Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Agentic Data Tailoring paradigm uses learnable data processing to structure high-entropy multimodal streams, with DataClaw_0-9B model achieving robust alignment through SFT and GRP…
Play favorite titles from popular game libraries, keep progress synced and jump back into gaming sessions on virtually any device. That’s the power of GeForce NOW cloud gaming. From providing access to members’ favorite game libraries to offering some of the season’s best membership pricing, GeForce NOW is making it easier than ever to get […]
A fast, training-free framework generates text-driven 3D visual illusions by decoupling generation into cross-space dual-branch denoising and view-conditioned texture synthesis for…
Multimodal large language models exhibit social bias driven by specific visual attributes, with fashion style and socioeconomic cues having the greatest impact on model judgments.
NVIDIA XR AI is now available in public beta, giving developers a framework for building multimodal AI agents for AR glasses and XR devices.
Modelo de geração de texto em alta no Hugging Face — 3.0 mil downloads e 43 curtidas da comunidade.
GeneralVLA-2 addresses limitations in vision-language-action systems by introducing GeoFuse-MV3D for improved 3D reconstruction and an enhanced KnowledgeBank for better memory mana…
Modelo de geração de texto em alta no Hugging Face — 3.7 mil downloads e 162 curtidas da comunidade.
Modelo de visão e linguagem em alta no Hugging Face — 412.8 mil downloads e 960 curtidas da comunidade.
Modelo de geração de texto em alta no Hugging Face — 52.8 mil downloads e 105 curtidas da comunidade.
ContextRL enhances long-horizon reasoning and multimodal performance through reinforcement learning that rewards context selection for supporting query-answer pairs, achieving impr…
Modelo de visão e linguagem em alta no Hugging Face — 233.4 mil downloads e 324 curtidas da comunidade.