Загрузка видео...

Не удалось загрузить видео

На главную

Working on a new topic and hardware for a while: Feet Language Action models. VLAs teach robots to act through vision and language FLAs teach legged robots to act through contact Given a task, terrain, body state, and instruction - decide where, when, and how to make contact

irvinxyz's profile picture

Irvin (in Japan 🇯🇵)

15,313 subscribers

13,943 просмотров • 1 месяц назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Travis Hunter Run Blocking Teach Tape 🎥 • Runs feet through contact • Fights to get hands inside • Understands where run is going and positions himself accordingly
0:14

Travis Hunter Run Blocking Teach Tape 🎥 • Runs feet through contact • Fights to get hands inside • Understands where run is going and positions himself accordingly

Jake Franklin Football

663,431 просмотров • 10 месяцев назад

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at hello@qualiastudios.dev More soon
0:16

Qualia has been selected for the Google DeepMind Robotics Program. We train embodied models that put a robot on a real manual task and make it work, on the floor, not in a demo. Foundation models and reasoning are where robotics is heading, and doing that work alongside DeepMind, who are pushing this frontier, is exactly where we want to be. If you are a company looking to see how a new generation of robots can help your manual tasks, contact us at [email protected] More soon

Qualia

87,678 просмотров • 1 месяц назад

Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿
0:13

Introducing ✨ Aya Vision ✨ - an open-weights model to connect our world through language and vision Aya Vision adds breakthrough multimodal capabilities to our state-of-the-art multilingual 8B and 32B models. 🌿

Cohere Labs

206,663 просмотров • 1 год назад

Selvaggia and Daniela met around five years ago on an Ersties shoot, and now they’re back together to teach us the science of flirting 🤭🔥 The two girls discuss the green and red flags; from eye contact, question asking and body language, there’s a lot to dissect from the art of seduction 🥰💕 Watch here! ➡️
0:14

Selvaggia and Daniela met around five years ago on an Ersties shoot, and now they’re back together to teach us the science of flirting 🤭🔥 The two girls discuss the green and red flags; from eye contact, question asking and body language, there’s a lot to dissect from the art of seduction 🥰💕 Watch here! ➡️

The Ersties Spot ✨

23,159 просмотров • 10 месяцев назад

gemini: teach me how to fly using mediapipe computer vision and threejs to make a first-person flappy bird game
0:17

gemini: teach me how to fly using mediapipe computer vision and threejs to make a first-person flappy bird game

AA

40,130 просмотров • 7 месяцев назад

How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.
0:14

How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.

Ruihan Yang

58,712 просмотров • 1 год назад

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:
0:16

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

NVIDIA AI

337,211 просмотров • 2 месяцев назад

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:
0:12

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:

AI Bites | YouTube Channel

43,496 просмотров • 5 месяцев назад

During missions in The Expanse: Osiris Reborn, you'll be pulled into constant action where focus and ability to act without hesitation make all the difference. Sometimes you'll have only a moment to decide, and it will determine how everything ends. Ready to test yourself?
0:11

During missions in The Expanse: Osiris Reborn, you'll be pulled into constant action where focus and ability to act without hesitation make all the difference. Sometimes you'll have only a moment to decide, and it will determine how everything ends. Ready to test yourself?

The Expanse: Osiris Reborn

34,865 просмотров • 4 месяцев назад

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction
0:17

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction

LeRobot

115,194 просмотров • 9 месяцев назад

Yesterday, I visited a student learning camp to teach young boys and girls how to shake hands confidently, greet respectfully, maintain eye contact, and carry themselves with composure. I also spoke to them about the importance of time management in today's highly distracting world. Simple lessons that open big doors. We are building great men and women for Africa through faith, discipline, and character.
0:13

Yesterday, I visited a student learning camp to teach young boys and girls how to shake hands confidently, greet respectfully, maintain eye contact, and carry themselves with composure. I also spoke to them about the importance of time management in today's highly distracting world. Simple lessons that open big doors. We are building great men and women for Africa through faith, discipline, and character.

Alex Onyia

15,613 просмотров • 1 месяц назад

How can we responsibly deploy agentic AI robots in real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖
0:13

How can we responsibly deploy agentic AI robots in real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖

Google DeepMind

47,887 просмотров • 10 месяцев назад

Converting video models ➡️ ego-centric world models capable of humanoids manipulating objects, robots navigating through paintings, and beyond! Huge effort led by Anurag Bagchi over a year! Special thanks to 1X for releasing so much data!
0:12

Converting video models ➡️ ego-centric world models capable of humanoids manipulating objects, robots navigating through paintings, and beyond! Huge effort led by Anurag Bagchi over a year! Special thanks to 1X for releasing so much data!

Homanga Bharadhwaj

10,478 просмотров • 6 месяцев назад

These devs are working on a futuristic parkour game where you must deliver to make a living - Only a compass and landmarks to navigate the map - Repair gear, upgrade loadouts, prepare for next run - Movement is your language, master it Called PANLINE
0:18

These devs are working on a futuristic parkour game where you must deliver to make a living - Only a compass and landmarks to navigate the map - Repair gear, upgrade loadouts, prepare for next run - Movement is your language, master it Called PANLINE

Jake Lucky

259,510 просмотров • 4 месяцев назад

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang
0:11

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

LeRobot

24,727 просмотров • 2 месяцев назад

Openly flirting with a taken woman while being a married man and a father. My heart breaks for his lovely wife and children. Can’t wait for Topuria to knock him cold out and teach him how to properly respect women
0:19

Openly flirting with a taken woman while being a married man and a father. My heart breaks for his lovely wife and children. Can’t wait for Topuria to knock him cold out and teach him how to properly respect women

ape

108,155 просмотров • 5 месяцев назад

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:
0:11

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

70,090 просмотров • 8 месяцев назад

Mika and Bianca, two hearts learning the language of consistency. Mika, with quiet efforts and loud love. Bianca, with soft gratitude and open hands. In a world that often forgets how to stay, may this friendship teach us how to hold on not just when it’s easy, but especially when it’s not. May this bond be the kind that grows through seasons where love is not just spoken, but shown. May we always meet halfway, again and again. Never FO my MiBi! 🌷 Mika Salamanca Bianca De Vera
0:35

Mika and Bianca, two hearts learning the language of consistency. Mika, with quiet efforts and loud love. Bianca, with soft gratitude and open hands. In a world that often forgets how to stay, may this friendship teach us how to hold on not just when it’s easy, but especially when it’s not. May this bond be the kind that grows through seasons where love is not just spoken, but shown. May we always meet halfway, again and again. Never FO my MiBi! 🌷 Mika Salamanca Bianca De Vera

𝓙𝓪𝔃𝔃𝔂 𝓝𝓪𝓮 🦖 | Estes ni Bumi! ✨

98,633 просмотров • 1 год назад