MoE Meets Instruction Tuning: A Winning Combination for Large Language Models [1/3] arxiv.org/pdf/2305.14705 Sheng Shen Zhou Yanqi Barret Zoph William Fedus Jason Wei Hyung Won Chung Shayne Longpre Xinyun Chen @tuvuumass Crick Wu Albert Webson Vincent Y. Zhao Denny Zhou

So excited to share that Gemini 1.0 is out! Incredibly proud to be part of this innovative journey🚀

What a way to celebrate one year of incredible Gemini progress -- #1🥇across the board on overall ranking, as well as on hard prompts, coding, math, instruction following, and more, including with style control on. Thanks to the hard work of everyone in the Gemini team and

Our new model is still experimental, and we’re eager to hear your feedback! One thing that I want to particularly highlight is that our model transparently shows its thought process.

Excited to see the release of Gemini 2.0 Flash Thinking🚀Grateful to have been part of the amazing team behind this experimental model. Its ability to transparently share its thought process is a big step forward.

Had a great time presenting our work on Robust Multi-Objective Preference Alignment with Online DPO at #AAAI2025! 🚀 Big thanks to my amazing coauthors and everyone for the great discussions and interest! #LLMs #AIAlignment #DeepLearning #AAAI

We are finally here! Huge shoutout to the amazing team behind this. 🔥 Check it out: aistudio.google.com #AI #TechNews #GoogleAI

We are hiring a full-time Student Researcher to work on RL at scale Google DeepMind. If you're passionate about RL and excited to build scalable, real-world solutions with us, please fill out the interest form: docs.google.com/forms/d/1gwMvG… #ReinforcementLearning #DeepMind #AI #LLM

Time to think smart and efficient ⚡

Today we’re sharing an early look at our latest Gemini update for I/O! Introducing the updated Gemini 2.5 Pro (I/O edition), which ranks #1 on WebDev Arena and surpasses our previous 2.5 Pro model by +147 Elo points. 🏆 blog.google/products/gemin…

🚀 Excited to share our latest paper of Bayesian-Adaptive RL! Huge congratulations to my student researcher, Shenao Zhang, for leading this effort. Check out our paper here: arxiv.org/abs/2505.20561

Impressive!

🚨BREAKING: Google DeepMind’s Gemini-3-Pro is now #1 across all major Arena leaderboards 🥇#1 in Text, Vision, and WebDev - surpassing Grok-4.1, Claude-4.5, and GPT-5 🥇#1 in Coding, Math, Creative Writing, Long Queries, and nearly all occupational leaderboards. Massive gains

🚀🚀🚀 The best team I’ve ever worked with. So proud of what we built.

Huge congratulations! This is an awesome opportunity!

A really great article! Bookmarked for holiday reading.😊

I'm delighted to jointly author this year-end summary of research advances with @DemisHassabis and James Manyika, on behalf of all of our colleagues across Google DeepMind, Google Research and Google. We look at research advances across eight different areas. These summaries