Загрузка видео...

Не удалось загрузить видео

На главную

🤖Simulation-Ready Human–Scene Interaction Reconstruction🤖 #HSImul3R reconstructs sim-ready 3D human-scene interactions from casual videos with *physics-in-the-loop* that can be directly deployed to humanoids. - Project: - Code:

liuziwei7's profile picture

Ziwei Liu

12,610 subscribers

15,326 просмотров • 2 месяцев назад •via X (Twitter)

#HSImul3R
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs transform instructions into execution plans & target layouts - Multi-stage framework generates synchronized object, body & finger motions - RL policy tracks generated motions in physics simulation Project: Demo: Paper:
0:34

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs transform instructions into execution plans & target layouts - Multi-stage framework generates synchronized object, body & finger motions - RL policy tracks generated motions in physics simulation Project: Demo: Paper:

Jiaman Li

104,574 просмотров • 1 год назад

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:
1:04

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

Ziwei Liu

26,953 просмотров • 1 год назад

🕸️ Introducing SPIDER — Scalable Physics-Informed Dexterous Retargeting! A dynamically feasible, cross-embodiment retargeting framework for BOTH humanoids 🤖 and dexterous hands ✋. From human motion → sim → real robots, at scale. 🔗 Website: 🧵 1/n
1:25

🕸️ Introducing SPIDER — Scalable Physics-Informed Dexterous Retargeting! A dynamically feasible, cross-embodiment retargeting framework for BOTH humanoids 🤖 and dexterous hands ✋. From human motion → sim → real robots, at scale. 🔗 Website: 🧵 1/n

Chaoyi Pan

64,922 просмотров • 6 месяцев назад

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models.
0:22

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models.

Angela Dai

106,850 просмотров • 2 лет назад

Wow! We just put a human-in-the-loop within ChatGPT. ❤️🤖
1:32

Wow! We just put a human-in-the-loop within ChatGPT. ❤️🤖

Marc Benioff

104,930 просмотров • 7 месяцев назад

Proof that human videos can be converted into context-aware humanoid locomotion. VideoMimic is a real-to-sim-to-real pipeline that reconstructs humans and scenes from video, retargets motion to a humanoid, and trains a single policy in sim immediately deployable on real robots.
1:44

Proof that human videos can be converted into context-aware humanoid locomotion. VideoMimic is a real-to-sim-to-real pipeline that reconstructs humans and scenes from video, retargets motion to a humanoid, and trains a single policy in sim immediately deployable on real robots.

The Humanoid Hub

63,226 просмотров • 1 год назад

2025. The year humans trained robots. 🤖 70,000+ teleop sessions 🤖 Nearly 5,000 hours of real human-in-the-loop work 🤖 1.2M+ app members This is PrismaX Wrapped 2025.
0:50

2025. The year humans trained robots. 🤖 70,000+ teleop sessions 🤖 Nearly 5,000 hours of real human-in-the-loop work 🤖 1.2M+ app members This is PrismaX Wrapped 2025.

PrismaX

54,436 просмотров • 5 месяцев назад

Excited to introduce COLA: Learning Human–Humanoid Coordination for Collaborative Object Carrying 🤝🤖 COLA makes humanoids truly helpful in human collaboration — capable of carrying objects, pushing carts, or responding to human push commands. It provides a proprioception-only policy for compliant human–humanoid coordination across diverse movement patterns. The core idea is simple yet effective: 👉 Fine-tune a collaborative policy from a locomotion policy using a residual teacher. 👉 Train in simulation and distill to a real-world student policy for deployment. Paper: Project:
3:13

Excited to introduce COLA: Learning Human–Humanoid Coordination for Collaborative Object Carrying 🤝🤖 COLA makes humanoids truly helpful in human collaboration — capable of carrying objects, pushing carts, or responding to human push commands. It provides a proprioception-only policy for compliant human–humanoid coordination across diverse movement patterns. The core idea is simple yet effective: 👉 Fine-tune a collaborative policy from a locomotion policy using a residual teacher. 👉 Train in simulation and distill to a real-world student policy for deployment. Paper: Project:

Siyuan Huang

21,892 просмотров • 7 месяцев назад

Sometimes the model’s driving. Sometimes the human is. With Lite-T, a wearable data collection system, operators can jump in and out of control during training—seamless human-in-the-loop. Tag team training for embodied AI 🤝🤖 #data #embodiedai
1:20

Sometimes the model’s driving. Sometimes the human is. With Lite-T, a wearable data collection system, operators can jump in and out of control during training—seamless human-in-the-loop. Tag team training for embodied AI 🤝🤖 #data #embodiedai

Galaxea Dynamics

21,113 просмотров • 2 месяцев назад

New NVIDIA physical AI agent-ready skills are changing how robotics researchers work. 🤖 With NVIDIA robotics skills, researchers can automate the most common development steps from scene preparation to simulation and learning with Omniverse libraries, Isaac frameworks, and physical AI open datasets. Specialized skills like Isaac Mobility extend that even further. Learn more ➡️
0:24

New NVIDIA physical AI agent-ready skills are changing how robotics researchers work. 🤖 With NVIDIA robotics skills, researchers can automate the most common development steps from scene preparation to simulation and learning with Omniverse libraries, Isaac frameworks, and physical AI open datasets. Specialized skills like Isaac Mobility extend that even further. Learn more ➡️

NVIDIA Robotics

97,269 просмотров • 3 дней назад

You can now enable Codex to execute CodeRabbit directly in your development workflow! Let AI code, review, and fix issues autonomously without any human intervention 🤖 (Check out the updated CodeRabbit CLI x Codex docs below!)
1:33

You can now enable Codex to execute CodeRabbit directly in your development workflow! Let AI code, review, and fix issues autonomously without any human intervention 🤖 (Check out the updated CodeRabbit CLI x Codex docs below!)

CodeRabbit

19,190 просмотров • 8 месяцев назад

📢 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: Code and Models: Paper:
0:50

📢 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: Code and Models: Paper:

Sherwin Bahmani

66,327 просмотров • 8 месяцев назад

We are happy to announce the launch of the beta version of GUIBOT! 🤖Trade Aptos Native Tokens from Telegram directly 🤖Earn 20% of fees from referrals that are new 🤖Earn points while enjoying trading 🤖Degen meme trade directly from Telegram 🤖
0:40

We are happy to announce the launch of the beta version of GUIBOT! 🤖Trade Aptos Native Tokens from Telegram directly 🤖Earn 20% of fees from referrals that are new 🤖Earn points while enjoying trading 🤖Degen meme trade directly from Telegram 🤖

GUIBot

27,648 просмотров • 1 год назад

Check out 🌟Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry & Physics for Mesh-Free Simulation #CVPR2025, from Lingjie Liu’s lab at UPenn. Congrats to Chuhao Chen! Vid2Sim aims to achieve system identification by reconstructing geometry, appearance, and physical properties directly from video. It combines learned data priors with closed-loop optimization: a feed-forward predictor trained on physical prior, followed by fast refinement via Neural Jacobian and mesh-free simulation. The system delivers simulation-ready outputs in minutes, with strong generalization across objects and materials. 🏠Project page: #PhysicalAI #AIGC #CV #CG #simulation #graphics
1:06

Check out 🌟Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry & Physics for Mesh-Free Simulation #CVPR2025, from Lingjie Liu’s lab at UPenn. Congrats to Chuhao Chen! Vid2Sim aims to achieve system identification by reconstructing geometry, appearance, and physical properties directly from video. It combines learned data priors with closed-loop optimization: a feed-forward predictor trained on physical prior, followed by fast refinement via Neural Jacobian and mesh-free simulation. The system delivers simulation-ready outputs in minutes, with strong generalization across objects and materials. 🏠Project page: #PhysicalAI #AIGC #CV #CG #simulation #graphics

Zhiyang (Frank) Dou

12,393 просмотров • 11 месяцев назад

Adobe presents SynCHMR! A method that can reconstruct camera trajectory, human motion, and scene in one global coordinate from videos 🔥
0:26

Adobe presents SynCHMR! A method that can reconstruct camera trajectory, human motion, and scene in one global coordinate from videos 🔥

Dreaming Tulpa 🥓👑

108,620 просмотров • 2 лет назад

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9
0:54

Humanoid motion tracking performance is greatly determined by retargeting quality! Introducing 𝗢𝗺𝗻𝗶𝗥𝗲𝘁𝗮𝗿𝗴𝗲𝘁🎯, generating high-quality interaction-preserving data from human motions for learning complex humanoid skills with 𝗺𝗶𝗻𝗶𝗺𝗮𝗹 RL: - 5 rewards, - 4 DR terms, - Proprio. ONLY, - NO history/curriculum. Ready for agile, human-like 🤖? (Best with 🎧) 🔗 🎥 1/9

Zhen Wu

807,937 просмотров • 8 месяцев назад

The future of package delivery is self-driving vehicles paired with humanoids that can perceive, reason and navigate within spaces designed for human interaction. Also, drones.
0:39

The future of package delivery is self-driving vehicles paired with humanoids that can perceive, reason and navigate within spaces designed for human interaction. Also, drones.

The Humanoid Hub

41,292 просмотров • 9 месяцев назад

Our new work PSHuman reconstructs a detailed 3D human mesh from a single-view image in ~1min. Codes have already been released! Welcome to try it! Project page: Codes: Paper:
0:39

Our new work PSHuman reconstructs a detailed 3D human mesh from a single-view image in ~1min. Codes have already been released! Welcome to try it! Project page: Codes: Paper:

Yuan Liu

53,252 просмотров • 1 год назад

Claude Code, please clean up this clip CLAUDE CODE : THIS CLIP IS AS CLEAN AS IT CAN BE 🤖🤖🤖
0:35

Claude Code, please clean up this clip CLAUDE CODE : THIS CLIP IS AS CLEAN AS IT CAN BE 🤖🤖🤖

lifeline

54,527 просмотров • 3 месяцев назад