English
Yulia Rubanova
108 posts
Yulia Rubanova
@YuliaRubanova
Staff Research Scientist in Veo team at Deepmind. Veo Ingredients-to-Video (I/O 2025). Controllable video generation, learning physics in 3D, world models
London, England Katılım Ekim 2015
500 Takip Edilen950 Takipçiler
I am thrilled to announce that I will be joining @Cambridge_Uni as Assistant Professor in Machine Learning at @Cambridge_Eng starting January 2027!
English
New version Ingredients to Video is out!
Now with a portrait mode, better storytelling and consistency -- now available directly on Youtube Shorts.
It is the most rewarding experience to be part of this team and put this into the hands of real users.
Google DeepMind@GoogleDeepMind
We’re updating Veo 3.1 Ingredients to Video to help create more expressive and dynamic clips, produce better visual consistency and more. 📽️ Here’s what’s new 🧵
English
Veo is officially a world simulator for robotics! 🤖🎥
We used action-conditioned Veo to evaluate robotics policies entirely in a generated video. This is a game-changer for scalable, safe robotics testing. Loved working with the team on this!
Anirudha Majumdar@Majumdar_Ani
Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥 🌎 Introducing our new work from @GoogleDeepMind: Evaluating Gemini Robotics Policies in a Veo World Simulator veo-robotics.github.io 🧵👇
English
Yulia Rubanova retweetledi
So excited to finally talk about this work!
Veo is a surprisingly strong world simulator. We fine-tuned Veo on action-conditioned, multi-view robotics data.
Key result: running a policy in the world model is strongly correlated with real-world results.
A few important take-aways:
1) Veo Robotics models real-world physics and robot interactions
2) The base model's world knowledge is retained after fine-tuning and can model OOD scenarios not seen in the robotics data
3) The world model can be used to score task success or failure for a given policy
4) This proves useful for predictive red teaming: simulate dangerous or rare scenarios that would be difficult or irresponsible to execute on the real robot, and judge its performance
I couldn't be more excited about where generalist video models are headed.
Anirudha Majumdar@Majumdar_Ani
Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥 🌎 Introducing our new work from @GoogleDeepMind: Evaluating Gemini Robotics Policies in a Veo World Simulator veo-robotics.github.io 🧵👇
English
Yulia Rubanova retweetledi
Our second Nano Banana in three months 🚢 🚢. Super proud of the team!!
Looking forward to seeing what you'll create with it. Any feedback welcome!
Sundar Pichai@sundarpichai
You went 🍌🍌 for Nano Banana. Now, meet Nano Banana Pro. It’s SOTA for image generation + editing with more advanced world knowledge, text rendering, precision + controls. Built on Gemini 3, it’s really good at complex infographics - much like how engineers see the world:)
English
Try out Veo Ingredients -- now on Gemini App!
Google Gemini@GeminiApp
We’re back with another update to Veo 3.1: Rolling out now on mobile and desktop, you can upload multiple reference images alongside your video prompts, to create entirely new worlds and more nuanced videos that are true to your vision.
English
Feeling honored and grateful to be named one of @techreview Innovators Under 35 Asia Pacific this year. It’s inspiring to see 6 out of 35 innovators in this cohort exploring #EmbodiedAI and #Robotics from different directions. I’ve learned so much from their work and perspectives.
It’s been a privilege to work on bringing large language models and vision language models into real-world robotics to solve long-horizon tasks in unstructured environments — together with inspiring teammates at @GoogleDeepMind and collaborators who share the same vision.
Still so much to discover, and I’m excited to keep learning and innovating in this space to make Physical AGI a reality.
innovatorsunder35.com/the-list/fei-x…
English
Excited to share a huge update Veo Ingredients!
Now your characters can speak🎤 and sing🎶
Seriously, this opens up a whole new level of storytelling. Try it out on Flow: labs.google/flow
#VeoIngredients #veo3_1
Google DeepMind@GoogleDeepMind
🖼️ Ingredients to video Give multiple reference images with different people and objects, and watch how Veo integrates these into a fully-formed scene - complete with sound.
English
Veo 3.1 got a major quality upgrade 👇 Try it out!
Arena.ai@arena
🚨🎬 Big news from Video Arena! @GoogleDeepMind’s latest Veo 3.1 now ranks #1 in both Text-to-Video and Image-to-Video leaderboards. 🏆 This is a +30-point leap from Veo 3.0 → 3.1, making it the first model to break 1400 in Video Arena history! Huge congrats to the @GoogleDeepMind team for pushing the frontier of video generation forward! More details in the thread 🧵
English
What an incredible night! Thank you @corl_conf for shaking things up and inviting both a K-pop band and a Korean traditional music band to the CoRL Banquet. It made the evening truly special.
Sourav Garg@sourav_garg_
K-Pop performance @corl_conf banquet by @geeniusofficial #CoRL2025
English
Veo 3 has powerful visual reasoning capabilities out of the box 👾 It can solve puzzles, understand optical illusions, reason about gravity, lighting, color mixing and more! Veo just keeps on giving 🍏
Check out a detailed investigation by our Deepmind colleagues below 👇
Paul Vicol@PaulVicol
🔥Veo 3 has emergent zero-shot learning and reasoning capabilities! This multitalented model can do a huge range of interesting tasks. It understands physical properties, can manipulate objects, and can even reason. Check out more examples in this thread!
English
Veo Ingredients is available with Veo Fast ⚡️ Make your creations 10x faster and with fewer credits!
We've also made huge strides on improving character consistency.
Here are some examples made from my profile image, and the results are amazing. 👇
Flow by Google@FlowbyGoogle
We posed a creative challenge to our Discord community: start with the exact same ingredients and a prompt to create something in Flow. The results... delightful! ✨
English
Crazy things to try with Nano Banana model that work out of the box. Amazing to see what people can do once they have creative tools to do so. 🔥
The Daily Ai@The_DailyAi
Google just build the craziest AI photo editor ever Nano Banana in Gemini is wild People are already dropping insane use cases 10 wild examples : 1. Model pose like the sketch
English
Yes, this is nano banana🍌
Generating images from "ingredients" + image editing capability is now available on Gemini.
Big congrats to the team for making it happen 🚀
Google DeepMind@GoogleDeepMind
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 🧵
English
Yulia Rubanova retweetledi
Character consistency is all the rage now. Give it a try in Flow!
Flow by Google@FlowbyGoogle
Keeping characters consistent in your AI films can be difficult. Flow's Ingredients to Video feature makes character consistency a breeze - and better yet, it's now available to both Ultra AND Pro users! 🔥
English
Veo ingredients goes beyond using character images as references -- try using clothing items, textures, layout to construct the exact shot you are looking for.
Flow by Google@FlowbyGoogle
In filmmaking, consistency is key to a strong narrative. Using Flow, you can build stories with consistent characters, scenes, and objects across multiple clips— giving you more creative control.
English
We are bringing Veo Ingredients to more users -- now available on Google AI Pro plan in @FlowbyGoogle
We had a blast building this feature. Can't wait to see your creations!
Thomas Kipf@tkipf
Veo Ingredients are now available in @FlowbyGoogle to all Google AI Pro plan subscribers! We've been working hard on this capability over the past couple of months. Excited to get this into the hands of everyone! Get consistent characters, objects and scenes into your worlds, like in this little fun lunar exploration project I put together in just a few minutes 🧑🚀
English