technocracy

One of the more frequent comments that expert Haskell developers make about other programming languages is that they lack something called higher-kinded types. Which leads to a communication problem. Since those programming languages don’t have a way to express either kinds or HKTs, it is hard for non-Haskell developers to understand what they are missing out on. In the end, the words of the Haskell developer are dismissed as mad ravings, and everybody moves on. But once you […]

Ver mais

arXiv:2603.25840v1 Announce Type: new Abstract: This paper studies system identification for nonlinear state-space models, a problem that arises across many fields yet remains challenging in practice. Focusing on maximum likelihood estimation, we employ Bayesian optimization (BayesOpt) to address this problem by leveraging its derivative-free global search capability enabled by surrogate modeling of the likelihood function. Despite these advantages, standard BayesOpt often suffers from slow convergence, high computational cost, and practical difficulty in attaining global optima under limited computational […]

Ver mais

In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging […]

Ver mais

Federated Learning (FL) enables collaborative model training by sharing model updates instead of raw data, aiming to protect user privacy. However, recent studies reveal that these shared updates can inadvertently leak sensitive training data through gradient inversion attacks (GIAs). Among them, active GIAs are particularly powerful, enabling high-fidelity reconstruction of individual samples even under large batch sizes. Nevertheless, existing approaches often require architectural modifications, which limit their practical applicability. In this work, we bridge this gap by introducing […]

Ver mais

arXiv:2601.15488v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit significant social biases that can perpetuate harmful stereotypes and unfair outcomes. In this paper, we propose Multi-Persona Thinking (MPT), a novel inference-time framework that leverages dialectical reasoning from multiple perspectives to reduce bias. MPT guides models to adopt contrasting social identities (e.g., male and female) along with a neutral viewpoint, and then engages these personas iteratively to expose and correct biases. Through a dialectical reasoning process, the framework […]

Ver mais

arXiv:2601.07946v1 Announce Type: new Abstract: Data-driven flow-field reconstruction typically relies on autoencoder architectures that compress high-dimensional states into low-dimensional latent representations. However, classical approaches such as variational autoencoders (VAEs) often struggle to preserve the higher-order statistical structure of fluid flows when subjected to strong compression. We propose DiffCoder, a coupled framework that integrates a probabilistic diffusion model with a conventional convolutional ResNet encoder and trains both components end-to-end. The encoder compresses the flow field into a latent representation, […]

Ver mais

The digital space feels noisy lately. Every scroll you make screams the same headlines: “AI is the future”, “AI will make you rich”, “20 prompts to 10x your workflow.” The overwhelming feeling you get listening to all this does not mean you are slow or left behind; it’s your honest reaction to the surface-level noise the market is currently saturated with. n The truth behind this noise is that knowing how to talk to a language model is […]

Ver mais

arXiv:2604.08630v1 Announce Type: new Abstract: We study differentially private data release, where a database is accessed through successive, possibly adaptive queries and mechanisms. Existing composition theorems and privacy filters combine worst case per-round privacy parameters, leaving room for more refined accounting based on realised leakage, which we term realisation-level accounting. We propose a realisation-level filtering approach to determine stopping times for data releases, and design one such filter. Despite technical challenges arising from conditioning on realisations and stopping […]

Ver mais