Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
A Blog post by Amazon on Hugging Face
21 min
en
Agents IA
Agents autonomes, outils, orchestration et automatisation.
Thème · 130 articles
Introducing Gemini 3.7 Flash
Gemini 3.7 Flash is our most intelligent workhorse model yet for coding and agents.
4 min enWhat We Learned by Reproducing 2,200 papers from ICML
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
12 min enMindTopo reveals VLMs’ spatial reasoning abilities
A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning. The post MindTopo reveals VLMs’ spatial reasoning abilities appeared…
5 min enThinking of ACE? We Can Do It with Fewer Tokens
A Blog post by IBM Research on Hugging Face
8 min enBuild Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
A Blog post by NVIDIA on Hugging Face
7 min enHow to build an AI agent: A simple guide for anyone
The post How to build an AI agent: A simple guide for anyone appeared first on Source.
1 min enMeta is back with Muse Glimmer: local, agentic, multimodal, and open source
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
19 min enBaseten on Hugging Face Inference Providers 🔥
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
4 min enOrchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure. The post…
8 min enEchoverse: Deep, evolving environments for computer-use agents
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve…
22 min enEvoLib: Turning experience into evolving knowledge
LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment. The post EvoLib: Turning experience into evolving…
5 min en
