Roopal Garg

Sn Staff Research Engineer @GoogleDeepMind | MultiModal & i18n Research for Gemini models | 🦋@roopalgarg |
Views are my own

[Roopal Garg @roopalgarg]

📢 Excited to unveil our latest research, ImageInWords (IIW)! 🚀We're pushing the boundaries of image descriptions with a new seeded, sequential, human-in-the-loop approach producing SOTA, articulate, hyper-detailed descriptions.

arXiv: https://t.co/LhZKSqtbXo 🧵1/12

[Aishwarya Agrawal @aagrawalAA]

Our workshop on Multimodal Alignment for a Pluralistic Society (MAPS) is starting at 8.20am today @CVPR in Room 113.

We have a great lineup of speakers! Get your breakfast and head straight to Room 113!

[Demis Hassabis @demishassabis]

Gemini 3.5 Flash is amazing!

- Performs better than 3.1 Pro on coding & agentic tasks
- 4x faster than other frontier models
- 12x faster in @antigravity - 800 tokens/sec!
- Often at less than half the cost

And Pro to come…

Try it in @antigravity, @GeminiApp & more - enjoy!

[Logan Kilpatrick @OfficialLoganK]

Welcome to Gemini 3.5 Flash, our most powerful model to date. It pushes the frontier of intelligence, speed, and cost putting 3.5 Flash in a class of its own.

We spent the last 6 months making sure Flash is great for real world use cases. It's available everywhere now!

[Sundar Pichai @sundarpichai]

Today at the @Android Show (I/O edition) we announced Gemini Intelligence - bringing the best of Gemini to our most advanced devices.

Automate multi-step tasks across apps and Chrome, fill out forms in a single tap, turn spoken thoughts into polished text with Rambler, build custom widgets & loads more.

[Demis Hassabis @demishassabis]

I’ve always believed the No.1 application of AI should be to improve human health.

That work started with AlphaFold, and now at @IsomorphicLabs with the mission to reimagine drug discovery and one day solve all disease!

We are turbocharging that goal with $2.1B in new funding.

[Radu Soricut @RSoricut]

Meet Vision Banana 🍌 from @GoogleDeepMind! We provide strong evidence that image generators are generalist vision learners. Traditional computer vision tasks (segmentation, depth estimation, normal prediction) can now be performed at/near SOTA with a single generalist model derived from an image generation model.

🖼️ Explore the results: https://t.co/wgBmLooZTO

📄 See details at: https://t.co/rhkDBRmfLR

[Josh Woodward @joshwoodward]

Excited about this!

ProducerAI is now Google Flow Music

Same mission: push the creative boundaries 🎹🎸
Giving people more control over their tracks
Check out the new remix feature!

[Demis Hassabis @demishassabis]

You can vibe design some incredible interfaces with @stitchbygoogle

[Google AI Developers @googleaidevs]

Try 👁 Agentic Vision with Gemini 3 Flash in @GoogleAIStudio or Vertex AI. This new capability enables the model to effectively use code and reasoning to improve performance for common vision tasks.

See Agentic Vision in action: https://t.co/z0k9VG1YmQ

[Roopal Garg @roopalgarg]

Wishing everyone a happy new year!!

[Sundar Pichai @sundarpichai]

We’re back in a Flash ⚡

Gemini 3 Flash is our latest model with frontier intelligence built for lightning speed, and pushing the Pareto Frontier of performance and efficiency. It outperforms 2.5 Pro while being 3x faster at a fraction of the cost.

With this release, Gemini 3’s next-generation intelligence is now rolling out to everyone across our products including @Geminiapp + AI Mode in Search. Devs can build with it in the Gemini API @GoogleAIStudio, Gemini CLI, and Google @antigravity and enterprises can get it in Vertex AI and Gemini Enterprise.

[Josh Woodward @joshwoodward]

Nano Banana Pro can:

Spell

Spell in 10+ languages

Spell in 10+ languages grounded in world knowledge

Spell in 10+ languages grounded in world knowledge and do precise edits

Spell in 10+ languages grounded in world knowledge and do precise edits w/ 14 reference images

Spell in 10+ languages grounded in world knowledge and do precise edits w/ 14 reference images and it's all watermarked with SynthID

I'm still blown away by it, it just doesn't get old

[Josh Woodward @joshwoodward]

Buckle up, India has found 🍌 Nano Banana in @GeminiApp

[Sundar Pichai @sundarpichai]

1/ Some are saying they’ll always remember the day our Gemini 2.5 Flash Image (aka nano 🍌) was released - that was the biggest thing to happen on August 26th, right?:) Try it if you haven’t yet: https://t.co/z8moZCdxb8 

More from an exciting week:

[Demis Hassabis @demishassabis]

boom! 🚀

[Roopal Garg @roopalgarg]

🚀🚀🚀

[Noam Shazeer @NoamShazeer]

Introducing Gemini 2.5 Pro Experimental.

The 2.5 series marks a significant evolution: Gemini models are now fundamentally thinking models.

This means the model reasons before responding, to maximize accuracy -- and it’s our best Gemini model yet.

Blog - https://t.co/Gx35wlkomq

[Oriol Vinyals @OriolVinyalsML]

A mere ~16 point jump on https://t.co/szwIJDhfk1. Such a good model! Gemini 2.5 Pro ♊️

[Arena.ai @arena]

BREAKING: Gemini 2.5 Pro is now #1 on the Arena leaderboard - the largest score jump ever (+40 pts vs Grok-3/GPT-4.5)! 🏆

Tested under codename "nebula"🌌, Gemini 2.5 Pro ranked #1🥇 across ALL categories and UNIQUELY #1 in Math, Creative Writing, Instruction Following, Longer Query, and Multi-Turn!

Massive congrats to @GoogleDeepMind for this incredible Arena milestone! 🙌

More highlights in thread👇

[Logan Kilpatrick @OfficialLoganK]

Introducing Gemini 2.5 Pro, the world's most powerful model, with unified reasoning capabilities + all the things you love about Gemini (long context, tools, etc)

Available as experimental and for free right now in Google AI Studio + API, with pricing coming very soon!

[Sundar Pichai @sundarpichai]

We have liftoff! After a successful launch this weekend, the first FireSat satellite is now orbiting Earth 🛰️ It’s the first of a 50+ satellite constellation that will help detect + track wildfires as small as 5x5 meters, using AI. Huge thanks to partners @MuonSpace @EarthFireAll @MooreFound, and special thanks to @SpaceX for the ride! Here’s a look at the satellite on the launch pad (it’s behind the yellow rectangle).