Haithem Turki

Arsenal celebrating like they’ve won the league

If you're in Rio, come check out SimULi at our poster session this Saturday Apr 25! Excited to meet friends old and new. research.nvidia.com/labs/sil/proje…

Asset Harvester tackles the challenging problem of robust image-to-3D extraction from messy real-world driving data. Pretrained models and code are available! Amazing work by @kangxue_yin, @TianshiCao, and @jiawei6_ren 🚀

Waymo/Tesla have suggested video world models could enable closed-loop simulation for self driving, but shared few details. NVIDIA now shows a concrete path, demonstrating that this can be achieved with AR-DiT trained with Self-Forcing. Impressive work! research.nvidia.com/labs/sil/proje…

What if a world model could render not an imagined place, but the actual city? We introduce Seoul World Model, the first world simulation model grounded in a real-world metropolis. TL;DR: We made a world model RAG over millions of street-views. proj: seoul-world-model.github.io

So excited for this to finally be released into the wild - real-time open-source world generation! Mad props to @ruilong_li, @zianwang97, @RdeLutio, @ZGojcic, and everyone else on the team!

World models are transforming AV development by capturing both the environment and the world’s response with high fidelity. Join Sanja Fidler, VP of AI Research at NVIDIA and Associate Professor at the University of Toronto, to explore how NVIDIA Cosmos powers the real-time simulation and closed-loop evaluation that empowers developers to iterate faster and bring safer autonomous systems to the real world. 📅 Thursday, March 19 | 10:00 a.m. - 10:40 a.m. 📍 #NVIDIAGTC 2026 Add to schedule 👉 nvda.ws/4kRYo9s

[7/N] Last but not least, our team at Nvidia Spatial Intelligence Lab is hiring PhD research interns for 2026! - if you are interested in data-driven simulation and/or generative world models, please feel free to DM to email directly. research.nvidia.com/labs/sil/

[6/N] Many thanks to my awesome collaborators @wilson_over, Xin Kang, Janick Martinez Esturo, @ShengyHuang, @ruilong_li , @ZGojcic , and @RdeLutio! Team work makes the dream work.

Our team at Nvidia Spatial Intelligence Lab is hiring PhD research interns for 2026! research.nvidia.com/labs/sil/ If you’re excited about fast video models, generative world simulators, or 3D foundation models, please reach out by email or apply directly lnkd.in/gGKU_sUr

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: research.nvidia.com/labs/toronto-a… Arxiv: arxiv.org/abs/2510.04290 Code and model are coming.

Teach a video diffusion model how to generate 3D Gaussians via self-distillation - no 3D data needed! Really exciting to see how neural reconstruction and generative modeling have been converging recently :) Awesome work by @sherwinbahmani and the rest of the team!

📢📢We have a last-minute internship opening on my team at @NVIDIAAI for this summer. If you are interested and have experience with large feedforward reconstruction models or post-training image/video diffusion models, please get in touch!

🚀 Just in time for the #CVPR rush: we’ve released the code for Difix3D+ — a Best Paper Award candidate! 🔧 Try out the code & demos: github.com/nv-tlabs/Difix… 🎤 Oral (June 15): 1:00–1:15 PM CDT, Karl Dean Grand Ballroom 🖼️ Poster: 4:00–6:00 PM CDT, ExHall D (#57) Join us! @CVPR

📢Our team at @NVIDIAAI is again looking for Research Scientists and Engineerings to help us push the boundaries of Neural Reconstruction and Generation in AV and Robotics simulation! Check out our latest work at zgojcic.github.io, and if interested, reach out directly!