Zhao Dong

Who is Adam? In this video, meet this guy who has some momentum and his cousin AdamW. youtu.be/1_nujVNUsto

For everyone interested in precise 📷camera control 📷 in transformers [e.g., video / world model etc] Stop settling for Plücker raymaps -- use camera-aware relative PE in your attention layers, like RoPE (for LLMs) but for cameras! Paper & code: liruilong.cn/prope/

What exactly is a "world model"? And what limits existing video generation models from being true world models? In my new blog post, I argue that a true video world model must be causal, interactive, persistent, real-time, and physical accurate. xunhuang.me/blogs/world_mo…

🚀 At #CVPR2025 we’ve open-sourced 3 SOTA 3D reconstruction baselines for high-quality digital twin creation: 🌀 Egocentric Photoreal 3DGS (SIGGRAPH 2025) 📦 Feed-forward Sparse-view LRM (CVPR 2025) 💡 Neural-PBIR Relightable Objects (ICCV 2023) All now available at 👉…

Thanks, @CSProfKGD! I love MeanFlow's elegant formulation of one-step generative modeling. But I was a bit confused about the notation and derivation. Hopefully, this video will help people interested in the paper understand it better.

🎉 Huge thanks to all attendees of the 3D Digital Twin Workshop @ CVPR 2025! The panel was insightful & fun—grateful to our amazing speakers & organizers 🙏 Recordings will be on YouTube soon—stay tuned! 🔗 Explore our Digital Twin Catalog (DTC): 📁 Dataset & paper:…

Join us to see the SOTA relightable digital twin reconstruction and inverse rendering by @MilosHasan @shuangz , Room 102 B!

We will host a discussion panel as the last session for the workshop. Please submit your questions regarding 3D Digital Twins research. forms.gle/1UqP2NxfNkSbpx…

We will start our afternoon session at 2pm, and @QianqianWang5 Prof. Andrea Vadaldi, @MilosHasan and @shuangz will bring excellent sharing and talk!

Humanoid Robotics expert, Prof. Xiaolong Wang (@xiaolonw ) is giving a talk in 5mins: "Learning Generalizable Manipulation from Sim and Real Data", Room 102 B.

Robotics industry expert, founding member of HillBot, @JetZhang12 is on: "Capture Reality End-to-End: Fast, Texture-Ready Digital Twins with Dynamic and Articulation"

Prof. Hao (Richard) Zhang from SFU is talking about "Learning Structured CAD Representations for 3D Digital Twins"

We will start the 2nd morning session in 2mins, @richardzhangsfu @xiaolonw @JetZhang12 will bring super exciting talk! Join us in Room 102 B

🚀 Excited to announce our CVPR 2025 Workshop: 3D Digital Twin: Progress, Challenges, and Future Directions 🗓 June 12, 2025 · 9:00 AM–5:00 PM 📢 Incredible lineup: @rapideRobot, Andrea Vedaldi @Oxford_VGG,@richardzhangsfu,@QianqianWang5,Dr. Xiaoshuai Zhang @Hillbot_AI,…

We are in Room 102 B, and will start at 9 am! Online zoom is also on and cu very soon!😃👍

As the final session of our workshop, we’ll be hosting a Discussion Panel featuring domain experts in Robotics, Vision, and Graphics. We invite you to submit your questions on 3D Digital Twin R&D via the following form: 🔗 forms.gle/E3ZrkiMx7MR464… We look forward to your insights…