Loading video...

Video Failed to Load

Go Home

New paper release: Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids Paper Videos We study how to do learning and sim2real for 3d traversal, such as monkey bars and overhanging obstacles.

ChongZzZhang's profile picture

C. Zhang

7,127 subscribers

77,263 views • 3 days ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to *many * components. paper: code:
0:31

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to *many * components. paper: code:

Tengfei Wang

27,096 views • 8 months ago

The million-dollar question in humanoid robotics is: Can humanoids tap into Internet-scale training data such as online videos due to their human-like physique? Our #CoRL2024 oral paper showed the promise of humanoids learning new skills from single video demonstrations. (1/n)
0:49

The million-dollar question in humanoid robotics is: Can humanoids tap into Internet-scale training data such as online videos due to their human-like physique? Our #CoRL2024 oral paper showed the promise of humanoids learning new skills from single video demonstrations. (1/n)

Yuke Zhu

69,582 views • 1 year ago

Check out our new paper that turns (text, sparse images, videos) => (dynamic 3D scenes)! I can't get over how cool the interactive demo is. Try it out for yourself on the project page:
0:46

Check out our new paper that turns (text, sparse images, videos) => (dynamic 3D scenes)! I can't get over how cool the interactive demo is. Try it out for yourself on the project page:

Aleksander Holynski

37,505 views • 1 year ago

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.
0:29

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision paper page: We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation.

AK

49,929 views • 2 years ago

[1/N] Current visual geometry prediction models primarily rely on labeled 3D data. Our CVPR26 paper, Flow3r, allows additionally leveraging unlabeled videos (using flow supervision) for scalable visual geometry learning, enabling accurate multi-view 3D reconstruction in-the-wild.
0:31

[1/N] Current visual geometry prediction models primarily rely on labeled 3D data. Our CVPR26 paper, Flow3r, allows additionally leveraging unlabeled videos (using flow supervision) for scalable visual geometry learning, enabling accurate multi-view 3D reconstruction in-the-wild.

Shubham Tulsiani

16,885 views • 6 months ago

📸 TOEM 2 GAMEPLAY PREMIERE 📸 The world is now 3D, more options for movement and traversal, and plenty of new friends to meet. Wishlist: ---- Huge thanks to Day of the Devs who let us be a part of their show, it's deeply appreciated!
2:57

📸 TOEM 2 GAMEPLAY PREMIERE 📸 The world is now 3D, more options for movement and traversal, and plenty of new friends to meet. Wishlist: ---- Huge thanks to Day of the Devs who let us be a part of their show, it's deeply appreciated!

TOEM 📸

17,876 views • 1 year ago

We are thrilled to share that our first paper from my new lab, Spateo ( for spatiotemporal modeling of molecular holograms, is now online in Cell: Spateo is a comprehensive analytical framework for 3D whole-embryo spatiotemporal modeling. Its advanced features include: • 3D alignment and reconstruction at the whole-mouse-embryo scale (see the animation). • 3D spatial domain digitization and cell-cell communication analysis to understand spatial gene expression gradients and both inter- and intracellular communication. • 3D morphometric and volumetric analyses along with 3D morphogenesis vector field modeling to quantify dynamics such as surface area, volume, and cell density across organs, and to dissect the interplay between morphogenesis factors and cell migration. • A “Google Earth”-like browser, Spateo-viewer ( and for interactive and intuitive exploration of 3D spatial data. • Additional features, such as RNA signal-based single-cell segmentation. We are also honored that Nature “News and Views” has highlighted this work as well: This is really an amazing outcome after two years' heroic revision process that rewrite the entire paper using a new data ( for whole mouse embryos.
1:24

We are thrilled to share that our first paper from my new lab, Spateo ( for spatiotemporal modeling of molecular holograms, is now online in Cell: Spateo is a comprehensive analytical framework for 3D whole-embryo spatiotemporal modeling. Its advanced features include: • 3D alignment and reconstruction at the whole-mouse-embryo scale (see the animation). • 3D spatial domain digitization and cell-cell communication analysis to understand spatial gene expression gradients and both inter- and intracellular communication. • 3D morphometric and volumetric analyses along with 3D morphogenesis vector field modeling to quantify dynamics such as surface area, volume, and cell density across organs, and to dissect the interplay between morphogenesis factors and cell migration. • A “Google Earth”-like browser, Spateo-viewer ( and for interactive and intuitive exploration of 3D spatial data. • Additional features, such as RNA signal-based single-cell segmentation. We are also honored that Nature “News and Views” has highlighted this work as well: This is really an amazing outcome after two years' heroic revision process that rewrite the entire paper using a new data ( for whole mouse embryos.

evo-devo

58,470 views • 1 year ago

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:
1:54

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

17,858 views • 9 months ago

Very excited to announce: Keypoint Action Tokens! We found that LLMs can be repurposed as "imitation learning engines" for robots, by representing both observations & actions as 3D keypoints, and feeding into an LLM for in-context learning. See: More 👇
0:29

Very excited to announce: Keypoint Action Tokens! We found that LLMs can be repurposed as "imitation learning engines" for robots, by representing both observations & actions as 3D keypoints, and feeding into an LLM for in-context learning. See: More 👇

Edward Johns

32,569 views • 2 years ago

New paper from our lab Nature Communications! Aakash Saha and colleagues reveal the dynamics and mechanism of target DNA traversal in #CRISPR-Cas12a, a conundrum in the field! #compchem We thank the amazing #HPC resources PSC (#Anton2) and San Diego Supercomputer Center
0:39

New paper from our lab Nature Communications! Aakash Saha and colleagues reveal the dynamics and mechanism of target DNA traversal in #CRISPR-Cas12a, a conundrum in the field! #compchem We thank the amazing #HPC resources PSC (#Anton2) and San Diego Supercomputer Center

Giulia Palermo

17,885 views • 2 years ago

--Towards Scalable Sidewalk Autonomy (2/4)-- Introducing UrbanVerse — turning city-tour videos into physics-aware, interactive simulations for scalable robot learning in NVIDIA Omniverse. 🌆 Real-world scene layouts 🧱100K+ 3D assets ICLR’26 paper and **Open-source** assets at 🔗 We thank Coco Robotics for robot support and NVIDIA Academic Grant support NVIDIA Robotics
0:23

--Towards Scalable Sidewalk Autonomy (2/4)-- Introducing UrbanVerse — turning city-tour videos into physics-aware, interactive simulations for scalable robot learning in NVIDIA Omniverse. 🌆 Real-world scene layouts 🧱100K+ 3D assets ICLR’26 paper and **Open-source** assets at 🔗 We thank Coco Robotics for robot support and NVIDIA Academic Grant support NVIDIA Robotics

Bolei Zhou

15,061 views • 4 months ago

We are releasing uCO3D! Built to supercharge 3D GenAI and digital-twin models, this evolution of CO3D features more and higher-quality object videos from 1k categories, 3D Gaussian Splats, and streamlined OSS tools. 💻Data&code: 📄Paper:
1:03

We are releasing uCO3D! Built to supercharge 3D GenAI and digital-twin models, this evolution of CO3D features more and higher-quality object videos from 1k categories, 3D Gaussian Splats, and streamlined OSS tools. 💻Data&code: 📄Paper:

David Novotny

16,702 views • 1 year ago

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.
5:36

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.

AK

141,051 views • 2 years ago

Thank you for 9 followers!! :o I've been learning 3D for 2 years and share all of my progress here ♡( ◡‿◡ )
0:05

Thank you for 9 followers!! :o I've been learning 3D for 2 years and share all of my progress here ♡( ◡‿◡ )

erce 🌱 commissions open

32,614 views • 1 year ago

🎮 React Three Game on Three.js Resources Learn how to build 3D games using React Three Fiber and #threejs. A great starting point for understanding game logic, interactivity, and real-time 3D on the web. 👉 #threejs #WebGL #GameDev #ReactThreeFiber #3D #Learning
1:05

🎮 React Three Game on Three.js Resources Learn how to build 3D games using React Three Fiber and #threejs. A great starting point for understanding game logic, interactivity, and real-time 3D on the web. 👉 #threejs #WebGL #GameDev #ReactThreeFiber #3D #Learning

Three.js Resources

15,990 views • 7 months ago

Hi #PortfolioDay („• ֊ •„)੭ !! I’m Kariha, an aspiring 3D artist who has been learning Blender and Unity to improve the quality of the 3D vtuber models I make! .☘︎ ݁˖ I enjoy sharing my progress here as a way to record my learning journey and milestones 💚
0:24

Hi #PortfolioDay („• ֊ •„)੭ !! I’m Kariha, an aspiring 3D artist who has been learning Blender and Unity to improve the quality of the 3D vtuber models I make! .☘︎ ݁˖ I enjoy sharing my progress here as a way to record my learning journey and milestones 💚

𝗞𝗔𝗥𝗜𝗛𝗔 🌘🍀 3D Artist ☻

36,338 views • 10 months ago

Excited to share our new #SIGGRAPH2025 paper! In this work, we show how to combine Gaussian splatting and computer-generated holography using Gaussian Wave Splatting. This enables photorealistic 3D holograms for emerging holographic VR/AR displays. 1/4
0:25

Excited to share our new #SIGGRAPH2025 paper! In this work, we show how to combine Gaussian splatting and computer-generated holography using Gaussian Wave Splatting. This enables photorealistic 3D holograms for emerging holographic VR/AR displays. 1/4

Gordon Wetzstein

21,220 views • 1 year ago

Jonas Hübotter is a doctoral Researcher at ETH Zurich. Where he works on Active Fine-Tuning and Local Learning. His paper Transductive Active Learning: Theory and Applications is published at NeurIPS24 and we discuss Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs (submitted for ICLR 25) - live on MLST now.
1:19

Jonas Hübotter is a doctoral Researcher at ETH Zurich. Where he works on Active Fine-Tuning and Local Learning. His paper Transductive Active Learning: Theory and Applications is published at NeurIPS24 and we discuss Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs (submitted for ICLR 25) - live on MLST now.

Machine Learning Street Talk

10,246 views • 1 year ago

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 model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:
0:32

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 model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 views • 1 year ago