🤖 Does VLA models really listen to language instructions?... Maybe not 👀 🚀 Introducing our RSS paper: CodeDiffuser -- using VLM-generated code to bridge the gap between **high-level language** and **low-level visuomotor policy** 🎮 Try the live demo: (1/9)show more

Is a single accuracy number all we can get... from model evals?🤔 🚨Does NOT tell where the model fails 🚨Does NOT tell how to improve it Introducing EvalTree🌳 🔍identifying LM weaknesses in natural language 🚀weaknesses serve as actionable guidance (paper&demo 🔗in🧵) [1/n]show more

🚀How to scale up robotic simulation tasks? We announce... GenSim: Generating Robotic Simulation Tasks via Large Language Models. Website ( arxiv ( and Gradio demo ( are all out! Try out the Gradio demo🤗!show more

Want to bring open-source vision language models to the... edge? 💻 Check out our Hugging Face article on deploying NVIDIA Cosmos Reasoning 2B across the NVIDIA Jetson family with vLLM and a Live VLM WebUI. 📖show more

🎙️MiniCPM-o 4.5: Full-duplex interaction in motion. Watch the 9B... model track and identify fruit price tags in a dynamic live stream. Unlike traditional reactive systems, MiniCPM-o 4.5 processes continuous video and audio inputs to see, listen, and respond simultaneously—without mutual blocking. 🚀This end-to-end architecture enables low-latency, proactive feedback even while the device is moving, bridging the gap between static vision-language tasks and real-world live interaction. Try the demo and share your feedback with us! Hugging Face 👉 #MiniCPMo45 #MLLM #EdgeAI #OpenSourceshow more

"If Marathi has been granted classical language status and... the cow declared Rajyamata, should we now accept the cow’s mooing as the state language?" ~ Uddhav Thackeray. He stoops to such a low level merely to appease a vote bank.show more

Introducing our new family of state-of-the-art AI models: Phoenix-3,... Raven-0, and Sparrow-0. Together they bring Conversational Video Interfaces (CVI) to the next level, and power Charlie, our new demo persona 👋show more

🚨 We're very happy to introduce TRIBE v2: a... foundation model of the brain's responses to sight, sound & language. 📄 Paper: ▶️ Demo: 💻 Code: 🤗 Model:show more

I'm beginning to think of the French language on... a similar level to Dutch.show more

✨🧠 Tribe v2, our latest model of human brain... responses to sound, sight and language can now be (partly) explored on your phone📱: ▶️demo: 📄paper: 💻code:show more

Can Vision-Language Models Solve the Shell Game? paper:

What comes after vision-language-action models in robotics? 🤖 Join... NVIDIA researchers live to explore World Action Models (WAMs), Vision-Language-Action models (VLAs), and hybrid robot foundation models, and see how NVIDIA Cosmos 3 natively represents action alongside video. 🕑 Thursday, Aug. 13 • 9:00–10:00 a.m. PT 📅Add calendar:show more

Are you ready to take your gameplay to the... next level?🎮🔥 Introducing the fusion system in #CelestiaUltimateshow more

A semi-truck recently wrecked its trailer on the High... Level Bridge in Edmonton, forcing the bridge to close.show more

Introducing ✨ Aya Vision ✨ - an open-weights model... to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿show more

Scaling laws describe how loss changes with scale. Do... neurons inside models change predictably too? We study vision and language models up to 30B params and find systematic scaling in neuron universality, specialization, and selectivity. Paper+code: 1/nshow more

Introducing ✨Aya Expanse ✨ – an open-weights state-of-art family... of models to help close the language gap with AI. Aya Expanse is both global and local. Driven by a multi-year commitment to multilingual research.show more

1/ Happy to share VADER: Video Diffusion Alignment via... Reward Gradients. We adapt foundational video diffusion models using pre-trained reward models to generate high-quality, aligned videos for various end-applications. Below we generated a short movie using VADER 😀, we used ChatGPT to write a script and an off-the-shelf AI music generator to generate the sound. Our code & weights are open-sourced:show more

We’re releasing model weights for our 8B- parameter Dynamic... Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.show more

5 straight wins. 9-1 in their last 10. 2nd... in the East. High-level hoops from the Raptors 👀show more

See how Gemini 3 Flash and Vision-Language-Action (VLA) models... work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎show more