Max Jiang
@maxjiang93
Followers
164
Following
238
Media
1
Statuses
58
Staff Research Scientist / TLM @ Waymo | Generative Models, 3D Vision, Self-driving Cars | Prev. PhD@Berkeley, Google, Cruise | Opinions are my own
Mountain View, CA
Joined November 2013
RT @sundarpichai: Exciting new @Waymo milestone: Waymo One is now serving 200k+ paid trips each week across LA, Phoenix and SF - that’s 20x….
0
534
0
“More than national prides and competitions, I think it’s time to start thinking globally about the challenges and social changes that AI will bring everywhere in the world. And open-source technology is likely our most important asset…”.
Finally took time to go over Dario's essay on DeepSeek and export control and to be honest it was quite painful to read. And I say this as a great admirer of Anthropic and big user of Claude*. The first half of the essay reads like a lengthy attempt to justify that closed-source.
0
0
1
RT @robertnishihara: Just sat down to read the DeepSeek-R1 paper. We're entering an era where compute isn't primarily for training. It's fo….
0
161
0
Joint work with @YijingEric @ancornman1 Chris Davis @XiukunH @hongjjeon Sakshum Kulshrestha @jlambert_ Shuangyu Li Xuanyu Zhou @CarlosFuertes Chang Yuan @tanmingxing Yin Zhou @drago_anguelov.
1
0
1
Highlights are (1) it unifies two keys stages of simulation, scene generation and rollout into a single e2e trained model (2) efficient rollout via amortizing the denoising cost over physical rollout steps reduces closed-loop errors and requires only 1 denoise step per sim step.
1
0
1
[NeurIPS 2024] We are excited to share SceneDiffuser - SceneDiffuser is a diffusion based world model for traffic simulation. Paper: Come talk to us at NeurIPS! Waymo Booth or Friday Poster Session. 11am, East Exhibit Hall A-C #1200.
1
0
5
Congrats to all my Waymo colleagues for making this incredible milestone! Now let’s bring our tech to the world!.
We’ve been waiting for this moment and now we can share it with you: Today, we received our paid driverless permit from the CPUC! In the coming weeks, we’ll begin charging fares for rider-only trips and welcoming new riders into Waymo One in San Francisco.
0
0
5
RT @Waymo: We’ve been waiting for this moment and now we can share it with you: Today, we received our paid driverless permit from the CPUC….
0
248
0
RT @CongyueD: My first computer graphics research project in undergrad was to build an interactive system for artists to create complex sha….
0
12
0
See you in Vancouver! Let me know if you want to meet up and discuss about Generative AI / 3D Perception / Autonomous Vehicles :).
Next week, we’ll be in Vancouver for #CVPR2023 to present our latest work in autonomous driving research. If you’re attending, stop by Booth #1217 to meet our team. Find more info on the workshops we're hosting or participating in:
0
0
3
Very excited to share our CVPR 2023 highlight paper from Waymo Research: MotionDiffuser. Single architecture (transformer) + single loss (diffusion L2) = SOTA multi-agent motion prediction. See you in Vancouver! Joint with @ancornman1 @cheolho Ben Sapp, Yin Zhou, @AnguelovDrago.
MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion. paper page: present MotionDiffuser, a diffusion based representation for the joint distribution of future trajectories over multiple agents. Such representation has several key
0
1
5
Happy to share NerDi 🤓 (NeRF + Diffusion). Exciting work by Congyue during her summer internship with me and my team at Waymo. Generalized 3D perception and reconstruction will help us better understand the challenging real world environments!.
How does the language embedding space balance semantics and appearance for 3D synthesis?.📣Happy to introduce our #CVPR paper NeRDi!.Joint work with @maxjiang93, Charles R. Qi, @skywalkeryxc, Yin Zhou, @GuibasLeonidas, and Dragomir Anguelov.
0
1
6
RT @dmitri_dolgov: Expanded our rider-only (no human driver) 24x7 operations to all of SF and doubled the downtown PHX area including @SkyH….
0
17
0
RT @saswat101: Waymo One is now open to the public in Downtown Phoenix! Download @Waymo’s app, hail a ride 24/7 and enjoy a rider-only jour….
0
32
0
RT @future__art: I made a quick and dirty Stable Diffusion notebook that lets you batch your images and then saves them to your Google Driv….
0
61
0
RT @iScienceLuvr: Have you seen #dalle2 and #Imagen and wondered how it works?. Both models utilize diffusion models, a new class of genera….
0
395
0
A very clear explanation of some very recent research. TL;DR.1) Boosters are very effective against Omicron, bringing effectiveness from <10% to >70%. 2) If you had Pfizer initially, heterogeneous boosting by Moderna is slightly more effective than Pfizer.
An update from our team on the latest vaccine effectiveness (VE) estimates against symptomatic infection with the Omicron variant has now been published in the UKHSA Variant Technical Briefing 33 (page 24). 1/9.
0
0
9