Google DeepMind's banner
Google DeepMind's profile picture

Google DeepMind

@GoogleDeepMind • 1,512,790 subscribers

The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL

Shorts

SL2T is our breakthrough sign language-to-text model powering new features for Deaf and hard of hearing users on Android. Starting with American Sign Language-to-English on Pixel 11, people can sign directly into Gboard and Live Transcribe instead of typing.

SL2T is our breakthrough sign language-to-text model powering new features for Deaf and hard of hearing users on Android. Starting with American Sign Language-to-English on Pixel 11, people can sign directly into Gboard and Live Transcribe instead of typing.

387,059 views

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵

Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity. A quick dive into Gemini 2.5 Flash’s capabilities 🧵

1,483,468 views

We built an AI model to simulate how a fruit fly walks, flies and behaves – in partnership with HHMI | Janelia. 🪰 Our computerized insect replicates realistic motion, and can even use its eyes to control its actions. Here’s how we developed it – and what it means for science. 🧵

We built an AI model to simulate how a fruit fly walks, flies and behaves – in partnership with HHMI | Janelia. 🪰 Our computerized insect replicates realistic motion, and can even use its eyes to control its actions. Here’s how we developed it – and what it means for science. 🧵

1,057,224 views

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

1,467,952 views

We just dropped Lyria 3: our latest generative music model. 🔊 It can turn photos and text into dynamic tracks - complete with vocals and lyrics. 🧵

We just dropped Lyria 3: our latest generative music model. 🔊 It can turn photos and text into dynamic tracks - complete with vocals and lyrics. 🧵

341,280 views

Powered by Gemini 3, the YouTube Playables Builder web app can help creators develop fun, bite-sized games with text, video or image prompts. 🕹️ Find out more →

Powered by Gemini 3, the YouTube Playables Builder web app can help creators develop fun, bite-sized games with text, video or image prompts. 🕹️ Find out more →

397,710 views

Our new state-of-the-art AI model Aeneas transforms how historians connect the past. 📜 Ancient inscriptions often lack context – it's like solving a puzzle with 90% of the pieces lost to time. It helps researchers interpret and situate inscriptions in their past context. 🧵

Our new state-of-the-art AI model Aeneas transforms how historians connect the past. 📜 Ancient inscriptions often lack context – it's like solving a puzzle with 90% of the pieces lost to time. It helps researchers interpret and situate inscriptions in their past context. 🧵

555,373 views

SIMA 2 🤝 Genie 3 We tested SIMA 2’s abilities in simulated 3D worlds created by our world model Genie 3. It demonstrated unprecedented adaptability by navigating its surroundings and took meaningful steps toward goals.

SIMA 2 🤝 Genie 3 We tested SIMA 2’s abilities in simulated 3D worlds created by our world model Genie 3. It demonstrated unprecedented adaptability by navigating its surroundings and took meaningful steps toward goals.

271,752 views

Veo is getting new precision editing capabilities that let you easily add or remove elements from a scene - all while preserving the integrity of your original video. 🎥

Veo is getting new precision editing capabilities that let you easily add or remove elements from a scene - all while preserving the integrity of your original video. 🎥

266,892 views

We're sharing progress on our video-to-audio (V2A) generative technology. 🎥 It can add sound to silent clips that match the acoustics of the scene, accompany on-screen action, and more. Here are 4 examples - turn your sound on. 🧵🔊

We're sharing progress on our video-to-audio (V2A) generative technology. 🎥 It can add sound to silent clips that match the acoustics of the scene, accompany on-screen action, and more. Here are 4 examples - turn your sound on. 🧵🔊

529,363 views

Veo 2 is more than just a video generation tool in @GoogleCloud’s #VertexAI. 🎥 Here’s a rundown of its features. 🧵

Veo 2 is more than just a video generation tool in @GoogleCloud’s #VertexAI. 🎥 Here’s a rundown of its features. 🧵

335,273 views

Extract – a system built by the UK government, using our Gemini foundational model – will help council planners make faster decisions. 🚀 Using multimodal reasoning, it turns complex planning documents – even handwritten notes and blurry maps – into digital data in just 40s. Find out more. ↓

Extract – a system built by the UK government, using our Gemini foundational model – will help council planners make faster decisions. 🚀 Using multimodal reasoning, it turns complex planning documents – even handwritten notes and blurry maps – into digital data in just 40s. Find out more. ↓

268,019 views

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵

Introducing 2️⃣ new AI systems for robotics: 🤖 ALOHA Unleashed to perform two-armed manipulation tasks 🦾 DemoStart to control a multi-fingered robotic hand They learned to tackle a range of actions requiring dexterity. Here's how. 🧵

297,295 views

Google Flow 🤝 Gemini Omni Create more cinematic stories with our latest model, which brings batch editing, improved character consistency and more. Here’s what else is new for Google Flow → #GoogleIO

Google Flow 🤝 Gemini Omni Create more cinematic stories with our latest model, which brings batch editing, improved character consistency and more. Here’s what else is new for Google Flow → #GoogleIO

57,823 views

Omni brings together an improved understanding of physics with Gemini's knowledge of history, biology, and culture, bridging the gap from photorealism to meaningful storytelling. Actions have consequences, environments respond to events, and narratives evolve logically.

Omni brings together an improved understanding of physics with Gemini's knowledge of history, biology, and culture, bridging the gap from photorealism to meaningful storytelling. Actions have consequences, environments respond to events, and narratives evolve logically.

55,368 views

The Gemini 2.0 era is here. And we’re excited for you to start building with it. A quick rewind of what we just released ⏪ Gemini 2.0 Flash ⚡ comes with low latency and better performance. 🔵 You can now access an experimental version in G3mini on the web, while Gemini Advanced users can try Deep Research, a new AI research assistant. 🔵 Developers can begin building through the Gemini API in Google AI Studio and Vertex AI 2.0 is also enabling new research prototypes of AI agents, including: 🔵 Project Astra, which explores future capabilities of a universal AI assistant 🔵 Project Mariner, which shows what’s possible for human-agent interaction, starting with your browser 🔵 Jules, an experimental AI-powered coding agent Finally, we’re exploring how 2.0 can be used in agents across domains — from navigating the virtual world of video games to applying its spatial reasoning capabilities to robotics. 🤖

The Gemini 2.0 era is here. And we’re excited for you to start building with it. A quick rewind of what we just released ⏪ Gemini 2.0 Flash ⚡ comes with low latency and better performance. 🔵 You can now access an experimental version in G3mini on the web, while Gemini Advanced users can try Deep Research, a new AI research assistant. 🔵 Developers can begin building through the Gemini API in Google AI Studio and Vertex AI 2.0 is also enabling new research prototypes of AI agents, including: 🔵 Project Astra, which explores future capabilities of a universal AI assistant 🔵 Project Mariner, which shows what’s possible for human-agent interaction, starting with your browser 🔵 Jules, an experimental AI-powered coding agent Finally, we’re exploring how 2.0 can be used in agents across domains — from navigating the virtual world of video games to applying its spatial reasoning capabilities to robotics. 🤖

231,798 views

So our 45-person team developed entirely new AI capabilities, enabling them to: 🎨 Fine-tune custom Veo and Imagen models on their paintings and artwork 📹 Provide a desired look through rough animations, which the models transformed into stylized videos 🎭 Edit specific regions without regenerating entire shots from scratch

So our 45-person team developed entirely new AI capabilities, enabling them to: 🎨 Fine-tune custom Veo and Imagen models on their paintings and artwork 📹 Provide a desired look through rough animations, which the models transformed into stylized videos 🎭 Edit specific regions without regenerating entire shots from scratch

93,938 views

Since launching Veo 2, we’ve built new capabilities and addressed a few pain points to help filmmakers and creatives. 📽️✨ Here’s a quick rundown. 🧵

Since launching Veo 2, we’ve built new capabilities and addressed a few pain points to help filmmakers and creatives. 📽️✨ Here’s a quick rundown. 🧵

170,093 views

You can even reimagine the action in a video you took by asking Gemini Omni. Transform your world instantly - change the environment, add new objects, or create something completely unexpected.

You can even reimagine the action in a video you took by asking Gemini Omni. Transform your world instantly - change the environment, add new objects, or create something completely unexpected.

47,806 views

How could robotics soon help us in our daily lives? 🤖 Today, we’re announcing a suite of research advances that enable robots to make decisions faster as well as better understand and navigate their environments. Here's a snapshot of the work. 🧵

How could robotics soon help us in our daily lives? 🤖 Today, we’re announcing a suite of research advances that enable robots to make decisions faster as well as better understand and navigate their environments. Here's a snapshot of the work. 🧵

281,760 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

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

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

One brain. For any robot. 🤖 We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.
1:32
GoogleDeepMind's profile picture

One brain. For any robot. 🤖 We’re launching Gemini Robotics 2: our next-generation physical AI bringing full body intelligence to humanoids, advanced dexterity, multi-robot teamwork and more.

Google DeepMind

2,596,956 views • 1 month ago

We used Gemini 3.1 Pro to build a realistic city planner app. 🏙️ Watch how the model tackles complex terrain, maps out infrastructure, and simulates traffic to generate a high-quality visualization.
1:30
GoogleDeepMind's profile picture

We used Gemini 3.1 Pro to build a realistic city planner app. 🏙️ Watch how the model tackles complex terrain, maps out infrastructure, and simulates traffic to generate a high-quality visualization.

Google DeepMind

14,576,083 views • 6 months ago

SynthID, our imperceptible watermark for AI-generated content, is expanding to more partners. We’re also adding new ways to find out if content was generated using AI - just ask in the Google Gemini or in Google Search.
0:55
GoogleDeepMind's profile picture

SynthID, our imperceptible watermark for AI-generated content, is expanding to more partners. We’re also adding new ways to find out if content was generated using AI - just ask in the Google Gemini or in Google Search.

Google DeepMind

5,784,119 views • 3 months ago

Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎
2:02
GoogleDeepMind's profile picture

Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎

Google DeepMind

13,480,056 views • 7 months ago

We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵
0:54
GoogleDeepMind's profile picture

We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video. It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵

Google DeepMind

1,656,771 views • 3 months ago

We’re reimagining a 50-year-old interface - the mouse pointer - with AI. 🖱️ These experimental demos show how people can intuitively direct Gemini on their screens using motion, speech, and natural shorthand to get things done 🧵
0:57
GoogleDeepMind's profile picture

We’re reimagining a 50-year-old interface - the mouse pointer - with AI. 🖱️ These experimental demos show how people can intuitively direct Gemini on their screens using motion, speech, and natural shorthand to get things done 🧵

Google DeepMind

1,682,426 views • 3 months ago

We’ve upgraded our specialized reasoning mode Gemini 3 Deep Think to help solve modern science, research, and engineering challenges – pushing the frontier of intelligence. 🧠 Watch how the Wang Lab at Duke University is using it to design new semiconductor materials. 🧵
1:28
GoogleDeepMind's profile picture

We’ve upgraded our specialized reasoning mode Gemini 3 Deep Think to help solve modern science, research, and engineering challenges – pushing the frontier of intelligence. 🧠 Watch how the Wang Lab at Duke University is using it to design new semiconductor materials. 🧵

Google DeepMind

3,198,238 views • 6 months ago

From weather forecasting to robotics, intelligent decision-making relies on understanding the unknown. Our VP Research Zoubin Ghahramani explores with Hannah Fry why teaching systems self-doubt and probability can lead to safer, more reliable real-world decision-making. 🧠 Watch the episode ↓ Timecodes: 00:00 Introduction 01:06 The role of uncertainty 07:45 Correctness vs confidence 09:40 Historical perspectives 16:10 Bayesian thinking in AI 26:30 Uncertainty in the real world 36:42 Future research and AGI
44:40
GoogleDeepMind's profile picture

From weather forecasting to robotics, intelligent decision-making relies on understanding the unknown. Our VP Research Zoubin Ghahramani explores with Hannah Fry why teaching systems self-doubt and probability can lead to safer, more reliable real-world decision-making. 🧠 Watch the episode ↓ Timecodes: 00:00 Introduction 01:06 The role of uncertainty 07:45 Correctness vs confidence 09:40 Historical perspectives 16:10 Bayesian thinking in AI 26:30 Uncertainty in the real world 36:42 Future research and AGI

Google DeepMind

63,362 views • 5 days ago

Gemini 3.5 Transcribe is our latest speech-to-text model for precise and intelligent transcriptions. 🧵
0:35
GoogleDeepMind's profile picture

Gemini 3.5 Transcribe is our latest speech-to-text model for precise and intelligent transcriptions. 🧵

Google DeepMind

66,008 views • 6 days ago

Our short film Dear Upstairs Neighbors is previewing at Sundance Film Festival. 🎬 It’s a story about noisy neighbors, but behind the scenes, it’s about solving a huge challenge in generative AI: control. Developed by Pixar alumni, an Academy Award winner, researchers, and engineers, here’s how it came together. 🎨
1:06
GoogleDeepMind's profile picture

Our short film Dear Upstairs Neighbors is previewing at Sundance Film Festival. 🎬 It’s a story about noisy neighbors, but behind the scenes, it’s about solving a huge challenge in generative AI: control. Developed by Pixar alumni, an Academy Award winner, researchers, and engineers, here’s how it came together. 🎨

Google DeepMind

2,223,148 views • 7 months ago

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵
2:22
GoogleDeepMind's profile picture

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

Google DeepMind

3,737,439 views • 1 year ago

We sat down with Apollo 2 to talk about what it's really like running on Gemini Robotics 2. 🤖
0:49
GoogleDeepMind's profile picture

We sat down with Apollo 2 to talk about what it's really like running on Gemini Robotics 2. 🤖

Google DeepMind

176,184 views • 25 days ago

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐 Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵
1:36
GoogleDeepMind's profile picture

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐 Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵

Google DeepMind

1,923,337 views • 9 months ago

This is Gemini 3: our most intelligent model that helps you learn, build and plan anything. It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵
1:56
GoogleDeepMind's profile picture

This is Gemini 3: our most intelligent model that helps you learn, build and plan anything. It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵

Google DeepMind

1,694,718 views • 9 months ago

Watch how fast Gemini 3.1 Flash-Lite can generate websites. ⚡ This browser creates each page in real-time as you click, search, and navigate. Give it a try →
1:27
GoogleDeepMind's profile picture

Watch how fast Gemini 3.1 Flash-Lite can generate websites. ⚡ This browser creates each page in real-time as you click, search, and navigate. Give it a try →

Google DeepMind

840,637 views • 5 months ago

We just dropped Nano Banana Pro, built on Gemini 3. 🍌 With state-of-the-art text rendering, vast world knowledge and studio-quality creative controls, Gemini 3 Pro Image can create and edit more complex visuals, infographics and more. Here’s what’s under the hood. 🧵
1:18
GoogleDeepMind's profile picture

We just dropped Nano Banana Pro, built on Gemini 3. 🍌 With state-of-the-art text rendering, vast world knowledge and studio-quality creative controls, Gemini 3 Pro Image can create and edit more complex visuals, infographics and more. Here’s what’s under the hood. 🧵

Google DeepMind

1,465,080 views • 9 months ago

This is how Gemini Robotics 2 helps Apptronik’s Apollo 2 use whole body intelligence to pack for a sports game ↓
2:47
GoogleDeepMind's profile picture

This is how Gemini Robotics 2 helps Apptronik’s Apollo 2 use whole body intelligence to pack for a sports game ↓

Google DeepMind

142,440 views • 1 month ago

A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝 On the latest episode of our podcast, host Hannah Fry sits down with Neel Nanda to explore interpretability – the science of reverse engineering how neural networks learn and think. Timecodes: 00:00 Introduction 02:41 Motivation for interpretability research 04:01 Mechanistic interpretability 08:14 Chain of thought monitoring 18:14 Interpretability techniques 35:00 Auditing models for safety 48:53 What comes next for interpretability
53:05
GoogleDeepMind's profile picture

A model’s chain of thought acts like a scratch pad, offering a window into its reasoning. 📝 On the latest episode of our podcast, host Hannah Fry sits down with Neel Nanda to explore interpretability – the science of reverse engineering how neural networks learn and think. Timecodes: 00:00 Introduction 02:41 Motivation for interpretability research 04:01 Mechanistic interpretability 08:14 Chain of thought monitoring 18:14 Interpretability techniques 35:00 Auditing models for safety 48:53 What comes next for interpretability

Google DeepMind

213,181 views • 1 month ago

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵
0:27
GoogleDeepMind's profile picture

We’re rolling out an upgrade designed to help robots reason about the physical world. 🤖 Gemini Robotics-ER 1.6 has significantly better visual and spatial understanding in order to plan and complete more useful tasks. Here’s why this is important 🧵

Google DeepMind

557,313 views • 4 months ago

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵
0:33
GoogleDeepMind's profile picture

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵

Google DeepMind

470,406 views • 4 months ago