Linyi Jin

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Are spatial abilities in MLLMs flat — or hierarchical? 🤔 And how do we systematically scale them across pre-training, SFT, and RL?🤔 🎯 We propose SpatialTree: How Spatial Abilities Branch Out in MLLMs 🔗 spatialtree.github.io

@chichengcc Thank you Cheng and congrats on Sunday!

@jin_linyi Congrats Linyi!

PhD defended! Excited for the next chapter.

A SINGLE encoder + decoder for all the 4D tasks! We release 🎯 D4RT (Dynamic 4D Reconstruction and Tracking). 📍 A simple, unified interface for 3D tracking, depth, and pose 🌟 SOTA results on 4D reconstruction & tracking 🚀 Up to 100x faster pose estimation than prior works

Next, @Jimantha will be talking about weird data

@hanwenjiang1 is giving a spotlight talk on his Best Paper Candidate RayZer

Happening now! Join us at Room 312. @QianqianWang5 is giving a talk on Cut3r and St4RTrack

For further details, please refer to our workshop webpage: 3d-in-the-wild.github.io. co-organized with: @weichiuma @ShenlongWang @yufei_ye @jin_linyi @qixing_huang @paschalidoud_1 @LeaMue27 @shubhtuls David Fouhey

🌺 Join us in Hawaii for Wild3D! We're hosting our 2nd Workshop on 3D Modeling, Reconstruction & Generation in the Wild! Dive into 3D + 4D topics, from real-world reconstruction to video generative models & dynamic scene modeling 🌋 #Wild3D #ICCV2025

🏆 RayZer is selected as a BEST PAPER CANDIDATE @ICCVConference ! I will present RayZer at Wild3D workshop on Monday morning and the oral session on Tuesday afternoon

10 years ago, deep learning was in its infancy. PyTorch didn't exist. Language models were recurrent, and not large. But it felt important: a new technology that would change everything. That's why @drfeifei , @karpathy, and I started @cs231n back in 2015 - to teach the world's best deep learning class and make these new ideas accessible to everyone. A lot has changed since then. But this year I was honored to return to the classroom for the 10th anniversary of cs231n and teach a new generation of students alongside @drfeifei, @eadeli, and Zane Durante. As usual, lecture videos are free for all to enjoy: youtube.com/playlist?list=…

🚨 Attention AI creative enthusiasts! Our team at @a16z is a gallery party to celebrate AI art in NYC on 9/18. We have an INCREDIBLE artist lineup + founders at some of the coolest AI creative startups. I've been saving a few spots, DM or comment if you're interested 👀

Welcome to submit your paper to our ICCV workshop "3D in the Wild" and enjoy Hawaii 🌺 #ICCV2025

📢Thrilled to share that I'll be joining Harvard and the Kempner Institute as an Assistant Professor starting Fall 2026! I'll be recruiting students this year for the Fall 2026 admissions cycle. Hope you apply!

Congrats on the really cool work!

Veo has an incredible "hidden" ability. It's one of my absolute favorite aspects of Veo 3 i2v. It's ability to transport elements through the latent space, with this simple but very powerful prompt structure: “Instantly jump/cut on frame 1. [Describe the new context]" With this structure, I was able to use my quick drawing as the main subject in all the scenes you saw here. Seeing how the model is able to retain my personal sketch in all of these different contexts.. Feels magical honestly 😍 Music from artlist.io. My personal opinion about the question asked here, should be clear if you've followed along with my posts 🔥🎨

Tactile sensing is gaining traction, but slowly. Why? Because integration remains difficult. But what if adding touch sensors to your robot was as easy as hitting “print”? Introducing eFlesh: a 3D-printable, customizable tactile sensor. Shape it. Size it. Print it. 🧶👇

@Khoa_NguyenTuan I’m one year behind 😅

@jin_linyi x.com/AntonObukhov1/…

🧐Wait, what happened to this pixel? 😜

@phillip_isola haha, thought this was an intentional reminder -- "Never forget to look at ALL the pixels"

@jin_linyi easter egg! (the file we sent the publisher didn't have that pixel, but somehow it got added in the final print. we like it!)