Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Dataset em destaque no Hugging Face — 456 downloads. AI Village dataset AI Village is an ongoing experiment by AI Digest in which a group of AI agents — built on frontier models from Anthropic, OpenAI,…
Um paper em alta nos Daily Papers do Hugging Face faz uma acusação incômoda aos chamados modelos de mundo: eles geram cenas convincentes, mas não mantêm um registro consistente do que existe ao longo do tempo.
Dataset em destaque no Hugging Face — 1.0 mil downloads. This dataset was generated using teich by TeichAI GLM-5.
Dataset em destaque no Hugging Face — 1.9 mil downloads. OmniVideo-100K Official repository for OmniVideo-100K, an instruction-tuning dataset introduced in our paper: "OmniVideo-100K: A Dataset for Audio-Vis…
In this tutorial, we build a complete Crawlee for Python workflow from setup to AI-ready output. We generate a local demo website, then crawl it with BeautifulSoupCrawler, ParselCrawler, and PlaywrightCrawler. We extract titles, metadata, product fields, and JavaScript-rendered cards, and capture full-page screenshots. We then normalize the data, build a link graph, and export JSON, CSV, and RAG-ready JSONL chunks. The post Crawlee for Python: Build a Web Crawling Pipeline with Robots Handling, ...
Modelo de modelo em alta no Hugging Face — 363 downloads e 43 curtidas da comunidade.
Modelo de modelo em alta no Hugging Face — 409 downloads e 42 curtidas da comunidade.
Modelo de modelo — 1.0 mil downloads e 140 curtidas no Hugging Face.
Modelo de modelo em alta no Hugging Face — 445 downloads e 42 curtidas da comunidade.
Modelo de geração de texto · 12 B de parâmetros — 7.5 mil downloads e 142 curtidas no Hugging Face.
Multimodal Chain-of-Thought reasoning shows selective effectiveness across different tasks, with limitations in maintaining visual introspection during reasoning processes.
PolicyTrim is a reinforcement learning-based framework that enhances VLA model efficiency by extending reliable action chunk lengths and reducing redundant physical steps through d…