Thomas Kipf

Excited to show some surprising inventions on generative multiplayer games we made at Google with Stanford. We call the work MultiGen. I've always been inspired by early studios like id Software with Doom or Blizzard with Warcraft bringing networked video games to the next level. We are at the point in history where we can make strides like them, but for generative games. It's a strange feeling to be in the age of generative video games while still discovering how exactly to train the models and design the tools that make them useful. All of the tools that have been invented for classic game engines need to be redesigned for generative games. For example level and world design is not entirely possible with existing technology. We introduce editable memory to diffusion game engines that allow for design of new levels via a minimap. But we can easily imagine how this can be expanded with different creation tools. The end goal of this research direction is to allow game designers to be able to guide the generation process of their world, at the granularity that they prefer. Editable memory also allows us to add multiplayer to Generative Doom. We were amazed when we saw GameNGen some years ago, and now you can play it live with friends in real-time, on your couch or even online. Shared representations like our editable memory seem like the future for this type of experience. Models are, in some cases, expensive and approximate encoders but great interpolators and extrapolators. Leveraging their strengths lets you have completely new experiences that can be realized now and not in the distant future. This work was started at my previous team and continued in collaboration with Stanford. Congratulations to all for the discoveries.

USA has ChatGPT USA has Grok USA has Claude USA has Gemini USA has Llama USA has Copilot China has DeepSeek China has Qwen China has Ernie China has GLM China has Kimi China has MiniMax Europe has?

Create elaborate scenes with Nano Banana 2 using 14 input images!

Coding got >10x more productive last month, which means that the opportunity cost of all work that isn't coding has gone up by >10x. You should rebalance your schedule accordingly: cancel meetings, reduce admin work, write fewer emails, close Overleaf. It's time to code.

We’re launching Nano Banana 2, built on the latest Gemini Flash model. 🍌 It’s state-of-the-art for creating and editing images, combining Pro-level capabilities with lightning-fast speed. 🧵

Today we're expanding Flow into a full AI creative studio. We’ve redesigned the experience and powerful new tools so you can draft, visualize, and refine your stories in a single, unbroken workflow. What’s new: ✨ An updated interface for seamless workflows 🖼️ An easier way to create with images and videos, together 🗣 Seamless prompting and editing with natural language We can't wait to see what you create!

Today we're expanding Flow into a full AI creative studio. We’ve redesigned the experience and powerful new tools so you can draft, visualize, and refine your stories in a single, unbroken workflow. What’s new: ✨ An updated interface for seamless workflows 🖼️ An easier way to create with images and videos, together 🗣 Seamless prompting and editing with natural language We can't wait to see what you create!

Introducing Gemini 3.1 Pro, our new SOTA model across most reasoning, coding, and stem use cases!