We built an AI model to simulate how a fruit fly walks, flies and behaves – in partnership with @HHMIJanelia. 🪰
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. 🧵
To create it, we turned to MuJoCo, our open-source physics simulator – created for robotics and biomechanics – and added features such as:
▪️simulating fluid forces on the flapping wings, enabling flight
▪️adhesion actuators – mimicking the gripping force of insect feet
We then trained an artificial neural network on real fly behavior from recorded videos 🎥 and let it control the model in MuJoCo.
This enables it to learn how to move the virtual insect in the most realistic way.
Here, the fly shows accurate movement along complex natural flight trajectories.
Watch how it’s instructed to follow a real path marked by the blue dots. 🔵🪰🔵
So why build these kinds of models?
We believe they could help scientists better understand how the brain, body and environment drive specific behaviors in an animal – finding connections that labs can't always measure. 🥼
We’ve already applied this approach to multiple organisms – a virtual rodent, and now a fruit fly.
So what comes next for neuroscientists? The zebrafish – a widely studied creature which shares 70% of its protein-coding genes with humans. 🐠
We’re announcing a major advance in the study of fluid dynamics with AI 💧 in a joint paper with researchers from @BrownUniversity, @nyuniversity and @Stanford.
Equations to describe fluid motion - like airflow lifting an airplane wing or the swirling vortex of a hurricane - can sometimes "break," predicting impossible, infinite values.
These "singularities" are a huge mystery in mathematical physics.
We used a new AI-powered method to discover new families of unstable “singularities” across three different fluid equations.
A clear and unexpected pattern emerged: as the solutions become more unstable, one of the key properties falls very close to a straight line.
This suggests a new, underlying structure to these equations that was previously invisible.
We’re helping to unlock the mysteries of the universe with AI. 🌌
Our novel Deep Loop Shaping method
published in @ScienceMagazine could help astronomers observe more events like collisions and mergers of black holes in greater detail, and gather more data about rare space phenomena. 🧵
Astronomers already know a lot about the smallest and largest black holes. ⚫
But we have limited data on intermediate-mass black holes, and the observatories we use to measure their gravitational waves need improved control, and expanded reach. ↓ goo.gle/47oalza
⚡This is where Deep Loop Shaping comes in.
Developed in collaboration with @LIGO Laser Interferometer Gravitational-Wave Observatory, @CalTech and the Gran Sasso Science Institute, it reduces noise and improves control in an observatory’s feedback system - helping stabilize components used for measuring gravitational waves.
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 🧵
🎯 Character consistency
Give the model reference images and it can produce new visuals that maintain a character, subject or object’s likeness across different poses, lighting, environments or styles - helping you create more compelling, narrative-driven work.
🔄 Design application
Looking to apply a specific artistic style, design, or texture? 2.5 Flash can now easily transfer this from one image to another while preserving the previous subject's form and details.
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. 🧵
By transforming each ancient text into a unique historical fingerprint, Aeneas can identify similarities across 176,000 Latin inscriptions.
In our study, historians found these ‘parallels’ to be helpful research starting points 9 out of 10 times - improving their confidence by 44%.
We tested Aeneas on the Res Gestae Divi Augusti – one of the most debated inscriptions.
Without prior knowledge, it successfully mapped out the leading scholarly theories on its dating, showing how AI can help model history in a quantitative way. 📊
We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖
It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵
What makes this new model unique?
🔵 It has the generality and dexterity of Gemini Robotics - but it can run locally on the device
🔵 It can handle a wide variety of complex, two-handed tasks out of the box
🔵 It can learn new skills with as few as 50-100 demonstrations
From humanoids to industrial bi-arm robots, the model supports multiple embodiments, even though it was pre-trained on ALOHA - while following instructions from humans. 💬
These tasks may seem easy for us but require fine motor skills, precise manipulation and more. ↓
Anyone can now use 2.5 Flash and Pro to build and scale production-ready AI applications. 🙌
We’re also launching 2.5 Flash-Lite in preview: the fastest model in the 2.5 family to respond to requests, with the lowest cost too. 🧵
2.5 Flash-Lite now supports:
🔹Thinking: improving performance and transparency through step-by-step reasoning
🔹Tool-use: including Search, code execution and 1 million token context window - similar to 2.5 Flash and Pro
⚡ 2.5 Flash-Lite is our most cost efficient model yet - and with lower latency than 2.0 Flash-Lite and Flash on a broad sample of prompts.
It also has all-around, higher quality than 2.0 Flash-Lite on coding, math, science, reasoning and multimodal benchmarks.