:::info Astounding Stories of Super-Science October, 1994, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. The Picture of Dorian Gray – Chapter XV Astounding Stories of Super-Science October 1994: The Picture of Dorian Gray – Chapter XV By Oscar Wilde ::: That evening, at eight-thirty, exquisitely dressed and wearing a large button-hole of Parma violets, Dorian Gray was ushered into Lady Narborough’s drawing-room by bowing servants. […]

Ver mais

arXiv:2602.15078v1 Announce Type: new Abstract: Following in the footsteps of the success of Mathlib – the centralised library of formalised mathematics in Lean – CSLib is a rapidly-growing centralised library of formalised computer science and software. In this paper, we present its founding technical principles, operation, abstractions, and semantic framework. We contribute reusable semantic interfaces (reduction and labelled transition systems), proof automation, CI/testing support for maintaining automation and compatibility with Mathlib, and the first substantial developments of languages […]

Ver mais

Recent machine-learning approaches to weather forecasting often employ a monolithic architecture, where distinct physical mechanisms (advection, transport), diffusion-like mixing, thermodynamic processes, and forcing are represented implicitly within a single large network. This representation is particularly problematic for advection, where long-range transport must be treated with expensive global interaction mechanisms or through deep, stacked convolutional layers. To mitigate this, we present PARADIS, a physics-inspired global weather prediction model that imposes inductive biases on network behavior through a functional decomposition […]

Ver mais

arXiv:2602.04774v1 Announce Type: cross Abstract: Setting the learning rate for a deep learning model is a critical part of successful training, yet choosing this hyperparameter is often done empirically with trial and error. In this work, we explore a solvable model of optimal learning rate schedules for a powerlaw random feature model trained with stochastic gradient descent (SGD). We consider the optimal schedule $eta_T^star(t)$ where $t$ is the current iterate and $T$ is the total training horizon. This […]

Ver mais

Most time series foundation models are pretrained by directly predicting future observations, which often yields weakly structured latent representations that capture surface noise rather than coherent and predictable temporal dynamics. In this work, we introduce EIDOS, a foundation model family that shifts pretraining from future value prediction to latent-space predictive learning. We train a causal Transformer to predict the evolution of latent representations, encouraging the emergence of structured and temporally coherent latent states. To ensure stable targets for […]

Ver mais

In-context learning (ICL) has proven highly effective across diverse large language model (LLM) tasks. However, its potential for enhancing tasks that demand step-by-step logical deduction, such as mathematical reasoning, remains underexplored. A core limitation of existing ICL approaches is their static use of demonstrations: examples are pre-selected before inference and remain fixed, failing to adapt to the dynamic confusion points that often arise during multi-step reasoning such as ambiguous calculations or logical gaps. These unresolved confusion points can […]

Ver mais

arXiv:2404.00735v4 Announce Type: replace-cross Abstract: Influence function (IF)-based estimators are widely used in mediation analysis due to their modeling flexibility, but standard implementations require direct estimation of the distribution functions of the mediator and treatment variables. Since these functions appear in the denominator of IF-based estimators, they can induce significant instability, particularly with continuous mediators. In this work, we propose an alternative implementation of IF-based estimators for both single- and multiple-mediator settings, based on reparametrizations of the likelihood. […]

Ver mais

Hey everyone, I’m fascinated by RL for LLMs. I have some SFT experience but none with RL, and I’d like to start experimenting with DPO. Some context: Over time I’ve built a framework for building LLM agents that I use internally at the company where I work. It started as na side project but evolved quite a bit, i recently added a tracer and an MCP server for Claude on top of it. What does this mean in […]

Ver mais

arXiv:2510.22848v2 Announce Type: replace-cross Abstract: Self-induced stochastic resonance (SISR) is the emergence of coherent oscillations in slow-fast excitable systems driven solely by noise, without external periodic forcing or proximity to a bifurcation. This work presents a physics-informed machine learning framework for modeling and predicting SISR in the stochastic FitzHugh-Nagumo neuron. We embed the governing stochastic differential equations and SISR-asymptotic timescale-matching constraints directly into a Physics-Informed Neural Network (PINN) based on a Noise-Augmented State Predictor architecture. The composite loss […]

Ver mais

Hey everyone , I’m working on the Farmer Training Adoption Challenge , I’ve hit a bit of a roadblock with optimizing my model performance. Current Public Score: Current score : 0.788265742 Target ROC-AUC: 0.968720425 Target Log Loss: ~0.16254811 I want to improve both classification ranking (ROC-AUC) and probability calibration (Log Loss), but I’m not quite sure which direction to take beyond my current approach. What I’ve Tried So Far Models: LightGBM CatBoost XGBoost Simple stacking/ensembling Feature Engineering: TF-IDF […]

Ver mais