Pranjali Joshi – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2025-06-17T19:22:23Z http://www.open-lab.net/blog/feed/ Pranjali Joshi <![CDATA[Develop Custom Physical AI Foundation Models with NVIDIA Cosmos Predict-2]]> http://www.open-lab.net/blog/?p=101575 2025-06-17T19:21:54Z 2025-06-11T11:00:00Z Building smarter robots and autonomous vehicles (AVs) starts with physical AI models that understand real-world dynamics. These models serve two critical roles:...]]>

Building smarter robots and autonomous vehicles (AVs) starts with physical AI models that understand real-world dynamics. These models serve two critical roles: accelerating synthetic data generation (SDG) to help autonomous machines learn about real-world physics and interactions—including rare edge cases—and serving as base models that can be post-trained for specialized tasks or adapted to…

Source

]]>
Pranjali Joshi <![CDATA[Curating Synthetic Datasets to Train Physical AI Models with NVIDIA Cosmos Reason]]> http://www.open-lab.net/blog/?p=100308 2025-06-17T19:22:23Z 2025-05-19T04:45:57Z How can an AI system understand the difference between a plausible accident and a physically impossible event? Or plan a multi-step interaction across humans,...]]>

How can an AI system understand the difference between a plausible accident and a physically impossible event? Or plan a multi-step interaction across humans, objects, and environments in an edge-case scenario? These are questions at the core of physical intelligence—the kind that underpin how robots manipulate the world, how autonomous vehicles make split-second decisions, and how virtual agents…

Source

]]>
Pranjali Joshi <![CDATA[Scale Synthetic Data and Physical AI Reasoning with NVIDIA Cosmos World Foundation Models]]> http://www.open-lab.net/blog/?p=97132 2025-04-23T00:31:38Z 2025-03-18T16:00:47Z The next generation of AI-driven robots like humanoids and autonomous vehicles depends on high-fidelity, physics-aware training data. Without diverse and...]]>

The next generation of AI-driven robots like humanoids and autonomous vehicles depends on high-fidelity, physics-aware training data. Without diverse and representative datasets, these systems don’t get proper training and face testing risks due to poor generalization, limited exposure to real-world variations, and unpredictable behavior in edge cases. Collecting massive real-world datasets for…

Source

]]>
Pranjali Joshi <![CDATA[Advancing Physical AI with NVIDIA Cosmos World Foundation Model Platform]]> http://www.open-lab.net/blog/?p=94577 2025-01-23T19:54:31Z 2025-01-09T17:42:06Z As robotics and autonomous vehicles advance, accelerating development of physical AI��which enables autonomous machines to perceive, understand, and perform...]]>

As robotics and autonomous vehicles advance, accelerating development of physical AI—which enables autonomous machines to perceive, understand, and perform complex actions in the physical world—has become essential. At the center of these systems are world foundation models (WFMs)—AI models that simulate physical states through physics-aware videos, enabling machines to make accurate decisions and…

Source

]]>
1
Pranjali Joshi <![CDATA[State-of-the-Art Multimodal Generative AI Model Development with NVIDIA NeMo]]> http://www.open-lab.net/blog/?p=91184 2025-01-13T17:19:42Z 2024-11-06T16:00:00Z Generative AI has rapidly evolved from text-based models to multimodal capabilities. These models perform tasks like image captioning and visual question...]]>

Generative AI has rapidly evolved from text-based models to multimodal capabilities. These models perform tasks like image captioning and visual question answering, reflecting a shift toward more human-like AI. The community is now expanding from text and images to video, opening new possibilities across industries. Video AI models are poised to revolutionize industries such as robotics…

Source

]]>
Pranjali Joshi <![CDATA[Join the First NVIDIA LLM Developer Day: Elevate Your App-Building Skills]]> http://www.open-lab.net/blog/?p=72618 2023-11-16T19:16:46Z 2023-11-06T21:37:40Z NVIDIA LLM Developer Day is a virtual event providing hands-on guidance for developers exploring and building LLM-based applications and services. You can gain...]]>

NVIDIA LLM Developer Day is a virtual event providing hands-on guidance for developers exploring and building LLM-based applications and services. You can gain an understanding ‌of key technologies, their pros and cons, and explore example applications. The sessions also cover how to create, customize, and deploy applications using managed APIs, self-managed LLMs…

Source

]]>
0
Pranjali Joshi <![CDATA[AI Models Recap: Scalable Pretrained Models Across Industries]]> http://www.open-lab.net/blog/?p=58341 2023-06-12T08:23:57Z 2022-12-07T19:32:20Z The year 2022 has thus far been a momentous, thrilling, and an overwhelming year for AI aficionados. Get3D is pushing the boundaries of generative 3D modeling,...]]>

The year 2022 has thus far been a momentous, thrilling, and an overwhelming year for AI aficionados. Get3D is pushing the boundaries of generative 3D modeling, an AI model can now diagnose breast cancer from MRIs as accurately as board-certified radiologists, and state-of-the-art speech AI models have widened their horizons to extended reality. Pretrained models from NVIDIA have redefined…

Source

]]>
0
Pranjali Joshi <![CDATA[Building an Automatic Speech Recognition Model for the Kinyarwanda Language]]> http://www.open-lab.net/blog/?p=56301 2023-11-03T07:15:08Z 2022-10-20T14:30:00Z Speech recognition technology is growing in popularity for voice assistants and robotics, for solving real-world problems through assisted healthcare or...]]>

Speech recognition technology is growing in popularity for voice assistants and robotics, for solving real-world problems through assisted healthcare or education, and more. This is helping democratize access to speech AI worldwide. As labeled datasets for unique, emerging languages become more widely available, developers can build AI applications readily, accurately, and affordably to enhance…

Source

]]>
0
���˳���97caoporen����