed point of a random algebraic equation. The analysis requires addressing […]

Ver mais

Why the next 24 months represent not an upgrade cycle, but an architectural transformation in human-AI symbiosis The Fallacy of Linear Extrapolation When analyzing AI trajectory predictions, most analysts fall into the trap of linear extrapolation — projecting current capabilities forward at constant rates. The predictions outlined in the source document, while appearing speculative, actually reveal something more profound: we’re approaching an architectural phase transition in how intelligence itself is deployed in human systems. Let me be explicit about what’s technically […]

Ver mais

arXiv:2603.22435v1 Announce Type: new Abstract: “Code-as-Policy” considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying […]

Ver mais

arXiv:2603.04275v1 Announce Type: cross Abstract: We introduce inference methods for score decompositions, which partition scoring functions for predictive assessment into three interpretable components: miscalibration, discrimination, and uncertainty. Our estimation and inference relies on a linear recalibration of the forecasts, which is applicable to general multi-step ahead point forecasts such as means and quantiles due to its validity for both smooth and non-smooth scoring functions. This approach ensures desirable finite-sample properties, enables asymptotic inference, and establishes a direct connection […]

Ver mais

arXiv:2602.03168v1 Announce Type: new Abstract: Online conformal prediction (OCP) seeks prediction intervals that achieve long-run $1-alpha$ coverage for arbitrary (possibly adversarial) data streams, while remaining as informative as possible. Existing OCP methods often require manual learning-rate tuning to work well, and may also require algorithm-specific analyses. Here, we develop a general regret-to-coverage theory for interval-valued OCP based on the $(1-alpha)$-pinball loss. Our first contribution is to identify emph{linearized regret} as a key notion, showing that controlling it implies […]

Ver mais

Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional radiative transfer models remain computationally expensive and often limited to spectrum-level outputs. In this work, we propose a latent representation-based framework for hyperspectral emulation that learns a latent generative representation of hyperspectral data. The proposed approach supports both spectrum-level and spatial-spectral emulation and can be trained either in a direct one-step formulation or in a two-step strategy that couples variational autoencoder […]

Ver mais