Xueyan Zou's banner

Xueyan Zou

@xyz2maureen • 2,736 subscribers

Assistant Professor @Tsinghua_Uni prev. PostDoc 🤖 @UCSDJacobs; PhD 🎓 @UWMadison; Intern @MSFTResearch @BytedanceTalk

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build connected parts for robot learning project 🤖. He contributed far beyond modeling, combining strong CAD skills with agent-workflow design to help build the multi-agent pipeline. Code:

🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build connected parts for robot learning project 🤖. He contributed far beyond modeling, combining strong CAD skills with agent-workflow design to help build the multi-agent pipeline. Code:

155,262 views • 2 months ago

Are you using up your $200 GPT-6 quota in a single day and struggling to apply for a new account? (I AM 🫣) 🔥🔥 We’re extending our open-source single-object Text2CAD Multi-Agent system to support complex assembled objects. Now, you can create a complex assembled CAD object for just $5–$10 and even design your own “robot” with this highly affordable system. Code:

Are you using up your $200 GPT-6 quota in a single day and struggling to apply for a new account? (I AM 🫣) 🔥🔥 We’re extending our open-source single-object Text2CAD Multi-Agent system to support complex assembled objects. Now, you can create a complex assembled CAD object for just $5–$10 and even design your own “robot” with this highly affordable system. Code:

29,251 views • 1 month ago

In the era of 10T-parameter foundation models 😈, can we still build next-generation world representations using 🦥 a single RTX 3090 GPU? We introduce WorldString (a name inspired by string theory), a tiny neural network representation for reconstructing dynamic world instances, ranging from articulated motion and skeletal skinning to soft-body deformation. 🔥 We view object representation as the core primitive of world modeling: the basic executable unit from which perception, interaction, simulation, and generation can be built. With a compact neural basis, WorldString aims to connect dynamic object modeling with neural simulation and foundation models, enabling a scalable path toward richer representations of the physical world.

In the era of 10T-parameter foundation models 😈, can we still build next-generation world representations using 🦥 a single RTX 3090 GPU? We introduce WorldString (a name inspired by string theory), a tiny neural network representation for reconstructing dynamic world instances, ranging from articulated motion and skeletal skinning to soft-body deformation. 🔥 We view object representation as the core primitive of world modeling: the basic executable unit from which perception, interaction, simulation, and generation can be built. With a compact neural basis, WorldString aims to connect dynamic object modeling with neural simulation and foundation models, enabling a scalable path toward richer representations of the physical world.

39,479 views • 4 months ago

As an AI researcher, are you interested in tracking trends from CV/NLP/ML to robotics—even Nature/Science. Our paper “Real Deep Research for AI, Robotics & Beyond” automates survey generation and trend/topic discovery across fields 🔥Explore RDR at

As an AI researcher, are you interested in tracking trends from CV/NLP/ML to robotics—even Nature/Science. Our paper “Real Deep Research for AI, Robotics & Beyond” automates survey generation and trend/topic discovery across fields 🔥Explore RDR at

63,442 views • 1 year ago

[1/n] We are releasing M3 (#ICLR2025): a Gaussian Splatting method that builds LMM memories for arbitrary scenes. 🔥 [Efficient] 16 degrees in each Gaussian primitive for one LMM. 🔥 [Alignment] The rendered features are directly in the source LMM embedding space.

[1/n] We are releasing M3 (#ICLR2025): a Gaussian Splatting method that builds LMM memories for arbitrary scenes. 🔥 [Efficient] 16 degrees in each Gaussian primitive for one LMM. 🔥 [Alignment] The rendered features are directly in the source LMM embedding space.

53,538 views • 1 year ago

Our Latent Encoder-Decoder code base is fully open sourced, you can train and visualize the latent space: Code⚙️: ArXiv 📚: #CVPR2026

Our Latent Encoder-Decoder code base is fully open sourced, you can train and visualize the latent space: Code⚙️: ArXiv 📚: #CVPR2026

19,323 views • 7 months ago

🔥Excited to share the first released work from our IEI lab! Congrats to AnteaWu 🎉 This work is motivated by the lack of quantitative evaluation for physics alignment in video world models. With tools like MegaSam and CoTracker, we can directly reconstruct dynamic 3D scenes, enabling quantitative evaluation of physical alignment. Both code and data are released — feel free to try it out! It should work, but if it doesn’t, contact AnteaWu directly : )

🔥Excited to share the first released work from our IEI lab! Congrats to AnteaWu 🎉 This work is motivated by the lack of quantitative evaluation for physics alignment in video world models. With tools like MegaSam and CoTracker, we can directly reconstruct dynamic 3D scenes, enabling quantitative evaluation of physical alignment. Both code and data are released — feel free to try it out! It should work, but if it doesn’t, contact AnteaWu directly : )

10,239 views • 5 months ago

No more content to load