Instead of scanning an entire file, Gemini reasons across the video’s transcript, audio, and frames, dynamically adjusting the frame rate to pull the exact moments needed.
The efficiency gains are most significant for long-form content, from 10-minute guides to multi-hour
We’re bringing agentic video understanding to our latest Gemini models.
They can now analyze videos with better accuracy while using up to 88% fewer tokens. 🧵
We’re rolling out Gemini Omni 1.1 Flash to make generative video highly controllable, faster to iterate on, and more polished for production-grade use.
Here’s how you can try it in @FlowbyGoogle and more → https://goo.gle/4zHEzJ2
From weather forecasting to robotics, intelligent decision-making relies on understanding the unknown.
Our VP Research @ZoubinGhahrama1 explores with @fryrsquared why teaching systems self-doubt and probability can lead to safer, more reliable real-world decision-making. 🧠
In an industry first, we’re piloting double-blind evaluations for frontier AI.
By creating a secure environment where neither test prompts nor model weights are revealed, we can ensure external safety and performance evaluations of our models remain private, robust, and
Here’s what’s new:
🔵 It’s better at understanding complex phone numbers, postal codes, and order IDs – even in noisy environments.
🔵 It can remove filler words and auto-format your text.
🔵 It recognizes custom vocabulary so the model knows unique names and product titles.
🔵
Games have been an important testbed for our AI research for over 15 years. 🎮
From mastering Atari to reaching Grandmaster in StarCraft II, they have driven some of our biggest AI breakthroughs.
Our work with SIMA taught agents how to understand 3D worlds, but learning to
🔵 It shows strong gains over 3.6 Flash in key coding tasks like debugging and issue resolution.
🔵 It’s better at designing more functional web layouts and apps using fewer prompts.
🔵 It delivers improved reasoning and accuracy when completing real-world business workflows.
We built SL2T with the Deaf community - guided by Deaf Googlers and our AI Sign Language Advisory Committee.
Bringing ASL input to phones is just the beginning and we’re working to expand this technology to more sign languages and applications.
Find out more →
SL2T is state-of-the-art on academic benchmarks, plus it's optimized for real-world use like one-handed signing while holding a phone.
To protect privacy, it tracks body poses on-device, while our servers translate them into text.
For years, building AI for sign language has been slow due to complex technical challenges and misconceptions about how the languages work.
We addressed this by training a model to translate simultaneous movements of the hands, body, and face directly into text, using huge
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.
We’re open sourcing the code and model weights on @Github, making them freely available for anyone to build on.
This could be for academic purposes, operational forecasting, or developing more specialized, localized models. Explore the research → https://goo.gle/3RRTSOo
During Hurricane Melissa, WeatherNext gave forecasters early predictions of its Category 5 landfall 5 days in advance with 80% confidence.
This year, we’re providing 1,000 probabilistic predictions per storm to support forecasters, now accessible via WeatherLab →
