正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation... show more

Chuang Gan

10,248 subscribers

43,265 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育

Anya Rossi• Live Now

Private livecam show

2 条评论

Gordan Knott 的头像

Gordan Knott1 年前

Because of the microseconds lag sending messages from eye to brain and then brain to hand, the brain generates/hallucinates/predicts the future state of the physical universe and uses that to plan and control the body. Is that kinda what you're doing?

ksminnovation 的头像

ksminnovation1 年前

AI is transforming healthcare! A KSM-led study shows AI can detect Celiac disease 4 years earlier @TalPatalon @MedPredict

相关视频

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Contributions: • We introduce 4D LangSplat for open-vocabulary 4D spatial-temporal queries. To the best of our knowledge, we are the first to construct 4D language fields with object textual captions generated by MLLMs. • To model smooth transitions across states for objects in 4D scenes, we propose a status deformable network to capture continuous temporal changes. • Experiential results show that our method attains state-of-the-art performance for both time-agnostic and time-sensitive open-vocabulary queries.

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Contributions: • We introduce 4D LangSplat for open-vocabulary 4D spatial-temporal queries. To the best of our knowledge, we are the first to construct 4D language fields with object textual captions generated by MLLMs. • To model smooth transitions across states for objects in 4D scenes, we propose a status deformable network to capture continuous temporal changes. • Experiential results show that our method attains state-of-the-art performance for both time-agnostic and time-sensitive open-vocabulary queries.

MrNeRF

10,934 次观看 • 1 年前

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

Stability AI

35,969 次观看 • 1 年前

NeoVerse Enhancing 4D World Model with in-the-wild Monocular Videos

NeoVerse Enhancing 4D World Model with in-the-wild Monocular Videos

AK

23,437 次观看 • 5 个月前

VerseCrafter Dynamic Realistic Video World Model with 4D Geometric Control

VerseCrafter Dynamic Realistic Video World Model with 4D Geometric Control

AK

26,856 次观看 • 4 个月前

Self-learning worked in AlphaGo because the world was a clean rulebook, says Demis Hassabis. Real life has no perfect rulebook, so long-term planning needs a strong “world model” to simulate what happens next. Without that simulation, a robot has to guess in the real world—where mistakes can be costly and irreversible. Better world models are the first missing piece, says Demis Hassabis.

Self-learning worked in AlphaGo because the world was a clean rulebook, says Demis Hassabis. Real life has no perfect rulebook, so long-term planning needs a strong “world model” to simulate what happens next. Without that simulation, a robot has to guess in the real world—where mistakes can be costly and irreversible. Better world models are the first missing piece, says Demis Hassabis.

Wes Roth

15,757 次观看 • 4 个月前

Robot Learning from a Physical World Model

Robot Learning from a Physical World Model

AK

34,195 次观看 • 6 个月前

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We introduced a novel density control strategy in training, which allows our 4DGT to handle longer space-time input while maintaining efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can significantly outperform prior Gaussian-based networks in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos Abstract: We propose 4DGT, a 4D Gaussian-based Transformer model for dynamic scene reconstruction, trained entirely on real-world monocular posed videos. Using 4D Gaussian as an inductive bias, 4DGT unifies static and dynamic components, enabling the modeling of complex, time-varying environments with varying object lifespans. We introduced a novel density control strategy in training, which allows our 4DGT to handle longer space-time input while maintaining efficient rendering at runtime. Our model processes 64 consecutive posed frames in a rolling-window fashion, predicting consistent 4D Gaussians in the scene. Unlike optimization-based methods, 4DGT performs purely feed-forward inference, reducing reconstruction time from hours to seconds and scaling effectively to long video sequences. Trained only on large-scale monocular posed video datasets, 4DGT can significantly outperform prior Gaussian-based networks in real-world videos and achieve on-par accuracy with optimization-based methods on cross-domain videos.

MrNeRF

34,782 次观看 • 11 个月前

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

RoboPapers

26,334 次观看 • 4 个月前

🔥Unbounded 4D City Generation🔥 #CityDreamer4D is a generative model of unbounded 4D cities that decouples static and dynamic scenes with realism and controllability - Project: - Code: - CityTopia Dataset:

🔥Unbounded 4D City Generation🔥 #CityDreamer4D is a generative model of unbounded 4D cities that decouples static and dynamic scenes with realism and controllability - Project: - Code: - CityTopia Dataset:

Ziwei Liu

24,326 次观看 • 1 年前

Diffuman4D 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

Diffuman4D 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

AK

12,518 次观看 • 10 个月前

What if we can simulate an *interactive 3D world*, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

What if we can simulate an interactive 3D world, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

Wenlong Huang @ CVPR

245,706 次观看 • 4 个月前

World Model meets robot policy! Robbyant's LingBot-VA: unifies video world modeling and robotic policy learning. - A single model generates both future video and the actions to make it real. - Long-term memory enables long-horizon tasks. - Claims significant outperformance over π₀.₅ in real-world tasks. - It's open-source

World Model meets robot policy! Robbyant's LingBot-VA: unifies video world modeling and robotic policy learning. - A single model generates both future video and the actions to make it real. - Long-term memory enables long-horizon tasks. - Claims significant outperformance over π₀.₅ in real-world tasks. - It's open-source

The Humanoid Hub

17,721 次观看 • 4 个月前

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

AK

84,940 次观看 • 2 年前

Zhou et al., "PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception" VGGT extended to dynamic scenes with a dynamic mask predictor.

Zhou et al., "PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception" VGGT extended to dynamic scenes with a dynamic mask predictor.

Kwang Moo Yi

11,492 次观看 • 7 个月前

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 次观看 • 9 个月前

Google presents CAT4D Create Anything in 4D with Multi-View Video Diffusion Models

Google presents CAT4D Create Anything in 4D with Multi-View Video Diffusion Models

AK

61,949 次观看 • 1 年前

Interactive visual of 4D spacetime. > Extending the 2D model into 3D. You can now see the animated field.

Interactive visual of 4D spacetime. > Extending the 2D model into 3D. You can now see the animated field.

Mirza Beig

76,559 次观看 • 5 个月前

Check out this BIM 4D sim by Thiery Peleias, owner of Virtuart4d 🚧 Imported into UE5 for the animation aspect, the project model was created in Revit, the 4D planning animation in Synchro 4D Pro and the environment captured from Cesium with Google Maps Photorealistic 3D Tiles!

Check out this BIM 4D sim by Thiery Peleias, owner of Virtuart4d 🚧 Imported into UE5 for the animation aspect, the project model was created in Revit, the 4D planning animation in Synchro 4D Pro and the environment captured from Cesium with Google Maps Photorealistic 3D Tiles!

Unreal Engine

20,772 次观看 • 1 年前

forget about physical camera stabilizations why don't we reconstruct the world in 4d and rerecord the footage:

forget about physical camera stabilizations why don't we reconstruct the world in 4d and rerecord the footage:

Dreaming Tulpa 🥓👑

106,083 次观看 • 11 个月前