Ze Yang (@yangze0930) profile picture

Distinguished Engineer, Head of World Models @Baidu_Inc PhD @UofT | @VectorInst

Toronto
Joined November 2020
Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)Photo by Ze Yang (@yangze0930)
Proud to share Apollo World, a collective effort by our World Model team! Taking world models from isolated scenarios to task-level simulation, powered by interactive traffic agents, joint camera–LiDAR generation, and full-trip virtual rides. Explore: apollogo.com/technology
Apollo World, our world model for physical AI, was unveiled yesterday at Baidu AI Day in Shenzhen! It turns complex interactions on the road and rare driving scenarios into repeatable, controllable simulations for training and testing autonomous driving systems. - AI traffic agents that make their own decisions and react as autonomous vehicles slow down, change lanes, or yield - Simulated camera, LiDAR, and other sensor data generated in real time, helping autonomous vehicles sense and respond to a virtual world that changes with their actions - Complete rides between any two locations in a virtual city, from accepting a ride request to dropping off passengers - A technology stack suited to robotics and other physical AI applications Apollo World is already part of Apollo Go's testing and validation. What we learn from those virtual trips helps us improve how the vehicles drive on real roads.
1
1
5
483
Ze Yang retweeted
Today, we are thrilled to announce that we have raised $1B USD of new capital to accelerate commercial progress in autonomous trucks and expand to robotaxis! For the first time in the industry, this enables one shared brain to power both applications—trucks and robotaxis. This means any progress in one vertical directly improves the other. This funding includes an oversubscribed $750M Series C round led by @khoslaventures and @G2VPLLC, as well as additional capital from @Uber tied to robotaxi development. We are excited to work with Uber to deploy 25,000 or more Waabi Driver-powered robotaxis on the Uber platform, substantially accelerating the adoption of robotaxis at scale. Thank you to our incredible team, investors, partners, and customers for helping us achieve this milestone. Here's to pioneering the future of Physical AI, together.
19
44
27
328
165,508
Can we reconstruct dynamic driving scenes without any labels? Check our #NeurIPS2025 paper Flux4D, a flow-based, generalizable, unsupervised 4D reconstruction model that scales to real-world driving data! Website: waabi.ai/flux4d Arxiv: arxiv.org/abs/2512.03210 [1/n]
1
13
4
54
11,510
For years, RAW pixel space pretraining has been sidelined: too compute-expensive. Our new @GoogleDeepMind paper 📜 dives into the scaling trends of raw pixel models to answer the question “how far are we from scaling up next-pixel prediction?” arxiv.org/pdf/2511.08704 Forecast: Raw next-pixel modeling will reach competitive ImageNet classification (>80% top1 accuracy) and generation metrics (90 Fr’echet Distance) in five years! Threads 👇
12
46
4
326
47,762
How do we perform 3D object detection well for all object classes of interest, including rare classes in self-driving data? 👀🚗 In our #CoRL2025 paper, we introduce FOMO-3D, the first LiDAR-camera detector that uses 2D vision foundation models for closed-set 3D detection. (1/8)
1
7
1
20
2,536
🚀 Excited to share our #CVPR2025 GenAssets: combining neural rendering & diffusion to turn in-the-wild driving data into realistic 3D assets — enabling scalable sim for autonomy. 🎥 Video: youtu.be/xaAGI-hNMG4 📄 Paper: openaccess.thecvf.com/conten… 📍 ExHall D, 128, Sun 10 - 12:30
2
9
2
61
5,304
Could we reconstruct large scenes in high quality in 30s? Yes! Excited to share our #ECCV24 paper, G3R: Gradient-Guided Generalizable Reconstruction (waabi.ai/g3r), which learns a network to iteratively refine the predicted 3D representation with 3D gradient feedback.
1
23
2
142
11,573
Today marks a huge milestone for @Waabi – we’ve raised $200M USD in an oversubscribed Series B round, led by @Uber & @khoslaventures. This significant investment will accelerate our progress toward launching fully driverless trucks in 2025! waabi.ai/waabi-series-b-anno…
40
29
12
329
80,415
Excited to share a new foundation model for self-driving, Copilot4D. Paper: "Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion", accepted to #ICLR2024 Arxiv: arxiv.org/abs/2311.01017 Blog: waabi.ai/introducing-copilot… Video: waabi.ai/copilot-4d/
Today, we are excited to unveil our latest research, Copilot4D: the first foundation model that explicitly reasons in both 3D space and time. Read more about this breakthrough in AI for the physical world in our blog: waabi.ai/introducing-copilot…
2
6
28
3,850
Ze Yang retweeted
Today, we are excited to unveil our latest research, Copilot4D: the first foundation model that explicitly reasons in both 3D space and time. Read more about this breakthrough in AI for the physical world in our blog: waabi.ai/introducing-copilot…
10
4
28
7,675
Hey everyone! This week we are thrilled of having @yangze0930 from @UofT and @Waabi_ai presenting at the robot learning seminar (Thursday 11:30am EST). See you soon! youtube.com/@MontrealRobotic… #robotics #machinelearning #simulators #selfdrivingcars
3
10
854
How can we generate high-quality auto-labels for self-driving LiDAR data without a human in the loop? 🚗 Check our @corl_conf paper LabelFormer, a simple, efficient, effective transformer-based model to refine object trajectories for auto-labelling. More: waabi.ai/labelformer
3
22
46
4,997
Can we do camera simulation on large scenes in real time? Check our #ICCV23 paper Neural Scene Rasterization which combines neural rendering and traditional rasterization pipeline for realistic and efficient (> 100FPS) rendering on large scenes! Website: waabi.ai/neuras
1
29
2
127
22,638
Want to dive deep into the core aspects of simulation crucial for self-driving systems? Check our #ICCV23 work LiDAR-DG waabi.ai/lidar-dg! We introduce a novel framework to study various aspects of sensor simulation, shedding light on their impact on the autonomy testing.
What makes LiDAR look realistic to a self-driving car? 🤖🚗Come check out our #ICCV2023 poster, "Towards Zero Domain Gap: A Study of Realistic LiDAR Simulation for Autonomy Testing" to find out! Thu 10:30am CET, Nord 011 PDF, Video, etc.: waabi.ai/lidar-dg/
6
424
What makes LiDAR look realistic to a self-driving car? 🤖🚗Come check out our #ICCV2023 poster, "Towards Zero Domain Gap: A Study of Realistic LiDAR Simulation for Autonomy Testing" to find out! Thu 10:30am CET, Nord 011 PDF, Video, etc.: waabi.ai/lidar-dg/
2
6
2
31
3,782
Check out our ICCV work on weather simulation over NeRF!
Introducing ClimateNeRF! ClimateNeRF fuses physical simulations with neural radiance field models of scenes, producing realistic videos of physical phenomena in those scenes. ❄️⛈️🌊😷
2
35
4,586
So excited to share @Waabi_ai strategic partnership with @UberFreight to accelerate the safe deployment of #AI-powered autonomous trucks at scale. Huge step toward the future of safer roads and more efficient supply chains. waabi.ai/waabi-uber-freight/
5
19
3
116
15,803
It was a pleasure speaking with @AlexSdelaGarza about what we’re building at Waabi! Thank you @TIME for including me alongside such incredible AI pioneers in the inaugural #TIME100AI list time.com/collection/time100-…
TIME's new cover: The 100 most influential people in AI ti.me/3ZnH4yJ
6
9
3
99
21,504