technocracy

arXiv:2411.01629v2 Announce Type: replace Abstract: Adding noise is easy; what about denoising? Diffusion is easy; what about reverting a diffusion? Diffusion-based generative models aim to denoise a Langevin diffusion chain, moving from a log-concave equilibrium measure $nu$, say an isotropic Gaussian, back to a complex, possibly non-log-concave initial measure $mu$. The score function performs denoising, moving backward in time, and predicting the conditional mean of the past location given the current one. We show that score denoising is […]

Ver mais

If you’ve worked with Ethereum and then tried Solana, you probably felt confused by how different everything looks. The account model especially feels strange. But here’s the thing: it’s not just different for the sake of being different. Ethereum and Solana made completely opposite choices about how to organize data, and these choices matter a lot. Let’s break down what makes Solana’s account model unique and why it works the way it does. The Big Picture: Two Different […]

Ver mais

The capacity to transfer knowledge across scientific domains relies on shared organizational principles. However, existing transfer-learning methodologies often fail to bridge radically heterogeneous systems, particularly under severe data scarcity or stochastic noise. This study formalizes Explainable Cross-Domain Transfer Learning (X-CDTL), a framework unifying network science and explainable artificial intelligence to identify structural invariants that generalize across biological, linguistic, molecular, and social networks. By introducing the Importance Inversion Transfer (IIT) mechanism, the framework prioritizes domain-invariant structural anchors over idiosyncratic, […]

Ver mais

Quantifying the impacts of air pollution on health and climate relies on key atmospheric particle properties such as toxicity and hygroscopicity. However, these properties typically require complex observational techniques or expensive particle-resolved numerical simulations, limiting the availability of labeled data. We therefore estimate these hard-to-measure particle properties from routinely available observations (e.g., air pollutant concentrations and meteorological conditions). Because routine observations only indirectly reflect particle composition and structure, the mapping from routine observations to particle properties is noisy […]

Ver mais

arXiv:2602.05036v1 Announce Type: new Abstract: Can multi-task self-supervised learning on graphs be coordinated without the usual tug-of-war between objectives? Graph self-supervised learning (SSL) offers a growing toolbox of pretext objectives: mutual information, reconstruction, contrastive learning; yet combining them reliably remains a challenge due to objective interference and training instability. Most multi-pretext pipelines use per-update mixing, forcing every parameter update to be a compromise, leading to three failure modes: Disagreement (conflict-induced negative transfer), Drift (nonstationary objective utility), and Drought […]

Ver mais

arXiv:2602.22362v1 Announce Type: new Abstract: With the advent of generative AI and large language models, embodied conversational agents are becoming synonymous with online interactions. These agents possess vast amounts of knowledge but suffer from exhibiting limited emotional expressiveness. Without adequate expressions, agents might fail to adapt to users’ emotions, which may result in a sub-optimal user experience and engagement. Most current systems prioritize content based responses, neglecting the emotional context of conversations. Research in this space is currently […]

Ver mais

Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is a critical control knob: if set too small, systematic over-clipping induces optimization bias; if too large, injected noise dominates updates and degrades accuracy. Existing adaptive clipping methods often depend on per-example gradient norm statistics, adding computational overhead and introducing sensitivity to datasets and architectures. We propose a control-driven clipping strategy that adapts the threshold using a […]

Ver mais

Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new paradigms for learning such representations. However, existing diffusion-based methods encourage factor independence via inductive biases, yet frequently lack strong semantic alignment. In this work, we propose a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space. To enforce explicit […]

Ver mais

:::tip The prompt below created much of the article after it, with some major editing, clarifications, and rephrasing. ::: AI-Prompted Recursive Prompt “You are tasked with writing a sophisticated, technically grounded article for HackerNoon that argues for recursive prompt engineering—where LLMs generate their own optimized prompts before executing tasks. Core Objectives: Demonstrate that LLMs can produce superior prompts for themselves than humans can write Explain the technical and cognitive mechanisms behind this superiority Provide concrete, detailed examples across […]

Ver mais

arXiv:2601.12220v1 Announce Type: new Abstract: We present an algorithm for normalizing emph{Batched Einstein Summation} expressions by mapping mathematically equivalent formulations to a unique normal form. Batches of einsums with the same Einstein notation that exhibit substantial data reuse appear frequently in finite element methods (FEM), numerical linear algebra, and computational chemistry. To effectively exploit this temporal locality for high performance, we consider groups of einsums in batched form. Representations of equivalent batched einsums may differ due to index […]

Ver mais