Actualités
OmniGAIA: Towards Native Omni-Modal AI Agents
arXiv:2602.22897v1 Announce Type: cross Abstract: Human intelligence naturally intertwines omni-modal perception — spanning vision, audio...
OMIND: Framework for Knowledge Grounded Finetuning and Multi-Turn Dialogue Benchmark for Mental Health LLMs
arXiv:2603.25105v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown remarkable capabilities for complex...
Ollama vs. LM Studio vs. llama.cpp: Which Local AI Runtime Should You Use in 2026?
In this article, you will learn how Ollama, LM Studio, and llama.cpp differ across the...
Olica: Efficient Structured Pruning of Large Language Models without Retraining
arXiv:2506.08436v1 Announce Type: new Abstract: Most existing structured pruning methods for Large Language Models (LLMs)...
OCRmyPDF Tutorial: Convert Scanned Documents into Searchable PDF/A Files with Sidecar Text Extraction and Batch Processing
In this tutorial, we build an advanced, self-contained OCRmyPDF workflow. We start by installing the...
OceanBase Releases seekdb: An Open Source AI Native Hybrid Search Database for Multi-model RAG and AI Agents
AI applications rarely deal with one clean table. They mix user profiles, chat logs, JSON...
NVIDIA’s Cosmos-Framework Tutorial: Designing a Colab-Friendly Miniature of Cosmos 3 World Models with Omnimodal Mixture-of-Transformers
In this tutorial, we explore NVIDIA’s cosmos-framework from a practical Colab-friendly angle while staying honest...
Nvidia-powered supercomputer to enable quantum leap for Taiwan’s research
Nvidia is powering a supercomputer at Taiwan’s National Center for High-Performance Computing that’s set to...
Nvidia thinks AI can solve electrical grid problems caused by AI
The Open Power AI Consortium says it will use domain-specific AI models to tackle problems...
NVIDIA Releases Polar, a Token-Faithful Rollout Framework for GRPO Training Across Codex, Claude Code, and Qwen Code
Reinforcement learning for language agents is growing more complex. Agents now manage multi-turn tool use...
NVIDIA Releases PersonaPlex-7B-v1: A Real-Time Speech-to-Speech Model Designed for Natural and Full-Duplex Conversations
NVIDIA Researchers released PersonaPlex-7B-v1, a full duplex speech to speech conversational model that targets natural...
NVIDIA Releases Nemotron-Labs-TwoTower: an Open-Weight Diffusion Language Model Built on a Frozen Autoregressive Nemotron-3-Nano-30B-A3B Backbone
NVIDIA has released Nemotron-Labs-TwoTower, a diffusion language model built on a pretrained autoregressive backbone. It...
