Загрузка видео...

Не удалось загрузить видео

На главную

🤖 LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 🔷 60,000 hours of high-quality pretraining data — combining curated robotic demonstrations and egocentric human operation videos 🔷 20 robot configurations across 17 brands — Astribot, Leju, Unitree, Franka, Fourier, Realman, and more 🔷 Whole-body DoF: heads,...

robbyant_brain's profile picture

Robbyant

1,902 subscribers

681,616 просмотров • 1 день назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

NVIDIA just announced EgoScale 🤖🧠 NVIDIA Research has uncovered a log-linear scaling law for robot dexterity by pretraining VLA models on over 20,000 hours of egocentric human video This massive dataset is 20 times larger than previous efforts and proves that robot intelligence follows a predictable path: the more human data, the lower the loss The secret is a simple recipe combining large-scale human pretraining with a small amount of aligned human-robot mid-training to bridge the gap In testing, this method boosted the average success rate by 54% on a 22-DoF robotic hand compared to policies built without pretraining EgoScale also enables one-shot task adaptation and works across different hardware, suggesting that human motion is a universal motor prior for robots Website: Paper: Source: NVIDIA Research #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #NVIDIA #EgoScale #GR00T
1:25

NVIDIA just announced EgoScale 🤖🧠 NVIDIA Research has uncovered a log-linear scaling law for robot dexterity by pretraining VLA models on over 20,000 hours of egocentric human video This massive dataset is 20 times larger than previous efforts and proves that robot intelligence follows a predictable path: the more human data, the lower the loss The secret is a simple recipe combining large-scale human pretraining with a small amount of aligned human-robot mid-training to bridge the gap In testing, this method boosted the average success rate by 54% on a 22-DoF robotic hand compared to policies built without pretraining EgoScale also enables one-shot task adaptation and works across different hardware, suggesting that human motion is a universal motor prior for robots Website: Paper: Source: NVIDIA Research #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #NVIDIA #EgoScale #GR00T

RoboHub🤖

43,752 просмотров • 4 месяцев назад

🌍 10 minutes was just the beginning. What if a world model could run forever — responding to your every action, generating new events, and never losing coherence? Today, we open-source LingBot-World 2.0 (Infinity) 🔥 The first interactive world model with: 🔷 Hour-long generation with zero quality drift 🔷 Rich actions & events — attack, cast spells, shoot, summon storms 🔷 Agentic world — a Director Agent drives real-time world evolution 720p/60fps. Playable like a game. 🎮 Try it now on reactor — or deploy it yourself with SGLang day-0 support. LMSYS Org #WorldModel #EmbodiedAI #OpenSource #Robotics
2:04

🌍 10 minutes was just the beginning. What if a world model could run forever — responding to your every action, generating new events, and never losing coherence? Today, we open-source LingBot-World 2.0 (Infinity) 🔥 The first interactive world model with: 🔷 Hour-long generation with zero quality drift 🔷 Rich actions & events — attack, cast spells, shoot, summon storms 🔷 Agentic world — a Director Agent drives real-time world evolution 720p/60fps. Playable like a game. 🎮 Try it now on reactor — or deploy it yourself with SGLang day-0 support. LMSYS Org #WorldModel #EmbodiedAI #OpenSource #Robotics

Robbyant

864,723 просмотров • 12 часов назад

The problem with humanoid teleoperation is that it is expensive and difficult to scale Enter NVIDIA's EgoScale: - A VLA model pretrained on thousands hours of egocentric human videos. - Mid-trained via 50 hours of human + 4 hours of robot "play" data for human-robot alignment. - Fine-tuned with very few examples of task-specific robot teleoperation (100 or fewer per task). - Successfully transfers across 5-finger (Sharpa) and 3-finger (Unitree G1) robot hands. - Performance scales predictably as data increases.
0:50

The problem with humanoid teleoperation is that it is expensive and difficult to scale Enter NVIDIA's EgoScale: - A VLA model pretrained on thousands hours of egocentric human videos. - Mid-trained via 50 hours of human + 4 hours of robot "play" data for human-robot alignment. - Fine-tuned with very few examples of task-specific robot teleoperation (100 or fewer per task). - Successfully transfers across 5-finger (Sharpa) and 3-finger (Unitree G1) robot hands. - Performance scales predictably as data increases.

The Humanoid Hub

44,441 просмотров • 4 месяцев назад

New meta on the horizon - AI x Robotics?👀 "The ChatGPT moment for general robotics is just around the corner..." – Jensen Huang, CEO of NVIDIA Most profitable wallet on 7D leaderboard by Nansen 🧭 loaded a few Robotic plays: 🔷 $SAM - Crowdsourcing real-world datasets with robotic gaming 🔷 $HIBER - robust AI Infrastructure 🔷 $BREW - Intersection of robotics × AI × crypto 🔷 $MROBOTICS - mobile gaming and robotics company Another quality project to research: $XRT What else did I miss?🤔
0:22

New meta on the horizon - AI x Robotics?👀 "The ChatGPT moment for general robotics is just around the corner..." – Jensen Huang, CEO of NVIDIA Most profitable wallet on 7D leaderboard by Nansen 🧭 loaded a few Robotic plays: 🔷 $SAM - Crowdsourcing real-world datasets with robotic gaming 🔷 $HIBER - robust AI Infrastructure 🔷 $BREW - Intersection of robotics × AI × crypto 🔷 $MROBOTICS - mobile gaming and robotics company Another quality project to research: $XRT What else did I miss?🤔

Crypto Gideon(🧠,🧠)

15,027 просмотров • 1 год назад

🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking potential for robotic foundation model ❗Over 30x pretraining efficiency for VLA training 🤗Code and checkpoints are all open-sourced!
0:51

🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking potential for robotic foundation model ❗Over 30x pretraining efficiency for VLA training 🤗Code and checkpoints are all open-sourced!

Seonghyeon Ye

33,239 просмотров • 1 год назад

Excited to release τ0-WM: an open-source unified video-action world model for robotic manipulation. It's a 5B-parameter robotic foundation model trained on 27.3K hours of real-robot teleoperation, UMI-style demonstrations, and egocentric interaction videos.
3:26

Excited to release τ0-WM: an open-source unified video-action world model for robotic manipulation. It's a 5B-parameter robotic foundation model trained on 27.3K hours of real-robot teleoperation, UMI-style demonstrations, and egocentric interaction videos.

Jianlan Luo

63,226 просмотров • 1 месяц назад

X-Humanoid unveiled TG-VLA, which it calls the world's first whole-body VLA framework for full-size humanoid robots. The goal: move humanoids past "mobile dual-arm systems" to human-like, whole-body coordinated operation. Built on three technologies: - HEX: an open-source full-size humanoid VLA that learns across embodiments and coordinates the whole body. Claimed SOTA on real-world whole-body manipulation - HAF-VLA: hierarchical action flow that decomposes whole-body motion into subtasks. Best or joint-best on 6 benchmarks - DSRL-DCT: online RL for high-DoF humanoids in a compressed latent space. 100% success on mobile manipulation HEX is open-source.
2:48

X-Humanoid unveiled TG-VLA, which it calls the world's first whole-body VLA framework for full-size humanoid robots. The goal: move humanoids past "mobile dual-arm systems" to human-like, whole-body coordinated operation. Built on three technologies: - HEX: an open-source full-size humanoid VLA that learns across embodiments and coordinates the whole body. Claimed SOTA on real-world whole-body manipulation - HAF-VLA: hierarchical action flow that decomposes whole-body motion into subtasks. Best or joint-best on 6 benchmarks - DSRL-DCT: online RL for high-DoF humanoids in a compressed latent space. 100% success on mobile manipulation HEX is open-source.

The Humanoid Hub

18,494 просмотров • 5 дней назад

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.
2:52

Qwen-VLA feels like one of the first real robotics foundation models. A single system trained across robot manipulation, navigation, egocentric human video, simulation, and vision-language reasoning instead of isolated robot policies.

Robots Digest 🤖

14,663 просмотров • 1 месяц назад

We built a fully open-source dexterous robotic hand — for just $314. 🤖 Meet Aero Hand Open — precise, affordable, and built for embodied AI research. Watch it perform natural finger motions 👇 🔗 📘 Docs: 💻 GitHub: #robotics #opensource #AI #dexteroushand #embodiedAI
0:29

We built a fully open-source dexterous robotic hand — for just $314. 🤖 Meet Aero Hand Open — precise, affordable, and built for embodied AI research. Watch it perform natural finger motions 👇 🔗 📘 Docs: 💻 GitHub: #robotics #opensource #AI #dexteroushand #embodiedAI

Chestnut Robotics

58,023 просмотров • 8 месяцев назад

We just open-sourced G0 Plus VLA model & launched "Pick Up Anything" demo. See our robot perform diverse real-world tasks through pure language. No specialized training needed. That's zero-shot embodied intelligence. #VLA #Robotics #OpenSource 🔗Try now：
3:21

We just open-sourced G0 Plus VLA model & launched "Pick Up Anything" demo. See our robot perform diverse real-world tasks through pure language. No specialized training needed. That's zero-shot embodied intelligence. #VLA #Robotics #OpenSource 🔗Try now：

Galaxea Dynamics

98,822 просмотров • 6 месяцев назад

Unitree G1 Open Source Dataset In order to promote the development of the global embodied AI industry, the Unitree G1 robot operation data set is open sourced, adapted to a variety of open source solutions, and continuously updated: Open source data collection: Open source learning algorithms: Open source datasets and models: #AI #Teleoperation #OpenSourceDataset #Unitree #EmbodiedAI #Humanoid #DataCollection #AGI
0:34

Unitree G1 Open Source Dataset In order to promote the development of the global embodied AI industry, the Unitree G1 robot operation data set is open sourced, adapted to a variety of open source solutions, and continuously updated: Open source data collection: Open source learning algorithms: Open source datasets and models: #AI #Teleoperation #OpenSourceDataset #Unitree #EmbodiedAI #Humanoid #DataCollection #AGI

Unitree

148,860 просмотров • 1 год назад

🎉 GlobalGPT just leveled up! We've added the following top models: 🔷Midjourney v7: Creates stunning, high-quality images from text. 🔷GPT-4.1: Smart AI for deep answers and complex tasks. 🔷GPT-4.1 mini: Fast, lightweight AI for quick replies. 🔷Grok 3 Beta: Great for creative ideas and unique insights. 🔷Llama 4 Maverick: Powerful for coding and multilingual tasks. 🔷Llama 4 Scout: Handles long texts and detailed analysis. 🔷ChatGPT-4o-image: Improved for generating and editing images. Try now👉
0:40

🎉 GlobalGPT just leveled up! We've added the following top models: 🔷Midjourney v7: Creates stunning, high-quality images from text. 🔷GPT-4.1: Smart AI for deep answers and complex tasks. 🔷GPT-4.1 mini: Fast, lightweight AI for quick replies. 🔷Grok 3 Beta: Great for creative ideas and unique insights. 🔷Llama 4 Maverick: Powerful for coding and multilingual tasks. 🔷Llama 4 Scout: Handles long texts and detailed analysis. 🔷ChatGPT-4o-image: Improved for generating and editing images. Try now👉

GlobalGPT

56,886 просмотров • 1 год назад

Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench. 🧵👇
1:32

Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench. 🧵👇

Robbyant

1,020,191 просмотров • 14 часов назад

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:
3:52

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

93,749 просмотров • 6 месяцев назад

🔹🔷another model done 🔷🔹 🔹🔷Late preview model for @/KumiVT 🔷🔹 🔹🔷what a cute birb🔷🔹 #VRChat #VSeeFace #Blender3d #3Dmodel
0:26

🔹🔷another model done 🔷🔹 🔹🔷Late preview model for @/KumiVT 🔷🔹 🔹🔷what a cute birb🔷🔹 #VRChat #VSeeFace #Blender3d #3Dmodel

Sikku_ Commissions (Closed)

16,458 просмотров • 11 месяцев назад

The wait is OVER! Puzzle Quest: Immortal Edition is OUT NOW on Steam, Epic Games Store, GOG, Xbox One, Xbox Series X|S, PlayStation 4, PlayStation 5, and Nintendo Switch. 🪙🔷🟨🔴🔷 💀🔴🌟🟨🪙 🌟💀🌟💀🔷 🔴🔷🟨🌟🔴 🔴🔴🔷🟨🔷 Enjoy 20% off:
0:29

The wait is OVER! Puzzle Quest: Immortal Edition is OUT NOW on Steam, Epic Games Store, GOG, Xbox One, Xbox Series X|S, PlayStation 4, PlayStation 5, and Nintendo Switch. 🪙🔷🟨🔴🔷 💀🔴🌟🟨🪙 🌟💀🌟💀🔷 🔴🔷🟨🌟🔴 🔴🔴🔷🟨🔷 Enjoy 20% off:

505 Games

128,280 просмотров • 9 месяцев назад

Big #Witchfire Early Access news! 🔷 Coming to Steam soon, wishlist at 🔷 Buy now on EGS with 20% off promo: 🔷 The Wailing Tower Update is out now on EGS, with new region to explore, new gear, and new features like Fallen Preyers and Prophecies. And here is a new showcase trailer!
2:23

Big #Witchfire Early Access news! 🔷 Coming to Steam soon, wishlist at 🔷 Buy now on EGS with 20% off promo: 🔷 The Wailing Tower Update is out now on EGS, with new region to explore, new gear, and new features like Fallen Preyers and Prophecies. And here is a new showcase trailer!

The Astronauts

31,611 просмотров • 1 год назад

RHP/INF Kanon Baxley (Kaneland, 2028) Loud tools across the board for the freshman, more on him and others from the #ILPASUnder, within. 👇 🔷98 mph peak EV, 90 mph avg. 🔷T89 mph INF 🔷7.00 runner 🔷FB: 85-87 mph 🔷CB: 74-76 mph, 3,096 rpm avg 🌪️ 👤
0:21

RHP/INF Kanon Baxley (Kaneland, 2028) Loud tools across the board for the freshman, more on him and others from the #ILPASUnder, within. 👇 🔷98 mph peak EV, 90 mph avg. 🔷T89 mph INF 🔷7.00 runner 🔷FB: 85-87 mph 🔷CB: 74-76 mph, 3,096 rpm avg 🌪️ 👤

Prep Baseball Illinois

18,443 просмотров • 1 год назад

DECLARACIÓN JOHANNES KAISER 🔷🔷🔷🔷🔷🔷🔷🔷
2:53

DECLARACIÓN JOHANNES KAISER 🔷🔷🔷🔷🔷🔷🔷🔷

Gloria

10,685 просмотров • 2 лет назад

🔍 DexScan with advanced filters now directly on CMC homepage! Find the next gem faster with: 🔷 Multiple chain filtering 🔷 Security verification 🔷 Token age sorting 🔷 Marketcap & liquidity filters & much more Catch meme’s the moment they launch 👀
0:32

🔍 DexScan with advanced filters now directly on CMC homepage! Find the next gem faster with: 🔷 Multiple chain filtering 🔷 Security verification 🔷 Token age sorting 🔷 Marketcap & liquidity filters & much more Catch meme’s the moment they launch 👀

CoinMarketCap

37,136 просмотров • 1 год назад