🔊New NVIDIA paper: Audio-SDS🔊 We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more. 🎧 Demos, audio examples, paper: research.nvidia.com/labs/tor…

📢want to produce realistic dynamic 3d worlds (with >100 splats) my new NVIDIA internship project, VoMP, is the first feed forward approach to convert input surface geometry to volumetric sim-ready assets by assigning real world physics materials 🌐Project: research.nvidia.com/labs/sil… 📜Paper: arxiv.org/abs/2510.22975

The future of generative models isn’t just about aesthetics, it’s about controllability and informativeness. We study how to make generative data controllable, informative and diverse for downstream learning. Key ideas: - Guide T2I toward meaningful concept coverage   - Improve discriminative signal without losing diversity Paper: arxiv.org/pdf/2510.24078

1/ #NVIDIAGTC We’re excited to share that ChronoEdit-14B model and 8-step Distillation LoRA (4s/image on H100) are released today. 🤗 Model huggingface.co/nvidia/Chrono… 🤗 Demo huggingface.co/spaces/nvidia… 💡ChronoEdit brings temporal reasoning to image editing task. It achieves STOA across various image editing and in-context generation tasks. 👇 More details in the thread.

🚀 Introducing Nano3D — a training-free framework for precise, coherent 3D object editing without masks! By integrating FlowEdit into TRELLIS and introducing Voxel/Slat-Merge, Nano3D preserves structure & consistency while delivering superior 3D quality.

[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…

I'm at #ICCV2025 this week🌸 - We will be hosting Curated Data for Efficient Learning workshop (w @GCazenavette) 🗓️ Oct. 20, 10:30-10:35 AM 📍Room 304A 🔗 curateddata.github.io/ - I will be presenting our recent work on "Where Is Motion From? Scalable Motion Attribution for Video Generation Models" at Reliable and Interactive World Model workshop (internship project w Nvidia) 🗓️ Oct. 20, 12:00-1:00 PM 📍Room 316A 🔗 riwm-2025.github.io/RIWM-202… Excited to catch up with old friends and meet new ones!

[1/N] Excited to introduce "SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms." We extend 3DGUT with LiDAR support and render a wide range of sensors 10-20x faster than ray tracing and 1.5-10x faster than prior rasterization work. research.nvidia.com/labs/sil…

The Spatial Intelligence Lab at NVIDIA (research.nvidia.com/labs/sil…) is looking for 2026 research interns! We do all kinds of cool work across graphics/vision, geometry, physics, & ML. Now is the time to apply & reach out! nvidia.eightfold.ai/careers/… (not limited to Canada-only)

The best hyperparameter sweep is [0.1, 0.3, 1, 3, 10]. If your model is highly sensitive to hparam scale variation less than 10**0.5, you should focus on changing or reparameterizing your model rather than tuning its hyperparameters.

Come and join us at NVIDIA! Aside from many intern openings, if you are graduating 2026 and will be looking for full-time job, let us know so we can keep you posted about our full-time hiring timeline!

We are hiring PhD interns starting from Jan/2026. Please reach out if you are interested in working with us at Nvidia SIL (Spatial Intelligence Lab, Old Toronto AI). Topics including world model, RL post training and multi-modality generative models. Please reach out!

📢 NVIDIA's Spatial Intelligence Lab (research.nvidia.com/labs/sil…) is hiring 2026 research interns for video/content generation, generative world simulation, RL, 4D perception, neural reconstruction, geometry processing, and physics simulation! Interested? Ping me here or via email.

Our team at NVIDIA is recruiting PhD research interns for the upcoming summer! Apply now! 🥳 Feel free to contact me for any questions or if you’re interested in getting to know the team! Listings are here: nvidia.eightfold.ai/careers?… nvidia.eightfold.ai/careers?…

Our team at Nvidia Spatial Intelligence Lab is hiring PhD research interns for 2026! If you’re excited about faster/smarter video models, please reach out by email and apply through this link: nvidia.eightfold.ai/careers?…

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

PhD INTERNSHIPS 2026 at NVIDIA's Spatial Intelligence Lab are now open! Are you ready to push the limits of generative models and AI for simulation technologies? We're looking for PhD students to join us in 2026 and help advance the frontier of spatial intelligence. Check out the details on our research works and topics: lnkd.in/gFfE8MJW Apply here: lnkd.in/gGKU_sUr for generative AI positions, and lnkd.in/g_Qg_-M3 for Graphics and Simulation research positions

Apply here: nvidia.eightfold.ai/careers?… I'm personally interested in multimodal generation and the tools that power it.

🔍 New NVIDIA Spatial Intelligence Lab internship postings for 2026. Come work with us to advance foundational technologies that enable AI systems to model and interact meaningfully with the world! Topics on our homepage: research.nvidia.com/labs/sil… Application link below

🕹️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/tor… Arxiv: arxiv.org/abs/2510.04290 Code and model are coming.

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: research.nvidia.com/labs/tor… Code and Models: github.com/nv-tlabs/lyra Paper: arxiv.org/abs/2509.19296