NVIDIA AI's banner

NVIDIA AI

@NVIDIAAI • 336,394 subscribers

Teaching your AI new tricks.

Shorts

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

761,701 görüntüleme

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

340,312 görüntüleme

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →

Happy Friday! We just put DeepSeek-V4-Pro up on It’s the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →

206,258 görüntüleme

What if your model handled its own tuning? ⚙️ With NVIDIA TAO 7, just prompt your coding agent what you want in plain language and let it do the rest. • Agent skills plug into your coding agent and improve accuracy. • AutoML removes the guesswork from hyperparameters. LLM-guided tuning finds strong configs up to 2x faster. • Fine-tune any Hugging Face CV or VLM model on local NVIDIA GPUs. • Data enhanced fine-tuning helps your agent identify why the model fails, then fix it. Try TAO skills ➡️

What if your model handled its own tuning? ⚙️ With NVIDIA TAO 7, just prompt your coding agent what you want in plain language and let it do the rest. • Agent skills plug into your coding agent and improve accuracy. • AutoML removes the guesswork from hyperparameters. LLM-guided tuning finds strong configs up to 2x faster. • Fine-tune any Hugging Face CV or VLM model on local NVIDIA GPUs. • Data enhanced fine-tuning helps your agent identify why the model fails, then fix it. Try TAO skills ➡️

42,238 görüntüleme

Artificial Analysis Image-to-video generation is just as impressive. Input image: "Generate a 16:9 image from a dashcam view of a formula 1 racing event" Video prompt: "A high-speed racing event where a car navigates multiple winding turns" 🔊 Sound on - generated by Cosmos 3.

Artificial Analysis Image-to-video generation is just as impressive. Input image: "Generate a 16:9 image from a dashcam view of a formula 1 racing event" Video prompt: "A high-speed racing event where a car navigates multiple winding turns" 🔊 Sound on - generated by Cosmos 3.

49,260 görüntüleme

“Every enterprise needs a claw strategy.” How did LangChain go from a weekend project to 1B+ downloads in 3 years? We sat down with CEO and co-founder Harrison Chase (Harrison Chase) to talk deep agents, evolving agent architectures, and what’s coming next. 🎧 Full episode:

“Every enterprise needs a claw strategy.” How did LangChain go from a weekend project to 1B+ downloads in 3 years? We sat down with CEO and co-founder Harrison Chase (Harrison Chase) to talk deep agents, evolving agent architectures, and what’s coming next. 🎧 Full episode:

47,817 görüntüleme

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

28,364 görüntüleme

Factories are getting a new AI brain 🧠 Introducing NVIDIA Factory Operations Blueprint (FOX), a reference design for building factory manager agents that monitor operations, reason across real-time data, and coordinate specialized AI agents to help resolve issues at scale. Early adopters including Hon Hai Technology Group (Foxconn), Pegatron, Advantech USA, and Wistron AiEdge Corporation are already seeing gains in productivity, quality, and efficiency. Read more: #NVIDIAGTC

Factories are getting a new AI brain 🧠 Introducing NVIDIA Factory Operations Blueprint (FOX), a reference design for building factory manager agents that monitor operations, reason across real-time data, and coordinate specialized AI agents to help resolve issues at scale. Early adopters including Hon Hai Technology Group (Foxconn), Pegatron, Advantech USA, and Wistron AiEdge Corporation are already seeing gains in productivity, quality, and efficiency. Read more: #NVIDIAGTC

25,688 görüntüleme

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗

With 3M+ downloads and counting, NVIDIA Cosmos is redefining physical AI. Announced at #CORL25, new Cosmos updates are allowing developers to generate diverse data for accelerating training robot models at scale. 👏 Cosmos Predict 2.5 will combine three models into one powerful model—reducing complexity, powering up to 30s video generation, and enabling multi-view simulations. 👏 Cosmos Transfer 2.5 will be 3.5x smaller yet faster and sharper—generating photorealistic synthetic data from 3D scenes or spatial inputs. 🔗

40,359 görüntüleme

The next wave of AI agents won’t just read text—they’ll reason over video and extract actionable insights.💡 In this #NVIDIAGTC session, be the first to hear about the new features powering visual AI agents with NVIDIA Blueprint for Video Search and Summarization (VSS), open VLMs including the latest Cosmos Reason, for development across edge, on‑prem, and cloud workloads. Add to schedule 👉 📅 Tues, March 17 | 10:00 a.m PT Speakers🎤: Roopa Prabhu and Adam Ryason

The next wave of AI agents won’t just read text—they’ll reason over video and extract actionable insights.💡 In this #NVIDIAGTC session, be the first to hear about the new features powering visual AI agents with NVIDIA Blueprint for Video Search and Summarization (VSS), open VLMs including the latest Cosmos Reason, for development across edge, on‑prem, and cloud workloads. Add to schedule 👉 📅 Tues, March 17 | 10:00 a.m PT Speakers🎤: Roopa Prabhu and Adam Ryason

12,850 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.

Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.

1,328,577 görüntüleme • 3 ay önce

Already running an inference engine? So where does NVIDIA Dynamo fit in? In five minutes, we break down how Dynamo sits around engines like SGLang, vLLM and TensorRT-LLM to scale inference across GPUs and nodes. Full video in the comments 🔽

Already running an inference engine? So where does NVIDIA Dynamo fit in? In five minutes, we break down how Dynamo sits around engines like SGLang, vLLM and TensorRT-LLM to scale inference across GPUs and nodes. Full video in the comments 🔽

29,221 görüntüleme • 4 gün önce

Introducing Cosmos 3 Edge: our open frontier world model built to run on-device. Cosmos 3 Edge helps robots learn and act, autonomous vehicles understand road scenes and predict intent, and vision AI agents reason across live video for smart infrastructure. With 4B parameters and a 2B Nemotron-based reasoner, you can run it on DGX Spark, NVIDIA Jetson, and more.

Introducing Cosmos 3 Edge: our open frontier world model built to run on-device. Cosmos 3 Edge helps robots learn and act, autonomous vehicles understand road scenes and predict intent, and vision AI agents reason across live video for smart infrastructure. With 4B parameters and a 2B Nemotron-based reasoner, you can run it on DGX Spark, NVIDIA Jetson, and more.

211,319 görüntüleme • 1 ay önce

Introducing Cosmos 3: Our latest frontier model for Physical AI Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation. Today we’re releasing Super (32B) and Nano (8B) variants.

Introducing Cosmos 3: Our latest frontier model for Physical AI Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation. Today we’re releasing Super (32B) and Nano (8B) variants.

427,728 görüntüleme • 3 ay önce

Nemotron 3 Ultra is coming this week. ⌛️

Nemotron 3 Ultra is coming this week. ⌛️

395,480 görüntüleme • 3 ay önce

Meet Nemotron 3 Nano Omni 👋 Our latest addition to the Nemotron family is the highest efficiency, open multimodal model with leading accuracy. 30B parameters. 256K context length. 🧵👇

Meet Nemotron 3 Nano Omni 👋 Our latest addition to the Nemotron family is the highest efficiency, open multimodal model with leading accuracy. 30B parameters. 256K context length. 🧵👇

460,565 görüntüleme • 4 ay önce

Most motion papers tailor one controller to one specific task. This year at SIGGRAPH, our research team asks: can motor control itself be pretrained and reused? Generative Pretrained Controllers, or GPC, turn motor skills into a vocabulary of discrete tokens and train a transformer-based generative controller through next-token prediction. Just like GPT, the same pretrained controller can then be fine-tuned to solve new tasks. Trained on 600+ hours of motion, GPC runs in real-time inside a physics simulation, producing natural and physically grounded behaviors for interactive control.

Most motion papers tailor one controller to one specific task. This year at SIGGRAPH, our research team asks: can motor control itself be pretrained and reused? Generative Pretrained Controllers, or GPC, turn motor skills into a vocabulary of discrete tokens and train a transformer-based generative controller through next-token prediction. Just like GPT, the same pretrained controller can then be fine-tuned to solve new tasks. Trained on 600+ hours of motion, GPC runs in real-time inside a physics simulation, producing natural and physically grounded behaviors for interactive control.

175,965 görüntüleme • 2 ay önce

When it comes to Chess, Vidit Gujrathi is an absolute legend. Recently, he entered the Hermes Agent Accelerated Business Hackathon to see who could build the best agent using Nemotron. Here's what he submitted. Special thanks to Stripe & Nous Research 🤝

When it comes to Chess, Vidit Gujrathi is an absolute legend. Recently, he entered the Hermes Agent Accelerated Business Hackathon to see who could build the best agent using Nemotron. Here's what he submitted. Special thanks to Stripe & Nous Research 🤝

155,874 görüntüleme • 1 ay önce

3D scene reconstruction works great until the camera never sees part of the scene. ArtiFixer from NVIDIA Research is an open autoregressive model that fills in the missing geometry that other methods leave blank. #SIGGRAPH2026 paper, code + demo:

3D scene reconstruction works great until the camera never sees part of the scene. ArtiFixer from NVIDIA Research is an open autoregressive model that fills in the missing geometry that other methods leave blank. #SIGGRAPH2026 paper, code + demo:

155,494 görüntüleme • 2 ay önce

NVIDIA Metropolis Blueprint for video search and summarization (VSS) 3 is here. Now your coding agent can analyze massive live streams and libraries of videos with a simple natural language prompt. Here's what's new: - 16 new agent skills: Search, summarize, alert, report, review clips. All from natural language prompts. - One unified open source repo: Source code, Docker and Helm deployment profiles for fast, easy deployment. - Multi-video reports and Nemotron 3 Nano Omni: Insights across video and audio at scale. - 3D multi-camera tracking: Production ready + #1 SOTA for smarter scene understanding. Try VSS skills 👉

NVIDIA Metropolis Blueprint for video search and summarization (VSS) 3 is here. Now your coding agent can analyze massive live streams and libraries of videos with a simple natural language prompt. Here's what's new: - 16 new agent skills: Search, summarize, alert, report, review clips. All from natural language prompts. - One unified open source repo: Source code, Docker and Helm deployment profiles for fast, easy deployment. - Multi-video reports and Nemotron 3 Nano Omni: Insights across video and audio at scale. - 3D multi-camera tracking: Production ready + #1 SOTA for smarter scene understanding. Try VSS skills 👉

125,310 görüntüleme • 2 ay önce

When AI understands your entire enterprise, everything gets smarter. 🎙️Join amit as he sits down with Justin Boitano (VP of Enterprise AI, NVIDIA) and Kevin Kawasaki (Head of Business Development, Palantir) to reveal how pairing NVIDIA accelerated computing with Palantir’s ontology lets companies optimize supply chains, react to disruptions instantly, and deploy LLMs that improve real-world outcomes, from hospitals to retail networks. ▶️ Watch the full interview:

When AI understands your entire enterprise, everything gets smarter. 🎙️Join amit as he sits down with Justin Boitano (VP of Enterprise AI, NVIDIA) and Kevin Kawasaki (Head of Business Development, Palantir) to reveal how pairing NVIDIA accelerated computing with Palantir’s ontology lets companies optimize supply chains, react to disruptions instantly, and deploy LLMs that improve real-world outcomes, from hospitals to retail networks. ▶️ Watch the full interview:

217,999 görüntüleme • 8 ay önce

One image + text + camera trajectory = controllable worlds. All on a single GPU. Our research team just released SANA-WM, a 2.6B open source world model natively trained for 60-second video generation with precise camera control.

One image + text + camera trajectory = controllable worlds. All on a single GPU. Our research team just released SANA-WM, a 2.6B open source world model natively trained for 60-second video generation with precise camera control.

93,154 görüntüleme • 3 ay önce

Teach an agent a workflow once. Have it remember after every rebuild. This tutorial shows how to deploy Nous Research Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, GitHub, and NVIDIA developer forums, then turn a chat correction into a reusable skill. Private data stays behind runtime policies. Learned skills persist across deployments.

Teach an agent a workflow once. Have it remember after every rebuild. This tutorial shows how to deploy Nous Research Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, GitHub, and NVIDIA developer forums, then turn a chat correction into a reusable skill. Private data stays behind runtime policies. Learned skills persist across deployments.

70,337 görüntüleme • 3 ay önce

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

Say hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back a detailed report with citations. See it in Codex below 👇

76,354 görüntüleme • 3 ay önce

Open source isn't just good for developers, it's one of America's strongest tools for AI security. More models means more defenders and more front doors protected. Earlier this week at the Milken Institute Global Conference, Jensen sat down with Becky Quick to explain why 👇

Open source isn't just good for developers, it's one of America's strongest tools for AI security. More models means more defenders and more front doors protected. Earlier this week at the Milken Institute Global Conference, Jensen sat down with Becky Quick to explain why 👇

75,716 görüntüleme • 3 ay önce

ICYMI: Not every step in an agent workflow needs the same model. Meet NVIDIA NeMo Switchyard, a new open-source library for model routing. Use frontier models for complex reasoning and planning, and NVIDIA Nemotron Lightning for high-volume, specialized execution.

ICYMI: Not every step in an agent workflow needs the same model. Meet NVIDIA NeMo Switchyard, a new open-source library for model routing. Use frontier models for complex reasoning and planning, and NVIDIA Nemotron Lightning for high-volume, specialized execution.

14,777 görüntüleme • 19 gün önce

Long video generation is a systems problem. Introducing LongLive-2.0 from NVIDIA Research: an end-to-end NVFP4 training and inference system for long video generation. Low-precision deployment often relies on post-training quantization, creating a gap between how models are trained and how they run. LongLive-2.0 aligns NVFP4-aware training, distillation, and W4A4 inference, maintaining strong benchmark quality while improving speed and memory efficiency.

Long video generation is a systems problem. Introducing LongLive-2.0 from NVIDIA Research: an end-to-end NVFP4 training and inference system for long video generation. Low-precision deployment often relies on post-training quantization, creating a gap between how models are trained and how they run. LongLive-2.0 aligns NVFP4-aware training, distillation, and W4A4 inference, maintaining strong benchmark quality while improving speed and memory efficiency.

60,687 görüntüleme • 3 ay önce

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

31,412 görüntüleme • 1 ay önce

💡Industries are scaling AI like never before. To help organizations extract maximum value, NVIDIA systems are built to deliver unmatched performance at AI factory scale. ⚙️ The latest InferenceMAX v1 benchmarks confirm: 💥 10× more performance per watt, translating to lower costs and greater energy efficiency 📈 15x more ROI across manufacturing, energy, healthcare, and beyond. Learn more:

💡Industries are scaling AI like never before. To help organizations extract maximum value, NVIDIA systems are built to deliver unmatched performance at AI factory scale. ⚙️ The latest InferenceMAX v1 benchmarks confirm: 💥 10× more performance per watt, translating to lower costs and greater energy efficiency 📈 15x more ROI across manufacturing, energy, healthcare, and beyond. Learn more:

114,261 görüntüleme • 10 ay önce

"Data stops being something you collect. It becomes something you compute." At #SIGGRAPH2026, Ming-Yu Liu, VP of NVIDIA's Cosmos Lab, laid out why world models are the data engine of physical AI. Plus, he announced Cosmos-Dreams, a neural closed-loop simulator, and showed off a full demo of it in action. You can watch the full keynote here:

"Data stops being something you collect. It becomes something you compute." At #SIGGRAPH2026, Ming-Yu Liu, VP of NVIDIA's Cosmos Lab, laid out why world models are the data engine of physical AI. Plus, he announced Cosmos-Dreams, a neural closed-loop simulator, and showed off a full demo of it in action. You can watch the full keynote here:

15,693 görüntüleme • 1 ay önce