🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Good morning. While many are just building agents here some of us are prompting cities into existence.

This looks insane, SynCity Training-Free Generation of 3D Worlds

This is freaking insane to be honest 🔥 SynCity : it generates complex and immersive 3D worlds from text prompts and does not require any training or optimization. It leverages the pretrained 2D image generator Flux and the 3D generator TRELLIS More examples and details below 👇

Yo, this is wonderful though!

Awesome breakdown of the approach. Very smart.

Damn cool. SynCity turns text prompts into immersive 3D worlds. It combines Flux (2D artistic diversity) with TRELLIS (3D accuracy) to build seamless, navigable environments tile by tile.

This is incredible. Infinite world generation is here. Now time to put the agents inside and simulate entire cities and economies.

has there been any other startup residency with $6bn created in <2yrs? and it's in Oxford, not SF. so much latent talent hiding out in the UK.

Humans learn from one continuous visual stream, but large video models have to be trained on billions of web videos. We found that learning from such sequential streams is challenging for video models—and we introduce a family of "orthogonal optimizers" to bridge the gap!

Have you wondered why you can pour water accurately even in dark or in opaque bottles? Turns out the sound of pouring secretly hides physical properties that we implicitly infer. Can we train machines to infer these? Know more at our poster IEEE ICASSP (April 10, 830-10 AM IST)!

Very excited to share that the code for SynCity 🌆 is out! Check out github.com/paulengstler/s… For more details about the method, please see the project page research.paulengstler.com/syncity/

Fancy vibe generating an entire 3D scene with a text prompt? The code for SynCity 🌆 is out 👇

Introducing JEGAL👐 JEGAL can match hand gestures with words & phrases in speech/text. By only looking at hand gestures, JEGAL can perform tasks like determining who is speaking, or if a keyword (eg beautiful) is gestured More about our latest research on co-speech gestures 🧵👇

🚀Excited to announce our #CVPR2025 2025 paper: Unbiasing through Textual Descriptions! We release UTD-descriptions for 1.9M videos and object-debiased splits for 12 datasets! 🔗Project: utd-project.github.io Arsha Nagrani Bernt Schiele Hilde Kuehne Christian Rupprecht 🧵👇

Ever wish you could turn your video generator into a controllable physics simulator? We're thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. 🧵(1/n)

We are presenting Dual Point Maps as a #CVPR highlight tomorrow! Learn about our novel, data-efficient representation for 3D/4D deformable objects—an alternative to classical template shape models. 📍🕑 ExHall D, Poster #100, afternoon session 🌍dualpm.github.io

Many Congratulations to Jianyuan#CVPR2025 2025, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht and David Novotny for winning the Best Paper Award @CVPR for "VGGT: Visual Geometry Grounded Transformer" 🥇🎉 🙌🙌 #CVPR2025!!!!!!

Thrilled and honored to receive the Best Paper Award at #CVPR2025! Huge thanks to my fantastic collaborators Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, and David Novotny. Could not be there without you!

When life gives you lemons, Andrea makes lemonade 🍋 Kudos to Andrea Vedaldi doing an excellent work presenting his paper in spite of an incident w/ the poster #cvpr2025