Sven Elflein

We just released code and model! Go check it out! Code: github.com/nv-dvl/vgg-ttt Model: huggingface.co/nvidia/vgg-ttt

@anagh_malik Nice demo! 😁

📢📢📢 Velox 🚀: Learning Representations of 4D Geometry and Appearance In our #CVPR2026 paper, we introduce a method for learning a native 4D representation, useful for many downstream tasks, such as video-to-4D, 3D tracking, cloth simulation, and others! 🌐: apple.github.io/ml-velox 📝: arxiv.org/abs/2605.04527

@taiyasaki @PaulGavrikov @overleaf Yeah that’s fair! Guess I am not at the stage of my career where I juggle 10 papers 😂

@s_elflein @PaulGavrikov @overleaf I used to use vscode extensions before moving to overleaf. The key advantage is that if you are editing 10 papers at the same time, 10 browser tabs are simply easier to handle. But yah in Cursor/Vscode you get all the LLM prowess, but you lose a lot in terms of usability

If @overleaf does not "wake up" and integrate Claude/ChatGPT/... within their UI (vs. writefull) , they are likely to become obsolete and go bankrupt. Reminds me of when MATLAB refused to expose GPU compute... because they had an existing deal with a small startup.

@taiyasaki @PaulGavrikov @overleaf Have you tried github.com/overleaf-works…. It at least gets you to the year of 2022 in terms of editor features (LLM features don’t work though).

@PaulGavrikov @overleaf Or quick-open a file by CMD+P like every other modern editor – right @overleaf ?

@cindy_x_wu @orussakovsky Congrats Xindi! Well deserved!!

Honored to receive the 2026 Apple Scholars in AIML PhD fellowship! 🍎 Extremely grateful to my advisor @orussakovsky and all the incredible mentors, collaborators and friends I’ve had throughout the journey. Excited to push toward more scalable and capable multimodal system! machinelearning.apple.com/updates/apple-…

🚀We just released Asset Harvester, an image-to-3D model and end-to-end pipeline that extracts real object assets from autonomous driving videos! 🌐 Website: research.nvidia.com/labs/sil/proje… 💻 Code: github.com/nvidia/asset-h… [1/5] #AssetHarvester #AVSimulation #WorldModel #AutonomousDriving

We scaled up Lyra to generate explorable 3D worlds! 🚀 Introducing Lyra 2.0 — turning a single image into a 3D world you can walk through, look back, and even drop a robot into 🤖 Code and Model available today! 🌐 Website: research.nvidia.com/labs/sil/proje… (1/N)

Introducing Neural Harmonic Textures: our new method for real-time novel view synthesis that outperforms all 3DGS and NeRF derivatives including (finally) ZipNeRF in terms of quality across all benchmarks. The code is released (Apache 2.0): (research.nvidia.com/labs/sil/proje…) 🧵

A new generation in AV simulation is here! We are announcing AlpaDreams, a real time interactive generative world model for AV simualtion! Just a year ago it took minutes to generate a few seconds of video, today it is real time and interactive! research.nvidia.com/labs/sil/proje…

@cllullt Cool, thanks for sharing! taking a look!

@s_elflein Awesome project! We are hosting the SHREC26 Track on 3D Reconstruction and your work could be a valuable addition to the track. Challenge: reconstruct objects from 2D images. After, we'll evaluate their quality using a novel feature-aware metric. See: shapevision.dcc.uchile.cl/cllull-shrec20…

🚀 Exciting news! We’re introducing VGG-T³: a scalable model for offline feed-forward 3D reconstruction that finally tackles the "quadratic bottleneck." Ever wanted to have VGGT reconstruct a 1,000-image scene in seconds instead of 10 minutes and use it for visual localization?

We're releasing DiffusionHarmonizer, an online diffusion enhancer bridging neural reconstruction and photorealistic simulation by correcting artifacts, and harmonizing inserted objects so they truly belong in the scene: matching shadows, lighting & color research.nvidia.com/labs/sil/proje…

@ducha_aiki Great question! Similar to VGGT, we observed that once the similarity of images becomes too high (or covers large areas and the model has to propagate covisibility) the reconstruction quality becomes worse. So scaling to reconstructing rome remains an open problem for FF methods

@s_elflein Looks nice! How does it work in 1000 images in indoor multiroom scenario?

7/7 🥂 Huge congrats to the team: @ruilong_li, @sragostinho, @ZGojcic, @lealtaixe, @QunjieZhou, & @AljosaOsep! See you at #CVPR2026! 📄 Paper: arxiv.org/abs/2602.23361 🤗HuggingFace: huggingface.co/papers/2602.23… 🌐 Project Page: research.nvidia.com/labs/dvl/proje…

6/7 ⚙️ Making it work: We find 1) it is critical to initialize from a pre-trained softmax-attention checkpoint. 2) TTT exhibits length generalization issues! Please check out the paper for more details on initialization and tricks towards closing the gap to softmax attention!