Jason Baldridge
@jasonbaldridge
Research scientist at Google in Austin working on grounded language understanding.
Our incredible team built many models announced here, including image, voice, music and video generation! And: I'm moving to London this summer, and I'm hiring for research scientist and engineering roles! Our focus is on speech & music in Zurich, Paris & London. DM/email me.
Day 1 of #GoogleCloudNext ✅ Here’s a taste of all the things that we announced today across infrastructure, research and models, Vertex AI, and agents → goo.gle/4j0u0rH Hint: Ironwood TPUs, Gemini on Google Distributed Cloud, Gemini 2.5 Flash, Lyria, and more.
Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:
If you’re applying for a position in Europe, apply here: job-boards.greenhouse.io/deepmind/jobs/…. If you’re interested in a position in North America, apply here job-boards.greenhouse.io/deepmind/jobs/…
Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:
The capability that enabled us to make Veodyssey (veodyssey-v0.appspot.com) is the new I2V + dialogue in Veo 3. Here's the prompt we used in @GoogleLabs Flow, using a character design made with Imagen 4. ✨ We were also able to keep the voice pretty consistent via these text…
Prompt: here's an example of the I2V prompt structure we used in @GoogleLabs Flow. Notice how the dialogue is generated directly by the Veo model, not prewritten. We've found this yields more natural dialogue, and it's also a fascinating way to explore Veo's creativity and…
Love 👏 to 👏 see 👏 it!! Great walk-through - check out this awesome video showing how to use Frames to Video in Flow to upload an image and add speech. Try it out today!
Google Veo 3 and Google Flow now support image-to-video, with speech! Upload an image of a person, and direct what they say in your text prompt! This is a great way to bring your characters to life. Check this out.
Really excited to see the return of open weights encoder-decoder models! It's amazing how often I still see T5 variants creating immense value at Google, and I'm sure we're not the only ones.
Introducing T5Gemma: the next generation of encoder-decoder/T5 models! 🔧Decoder models adapted to be encoder-decoder 🔥32 models with different combinations 🤗Available in Hugging Face and Kaggle developers.googleblog.com/en/t5gemma
We’re also expanding Flow, our AI tool for filmmakers, to 76 more countries. Access it with a Pro or Ultra plan here: labs.google/flow
Since I/O in May, you've created 40M+ videos with Veo 3! Now our new photo to video feature in the @Geminiapp lets you create clips inspired by the world around you. Here’s how I imagine our resident dino Stan roams the Google campus when we’re not looking:) Ultra/Pro…
New VST/AU Plugin! 🚨 Play with Lyria RealTime directly from inside your favorite DAW with “The Infinite Crate” 🎧🎶 Like other Lyria RT demos, you can mix together text prompts and other controls to steer the model in real-time. But now with a VST plugin you can feed audio…
🔥Happy to announce that the AI for Music Workshop is coming to #NeurIPS2025! We have an amazing lineup of speakers! We call for papers & demos (due on August 22)! See you in San Diego!🏖️ @chrisdonahuey @Ilaria__Manco @zawazaw @huangcza @McAuleyLabUCSD @zacknovack @NeurIPSConf
now wouldn't that be something...
Let me play a video game of my veo 3 videos already. Google cooked so good 👌 @OfficialLoganK playable world models wen?
Calling all students in 🇺🇸🇬🇧🇯🇵🇮🇩🇧🇷 Still time to sign up and get @GeminiApp + a full year FREE of the Google AI Pro plan, do it before the June 30th deadline 👇
Our LLM based agents like AlphaEvolve, Google Co-scientist and Project Naptime enable a dramatic step change in performance across Science, Coding and Cybersecurity. The awe-inspiring effectiveness of agentic frameworks will drive a lot of progress in the coming years.
New @NoPriorsPod with @pushmeet @matejbalog from DeepMind AlphaEvolve on: *ai co-scientists *improving matrix multiplication *reclaiming ~1% of google compute *can AI discover new knowledge? *evolutionary algorithms
Last week, we shared a refresher on our favorite Flow features. Today, we're doing a deep dive into prompting with a few tips on how to craft the optimal prompt, create your dream video, and #FindYourFlow 🕺 Clearly identify your characters or objects and describe their…
Our open source Gemma models are the most powerful single GPU/TPU models out there! Our latest model Gemma 3n has amazing performance, multimodal understanding, & can run with as little as 2GB of memory - perfect for edge devices - enjoy building at ai.studio !
We’re fully releasing Gemma 3n, which brings powerful multimodal AI capabilities to edge devices. 🛠️ Here’s a snapshot of its innovations 🧵
Amazing to see the generality & dexterity of Gemini Robotics in a model small enough to run directly on a robot. Incredible speed & performance even in areas with low connectivity. Excited to continue this momentum to make robots more helpful & useful to people
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. 🧵
Imagen 4 is now available via AI Studio for developers. Get your images, now via minimal python code! ai.google.dev/gemini-api/doc…
Here's a fun review of Magenta RealTime (our new open source music generation model), with a good tour of the interface and capabilities: youtube.com/watch?v=6gVvsv…
So happy to see this panel discussion from Tribeca, about the making of ANCESTRA, has made it online. Ably moderated by @korymath with @Eliza_McNitt, @DarrenAronofsky, @aaronraff, @BenjaminWiley going deep on what it took, and the difficulty of babies. youtube.com/watch?v=B4ESZ1…