Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action
NVIDIA has released Cosmos 3, described as the first open omni-model targeting physical AI reasoning and action. The model is hosted and announced via Hugging Face, positioning it as an open-weights offering for robotics and embodied AI applications. The announcement highlights multimodal capabilities oriented toward physical world understanding and agent-level action.
Related guides (3)
Related events (8)
NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI
NVIDIA has released Cosmos Reason 2, a model designed to bring advanced reasoning capabilities to physical AI applications. The announcement appears on the Hugging Face blog, indicating the model is likely available or accessible through the platform. This represents a continuation of NVIDIA's Cosmos model family targeting robotics and physical world understanding.
NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets
NVIDIA announced new open models and datasets for physical AI development at GTC 2025, covered via the Hugging Face blog. The release targets robotics and embodied AI developers with open-weights resources. This represents NVIDIA's continued push into the physical AI ecosystem alongside its hardware dominance.
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
NVIDIA has released Nemotron 3 Nano Omni, a multimodal model targeting long-context understanding across documents, audio, and video modalities. The model is positioned for agentic use cases requiring cross-modal reasoning. It is published via the Hugging Face blog as part of NVIDIA's Nemotron model family. No detailed technical specifications or benchmark results are provided in the available body text.
NVIDIA Cosmos 3, Nemotron 3 Ultra, and RTX Spark
A Latent Space AI news digest covers three NVIDIA announcements: Cosmos 3 (a world model/simulation platform), Nemotron 3 Ultra (a large language model), and RTX Spark (likely a new hardware or inference product). The piece frames these as a significant win for Jensen Huang and NVIDIA's AI portfolio. Coverage is commentary-tier aggregation rather than primary technical reporting.
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
This Hugging Face blog post details a workflow for fine-tuning NVIDIA's Cosmos Predict 2.5 world model using LoRA and DoRA parameter-efficient techniques for robot video generation tasks. The post covers practical implementation steps for adapting the foundation video model to robotics-specific domains. This represents a concrete application of world models to embodied AI, where synthetic video generation can support robot training data pipelines.
Nvidia Nemotron 3 Ultra: hybrid Mamba-transformer open-weights model targeting agentic workloads
Nvidia released Nemotron 3 Ultra, a 550B parameter (55B active) hybrid Mamba-transformer mixture-of-experts model with a 1M token context window, publishing weights, training data, and RL environments under an open license. The model ranks as the highest-scoring U.S. open-weights model on the Artificial Analysis Intelligence Index (47.7-48.2) and is approximately three times faster than comparable open-weights rivals, though it trails leading Chinese models like Kimi K2.6 and DeepSeek V4 Pro on intelligence benchmarks. Nvidia used a novel Multi-Teacher On-Policy Distillation approach with 10+ specialized teacher models and trained using NVFP4 quantization. The release is strategically motivated by Nvidia's interest in a healthy open-weights ecosystem that drives AI semiconductor adoption.
Introducing OpenAI o3 and o4-mini
OpenAI has released o3 and o4-mini, described as their smartest and most capable models to date. Both models ship with full tool access, representing a significant step in integrating reasoning models with agentic capabilities. The announcement comes from OpenAI's official blog, marking a major frontier model release.
OpenAI o3-mini Release
OpenAI has released o3-mini, a smaller and more efficient variant of its o3 reasoning model. The announcement comes from OpenAI's official blog, indicating a formal product launch. As a tier-1 source announcement, this represents a significant addition to OpenAI's model lineup, targeting cost-effective reasoning capabilities. Further technical details about benchmarks, context length, and pricing are expected in the full release documentation.