Max Jiang

Staff Research Scientist / TLM @ Waymo | Generative Models, 3D Vision, Self-driving Cars | Prev. PhD@Berkeley, Google, Cruise | Opinions are my own

[Max Jiang @maxjiang93]

@taiyasaki @wayve_ai Congrats Andrea! We are in the same industry again :)

[Max Jiang @maxjiang93]

Attending CVPR? Come see the poster! 📍 Day 3 Morning — June 7 📝 Paper ID: 41224

[Max Jiang @maxjiang93]

1/ Thrilled to share our latest research from Waymo at #CVPR2026: Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving.

Shoutout to our stellar intern Jiahao Wang for leading this project

[Max Jiang @maxjiang93]

4/ How it works: We combined 4D Gaussian Splatting (for paired-data construction) with diffusion-based sensor generation.

This opens up an entirely new avenue for scaling data in AV training and validation.📈

[Demis Hassabis @demishassabis]

Gemini Omni is a major leap in world understanding & multimodal editing! It can take photos, video & audio and build entirely new scenes. Over time it’ll be able to handle any input & any output - starting w/ video

You can even give it your own videos & iterate on your ideas:

[Max Jiang @maxjiang93]

@ZGojcic @FidlerSanja Very nice work, congrats!

[Songyou Peng @songyoupeng]

📢Our team @GoogleDeepMind is hiring a Research Scientist in MTV, NYC, or SF!

Join us to push the frontiers of visual perception & spatial reasoning for multimodal foundation models like Gemini, Nano Banana, and more!

Send your CV to [email protected]

[Sundar Pichai @sundarpichai]

Great use of Genie 3 from @waymo to create high-fidelity, interactive simulations of rare events that are nearly impossible to capture in the real world.

[Demis Hassabis @demishassabis]

Super cool use case of Genie 3 simulations!

[Max Jiang @maxjiang93]

Incredibly excited to share our most recent work: the Waymo World Model. We leverage the broad world knowledge in Google DeepMind's Genie 3 and bring it into our most advanced autonomous driving simulator to date, with emergent transfer of world knowledge even into the 3D domain.

[Waymo @Waymo]

We’re excited to introduce the Waymo World Model—a frontier generative mode for large-scale, hyper-realistic autonomous driving simulation built on @GoogleDeepMind’s Genie 3.

By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and complex scenarios—from tornadoes to planes landing on freeways—long before it encounters them in the real world.

https://t.co/EbMut47ZEY

[Dmitri Dolgov @dmitri_dolgov]

Exponential scaling ongoing – @Waymo has officially doubled our fully autonomous cities in a matter of weeks, reaching 10 cities with the newest additions of San Antonio and Orlando. This is a testament to the maturity and generalizability of the Waymo Driver, our deliberate, safety-first approach to scaling, and an important step as we prepare to serve more riders across more cities soon.

[Max Jiang @maxjiang93]

An early glimpse into the exciting future of fully generative AV world models ;)

[Jiahao Wang @jiahaowg]

🚗 Excited to present our paper "Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models" at #IROS2025!

📅 Time: 10:55–11:00, Wed, 10.22.2025
📍 Room: 103C, Paper WeAT27.6

arxiv: https://t.co/oA6J42EOGV

#IROS2025 #WorldModels #AutonomousDriving #GenerativeAI

[Jiahao Wang @jiahaowg]

🚗 Excited to present our paper "Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models" at #IROS2025!

📅 Time: 10:55–11:00, Wed, 10.22.2025
📍 Room: 103C, Paper WeAT27.6

arxiv: https://t.co/oA6J42EOGV

#IROS2025 #WorldModels #AutonomousDriving #GenerativeAI

[Max Jiang @maxjiang93]

If you share this mission and have related experience in world models / video, image generation models, diffusion models, LLMs, 3D, …, let’s chat!

[Max Jiang @maxjiang93]

📣Super excited to share a new opportunity to work with me and my team to build the most advanced generative world model for simulating autonomous vehicles 🤖🚕🌎 enabling Waymo to scale faster, safer, and serve more people.

https://t.co/wRIxzE82dq

[Max Jiang @maxjiang93]

We are in the most unique position to leverage the data, compute, talent and a little bit of secret sauce 😉 to crack one of AI’s most exciting new frontiers.

[John Lambert @jlambert_]

Can a single autonomous driving simulation world model jointly insert, delete, and control the behavior of all agents and traffic lights in a bird's-eye-view scene?

For the first time, we show this is possible in SceneDiffuser++, our CVPR '25 paper, w/ 60+ second simulations.🧵