Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Modelo de visão e linguagem · 27 B de parâmetros — 83.1 mil downloads e 106 curtidas no Hugging Face.
In this article we look at YaFF, Yandex's open-source zero-copy wire format for the Protobuf ecosystem. We keep the .proto file as the single source of truth, changing only how data sits in memory. We walk through its four layouts — Fixed, Flat, Sparse, and Dynamic — and the benchmark where Flat Layout reads within 1.2× of a raw C++ struct. We also cover where it fits, including the advertising recommendation system reporting 10–20% CPU savings at production scale. The post Yandex Open-So...
We build an end-to-end forecasting workflow with TimeCopilot on a panel of real airline passenger data and a synthetic seasonal series with injected anomalies. We evaluate statistical, foundation, and optional GPU-based models using rolling cross-validation and multiple error metrics. We generate probabilistic forecasts with prediction intervals, visualize future trends, and flag unusual observations. We then explore TimeCopilot's optional LLM agent, which selects a model and explains its predic...
Dataset com 1 – 10 milhões de exemplos — 1.7 mil downloads no Hugging Face. LOCUS v1.0 This repository contains the dataset presented in the paper Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States. Dat…
A new biomedical benchmark evaluates agentic models' ability to verify sources and avoid false citations by testing unsolved research questions with no answer keys, revealing signi…
Autoregressive generation in large language models traditionally uses the final layer for token prediction, but a new decoding strategy dynamically selects more reliable intermedia…
BioMatrix is a novel multimodal foundation model that integrates molecular sequences, structures, and natural language into a unified decoder-only architecture for diverse biologic…
Multi4D addresses the trade-off between motion consistency and visual fidelity in dynamic 3D Gaussian splatting through a multi-level competitive allocation framework that enables…
EBench is a comprehensive simulation benchmark for evaluating generalist mobile manipulation policies across diverse tasks and dimensions, revealing distinct capability profiles an…
Training models on chain-of-thought demonstrations fails for tasks requiring backtracking search because the forward derivation cannot be faithfully imitated, demonstrating a funda…
Modelo de síntese de voz — 0 downloads e 207 curtidas no Hugging Face.
For the last 30 years, stopping the flow of cybersecurity-related software has proven to be ineffective. It's unclear why it would work now with Anthropic’s cybersecurity model Mythos.