Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
HAKARI-Bench provides a lightweight benchmark for comparing retrieval methods across multiple configurations and languages, enabling efficient model selection and performance analy…
A bi-modal construction domain dataset combining stereo RGB and LiDAR data under challenging environmental conditions is introduced for autonomous system perception research.
A principled synthesis engine generates high-quality terminal-agent tasks through multi-dimensional capability taxonomy and evidence-guided research, creating a distilled dataset t…
LLMs are stateless by default. Agent memory fixes that. This guide breaks down all 7 types — working, semantic, episodic, procedural, retrieval, parametric, and prospective. It covers what each stores, where it lives, and when to build it. Includes a comparison table and working Python code. The post The 7 Types of Agent Memory: A Technical Guide for AI Engineers appeared first on MarkTechPost .
A LiquidAI lançou um modelo de embeddings com apenas 350 milhões de parâmetros. A pergunta interessante não é se ele é o maior — é por que tamanho menor virou vantagem competitiva na busca semântica.
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,…
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, ...
PlanBench-XL evaluates large language model agents' ability to plan and adapt in complex tool-rich environments with limited visibility and dynamic disruptions.
Cisco Foundation AI has open-sourced FAPO (Fully Automated Prompt Optimization), a Claude Code-driven system that autonomously optimizes multi-step LLM pipelines from baseline prompts to target accuracy. FAPO evaluates a chain, attributes failures at the step level, proposes variants across prompt, parameter, and chain-structure levels, and validates each through an independent reviewer. In Cisco's evaluation, it beat GEPA on 15 of 18 model-benchmark comparisons. Here's how the optimization loop...
Dataset em destaque no Hugging Face — 10.6 mil downloads. AI Conference & Journal Papers Searchable metadata and full-text PDF mirrors for papers from top-tier AI venues (NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV…
Modelo de similaridade de sentenças em alta no Hugging Face — 8.8 mil downloads e 100 curtidas da comunidade.
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...