digitado

About digitado

https://www.digitado.com.br

Posts by :

SELDON: Supernova Explosions Learned by Deep ODE Networks

⋅

The discovery rate of optical transients will explode to 10 million public alerts per night once the Vera C. Rubin Observatory’s Legacy Survey of Space and Time comes online, overwhelming the traditional physics-based inference pipelines. A continuous-time forecasting AI model is of interest because it can deliver millisecond-scale inference for thousands of objects per day, whereas legacy MCMC codes need hours per object. In this paper, we propose SELDON, a new continuous-time variational autoencoder for panels of sparse […]

Ver mais

Liked Liked
The US Senate empowers NASA to fully engage in lunar space race

The US Senate empowers NASA to fully engage in lunar space race

⋅

During a brief hearing on Wednesday morning, the Senate Committee on Commerce, Science, and Transportation spent only a few minutes “marking up” new legislation that provides guidance to NASA for its various initiatives, including the Artemis program to land humans on the Moon. “Our bill authorizes critical funding for, and gives strategic direction to, the agency in line with the priorities of administrator Isaacman and the Trump administration,” said the committee’s chairman, Sen. Ted Cruz, (R-Texas). The duration […]

Ver mais

Liked Liked
MacBook Neo hands-on: Apple build quality at a substantially lower price

MacBook Neo hands-on: Apple build quality at a substantially lower price

⋅

NEW YORK CITY—Whether you’re talking about the iBook, MacBook, or MacBook Air, Apple’s most basic laptops have started at or within $100 of the $1,000 price point for over 20 years. Sure, the company had quietly been testing the waters with a Walmart-exclusive M1 MacBook Air configuration for several years, first at $699 and then at $599. But as far as what Apple would actively advertise and offer on its own site and in its own retail stores, […]

Ver mais

Liked Liked

What Does Flow Matching Bring To TD Learning?

⋅

Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it remains unclear why or how this approach differs from standard critics. Contrary to conventional belief, we show that their success is not explained by distributional RL, as explicitly modeling return distributions can reduce performance. Instead, we argue that the use of integration for reading out values and dense velocity supervision at each step of this integration process for […]

Ver mais

Liked Liked

PTOPOFL: Privacy-Preserving Personalised Federated Learning via Persistent Homology

⋅

Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions degrade aggregation quality. We introduce PTOPOFL, a framework that addresses both challenges simultaneously by replacing gradient communication with topological descriptors derived from persistent homology (PH). Clients transmit only 48-dimensional PH feature vectors-compact shape summaries whose many-to-one structure makes inversion provably ill-posed-rather than model gradients. The server performs topology-guided personalised aggregation: clients are clustered by Wasserstein similarity between their PH diagrams, intra-cluster models […]

Ver mais

Liked Liked

Anti-patterns: things to avoid

⋅

Agentic Engineering Patterns > There are some behaviors that are anti-patterns in our weird new world of agentic engineering. Inflicting unreviewed code on collaborators This anti-pattern is common and deeply frustrating. Don’t file pull requests with code you haven’t reviewed yourself. If you open a PR with hundreds (or thousands) of lines of code that an agent produced for you, and you haven’t done the work to ensure that code is functional yourself, you are delegating the actual […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025