Pinned Tweet
This is the last year I create content in 2D.
To prove it I’m releasing an 11-minute 4DGS video in partnership with @4DV_ai where every single shot is dynamic 3D. Over the next 12–18 months, I'll be moving my filming exclusively to dynamic 3D.
Thank you so much to @NVIDIAAI and ideo possible.
To prove it I’m releasing an 11-minute 4DGS video in partnership with @4DV_ai where every single shot is dynamic 3D. Over the next 12–18 months, I'll be moving my filming exclusively to dynamic 3D.
Thank you so much to @NVIDIAAI and ideo possible.
13
32
213
25,159
You can animate flowing water in splats now with more splats. And yes it also works with lava 😂
7
19
202
11,522
Visual artist @tommyoshima and Kaukokaipuu Kobo are converting Dr. Kenji Kohiyama's two decades of macro insect photogrammetry into 3D Gaussian splats.
The project is part of the exhibition "Insects: An Exhibition by Takeshi Yoro and Kenji Kohiyama, Look, Feel, and Think," he show opened at the Okayama Prefectural Museum of Art on 9 October 2026 and runs until 29 November 2026.
The project is part of the exhibition "Insects: An Exhibition by Takeshi Yoro and Kenji Kohiyama, Look, Feel, and Think," he show opened at the Okayama Prefectural Museum of Art on 9 October 2026 and runs until 29 November 2026.
1
4
29
1,857
Radiance Fields retweeted
NVIDIA Cosmos world models have come to life with real-time interactivity! 🌎🤖🚘
We are releasing our post-training framework for real-time interactive world simulation for Physical AI. The framework builds upon Cosmos 3 through causal training, distillation, and optimized e post-trained models stream visual observations via autoregressive generation in response to incoming actions and scene controls.
We are also releasing example model checkpoints for robotics, autonomous vehicles, and sim-to-real transfer. The release includes optimized streaming inference code to power the models.
Cosmos world foundation models provide broad visual knowledge. Each simulation setting adds its own controls, data, and evaluation requirements. Our shared recipe and example models give researchers and developers a practical starting point for building specialized interactive world simulators.
Huge shoutout to the team for the dedication, creativity, and hard work poured into this release! I am incredibly proud of this work and feel fortunate to lead such a talented team. A special thank-you to the broader Cosmos group for building the world foundation models together. Team green 💚
I am excited to see how you build your own interactive world simulator with Cosmos!
🏠 Project website: research.nvidia.com/labs/cosmos-la…
🤗 Model checkpoints: huggingface.co/collections/nv…
💻 Code: github.com/NVIDIA/cosmos
We are releasing our post-training framework for real-time interactive world simulation for Physical AI. The framework builds upon Cosmos 3 through causal training, distillation, and optimized e post-trained models stream visual observations via autoregressive generation in response to incoming actions and scene controls.
We are also releasing example model checkpoints for robotics, autonomous vehicles, and sim-to-real transfer. The release includes optimized streaming inference code to power the models.
Cosmos world foundation models provide broad visual knowledge. Each simulation setting adds its own controls, data, and evaluation requirements. Our shared recipe and example models give researchers and developers a practical starting point for building specialized interactive world simulators.
Huge shoutout to the team for the dedication, creativity, and hard work poured into this release! I am incredibly proud of this work and feel fortunate to lead such a talented team. A special thank-you to the broader Cosmos group for building the world foundation models together. Team green 💚
I am excited to see how you build your own interactive world simulator with Cosmos!
🏠 Project website: research.nvidia.com/labs/cosmos-la…
🤗 Model checkpoints: huggingface.co/collections/nv…
💻 Code: github.com/NVIDIA/cosmos
4
21
157
11,408
The man who built K-pop just shot two debut music videos in 4D gaussian splatting and then called splats “the final form of the camera.”
The videos just look like normal video, but they’re 3D.
The videos just look like normal video, but they’re 3D.
1
12
112
5,824
Watch the full weekly update of gaussian splatting: youtu.be/meH7K70rt3o
0
2
8
914
Viggle just launched JST-2, which heavily uses gaussian splatting.
I played around creating with their model, with different scenes and characters. It's out today and they have a free tier!
I played around creating with their model, with different scenes and characters. It's out today and they have a free tier!
Today we are releasing JST-2, the world's first full-stack physics-native world foundation model.
Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D.
Generate a 3D scene in seconds and expand it in real with motion built in, all through one general architecture.
4
5
80
4,045
Wild we’re in a time where research can be posted without code and can be reimplemented within a day
0
12
94
4,694
Quite a few cool gaussian splatting papers came out within the last week. Here's SteadySplats from a familiar group of authors!
2
9
95
8,386
New gaussian splatting camera from @KosmoAIOfficial. I've been using it for a few months and the captures coming out are consistently epic.
9
12
103
8,692
Radiance Fields retweeted
Our MLP-Splatting (ECCV 2026) code is out: github.com/kxhit/mlp-spla….
We splat MLPs as light-field primitives instead of Gaussians: more expressive, fewer primitives, and better aligned with object semantics.
Give it a spin!
We splat MLPs as light-field primitives instead of Gaussians: more expressive, fewer primitives, and better aligned with object semantics.
Give it a spin!
7
12
200
185,533