Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🎓 Excited to defend my PhD thesis “Learning Universal Humanoid Control” at CMU this Friday! From scalable motion imitators to visual dexterous whole-body policies — it’s been a wild ride 🤖✨ 📅 April 25, 2025 📍 CMU RI & online 🔗

zhengyiluo's profile picture

Zhengyi “Zen” Luo

6,069 subscribers

49,433 görüntüleme • 1 yıl önce •via X (Twitter)

Sağlık & İyilikEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

11 Yorum

Jim Fan profil fotoğrafı
Jim Fan1 yıl önce

So proud of you!!

Zhengyi “Zen” Luo profil fotoğrafı
Zhengyi “Zen” Luo1 yıl önce

Thank you boss 🫡

Estadio Deportes profil fotoğrafı
Estadio Deportes1 yıl önce

#ExtraCancha LO MEJOR DE ENERO 🥹 Enero duró una eternidad, pero estos animes nos lo hicieron duradero. 😩Es por ello que reconocemos a lo mejor del primer mes del 2025. 😉 ¡Son los mejores títulos! #Anime #enero #ranking

Baixin Guo(Max) profil fotoğrafı
Baixin Guo(Max)1 yıl önce

恭喜啊哥🎉

ζ Pedram ζ profil fotoğrafı
ζ Pedram ζ1 yıl önce

Good stuff, Kung Fu time?

Andrew Carr (e/🤸) profil fotoğrafı
Andrew Carr (e/🤸)1 yıl önce

Congrats Zen

Zhengyi “Zen” Luo profil fotoğrafı
Zhengyi “Zen” Luo1 yıl önce

Thanks Andrew!!!

mansin profil fotoğrafı
mansin1 yıl önce

Baller

Markie Kendahl profil fotoğrafı
Markie Kendahl1 yıl önce

you don’t see this often. @MichaelDavisW the consistency is insane. Really can’t ignore I started using his exact entries,

10 profil fotoğrafı
101 yıl önce

good job

SHILONG SUN profil fotoğrafı
SHILONG SUN1 yıl önce

Congrats, Dr.

Benzer Videolar

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]
2:39

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]

Siqiao Huang

13,750 görüntüleme • 2 ay önce

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid
1:25

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid

Galbot

46,024 görüntüleme • 5 ay önce

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥
1:32

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,399 görüntüleme • 9 ay önce

X-Humanoid just dropped TG-VLA — the first full-size, whole-body VLA framework for humanoids. 🤖 Most VLA demos today still look arm-centric: see, plan, reach, grasp. The legs are mostly there to carry the arms. TG-VLA pushes action into the whole body: → HEX: task context & cross-embodiment learning → HAF-VLA: high-DoF motion → structured action flows → DSRL-DCT: online RL through a compressed latent space The real shift isn't a smarter hand — it's locomotion, torso control, balance, and manipulation inside one control loop. That's the move: from mobile dual-arm machines to full-body agents.
2:41

X-Humanoid just dropped TG-VLA — the first full-size, whole-body VLA framework for humanoids. 🤖 Most VLA demos today still look arm-centric: see, plan, reach, grasp. The legs are mostly there to carry the arms. TG-VLA pushes action into the whole body: → HEX: task context & cross-embodiment learning → HAF-VLA: high-DoF motion → structured action flows → DSRL-DCT: online RL through a compressed latent space The real shift isn't a smarter hand — it's locomotion, torso control, balance, and manipulation inside one control loop. That's the move: from mobile dual-arm machines to full-body agents.

RoboHub🤖

42,061 görüntüleme • 1 ay önce

X-Humanoid just officially dropped Embodied Tien Kung 3.0, A universal platform designed to be way more open and developer-friendly. 🤖 Built on their Wise Kaiwu AI platform, this next-gen humanoid is all about slashing development costs. It’s a fully interoperable ecosystem that supports everything from tactile interaction to high-dynamic motion control at a full humanoid scale. ➤ Radical Openness: X-Humanoid is open-sourcing the full stack—robot body, motion control, VLM/VLA models, and the RoboMIND dataset. It fully supports ROS2, MQTT, and TCP/IP, so developers can customize use cases without re-engineering the basics. ➤ High-Performance Hardware: With high-torque integrated joints, Tien Kung 3.0 can clear 1-meter (3.3ft) obstacles and handle dexterous moves like kneeling and bending. It hits millimeter-level precision, making it a solid fit for industrial-grade tasks. ➤ True Autonomy: The bot runs a continuous perception-decision-execution loop. It uses world models to break down complex language commands and VLA models for real-time obstacle avoidance and navigation. ➤ Scalable Collaboration: The platform moves beyond single-unit tasks to support multi-robot collaboration with autonomous scheduling. It’s built to move embodied AI from the lab straight into real-world commercial and industrial environments. Source: X-Humanoid #Humanoid #OpenSource #Robotics #EmbodiedAI #PhysicalAI #Automation #XHumanoid #TienKung #WiseKaiwu
2:18

X-Humanoid just officially dropped Embodied Tien Kung 3.0, A universal platform designed to be way more open and developer-friendly. 🤖 Built on their Wise Kaiwu AI platform, this next-gen humanoid is all about slashing development costs. It’s a fully interoperable ecosystem that supports everything from tactile interaction to high-dynamic motion control at a full humanoid scale. ➤ Radical Openness: X-Humanoid is open-sourcing the full stack—robot body, motion control, VLM/VLA models, and the RoboMIND dataset. It fully supports ROS2, MQTT, and TCP/IP, so developers can customize use cases without re-engineering the basics. ➤ High-Performance Hardware: With high-torque integrated joints, Tien Kung 3.0 can clear 1-meter (3.3ft) obstacles and handle dexterous moves like kneeling and bending. It hits millimeter-level precision, making it a solid fit for industrial-grade tasks. ➤ True Autonomy: The bot runs a continuous perception-decision-execution loop. It uses world models to break down complex language commands and VLA models for real-time obstacle avoidance and navigation. ➤ Scalable Collaboration: The platform moves beyond single-unit tasks to support multi-robot collaboration with autonomous scheduling. It’s built to move embodied AI from the lab straight into real-world commercial and industrial environments. Source: X-Humanoid #Humanoid #OpenSource #Robotics #EmbodiedAI #PhysicalAI #Automation #XHumanoid #TienKung #WiseKaiwu

RoboHub🤖

49,440 görüntüleme • 6 ay önce

🤖 Ever dreamed of controlling a humanoid robot to perform complex, long-horizon tasks — using just a single Vision Pro? 🎉 Meet CLONE: a holistic, closed-loop, whole-body teleoperation system for long-horizon humanoid control! 🏃‍♂️🧍 CLONE enables rich and coordinated interactive tasks: 🥊 boxing 🏓 table tennis 🤲 object pickup 📦 room arrangement 🤝 handover … and more! 🌀 Our closed-loop error correction powered by LiDAR odometry ensures precision, while motion-captured demonstrations supercharge policy learning — unlocking the full potential of the G1 robot. 🎥 It’s hard to squeeze the magic into 1 minute — check out the full video demo and project page here: 🔗
3:15

🤖 Ever dreamed of controlling a humanoid robot to perform complex, long-horizon tasks — using just a single Vision Pro? 🎉 Meet CLONE: a holistic, closed-loop, whole-body teleoperation system for long-horizon humanoid control! 🏃‍♂️🧍 CLONE enables rich and coordinated interactive tasks: 🥊 boxing 🏓 table tennis 🤲 object pickup 📦 room arrangement 🤝 handover … and more! 🌀 Our closed-loop error correction powered by LiDAR odometry ensures precision, while motion-captured demonstrations supercharge policy learning — unlocking the full potential of the G1 robot. 🎥 It’s hard to squeeze the magic into 1 minute — check out the full video demo and project page here: 🔗

Siyuan Huang

66,737 görüntüleme • 1 yıl önce

From writing tunes in my room to playing them live at kexp 🤯 It’s wild how far music can carry you. Taking this music across the world, staying true to the soul, & connecting with people in a whole new place, I’m beyond grateful. Thanks to everyone who’s been riding with me ✊
0:59

From writing tunes in my room to playing them live at kexp 🤯 It’s wild how far music can carry you. Taking this music across the world, staying true to the soul, & connecting with people in a whole new place, I’m beyond grateful. Thanks to everyone who’s been riding with me ✊

Brooke Combe

12,898 görüntüleme • 1 yıl önce

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n
1:54

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n

Ashish Kapoor

118,357 görüntüleme • 11 ay önce

My conversation with Kanishka Rao, who went from working on particle physics at CERN to driving robotics at Google DeepMind. We get into the Gemini Robotics 2 release, trending training recipes in the industry, physical AGI, world models, and more. 1:00 Intro 1:47 Does AI's pace feel crazy? 4:04 From particle physics PHD to robotics 6:03 Speech recognition's deep learning moment 8:43 Whole-body humanoid control 10:47 The trash-bag tying demo 13:07 The robotics data pyramid 14:13 Transferring skills across robots 16:30 How does Motion Transfer work 16:56 Why a separate reasoning model 19:02 Can distillation work in robotics? 20:02 The ASIMOV safety benchmark 22:47 VLAs vs world models 25:10 The missing tactile sensing piece 27:48 How far to physical AGI? 30:07 Fundamental breakthrough needed? 31:53 World models for evaluation 33:45 Will the model layer commoditize? 35:11 Humanoid as a form factor
38:27

My conversation with Kanishka Rao, who went from working on particle physics at CERN to driving robotics at Google DeepMind. We get into the Gemini Robotics 2 release, trending training recipes in the industry, physical AGI, world models, and more. 1:00 Intro 1:47 Does AI's pace feel crazy? 4:04 From particle physics PHD to robotics 6:03 Speech recognition's deep learning moment 8:43 Whole-body humanoid control 10:47 The trash-bag tying demo 13:07 The robotics data pyramid 14:13 Transferring skills across robots 16:30 How does Motion Transfer work 16:56 Why a separate reasoning model 19:02 Can distillation work in robotics? 20:02 The ASIMOV safety benchmark 22:47 VLAs vs world models 25:10 The missing tactile sensing piece 27:48 How far to physical AGI? 30:07 Fundamental breakthrough needed? 31:53 World models for evaluation 33:45 Will the model layer commoditize? 35:11 Humanoid as a form factor

The Humanoid Hub

17,217 görüntüleme • 1 ay önce

NEWS: Humanoid robotics company Figure has released Helix 02, what they claim in their most capable humanoid model yet. "A single neural system that controls the full body directly from pixels, enabling dexterous, long horizon autonomy across an entire room: • Autonomous, long‑horizon loco-manipulation: Helix 02 unloads and reloads a dishwasher across a full-sized kitchen - a four-minute, end-to-end autonomous task that integrates walking, manipulation, and balance with no resets and no human intervention. We believe this is the longest horizon, most complex task completed autonomously by a humanoid robot to date. • All sensors in. All actuators out: Helix 02 connects every onboard sensor - vision, touch, and proprioception - directly to every actuator through a single unified visuomotor neural network. • Human-like whole body control from human data: All results are enabled by System 0, a learned whole‑body controller trained on over 1,000 hours of human motion data and sim‑to‑real reinforcement learning. System 0 replaces 109,504 lines of hand‑engineered C++ with a single neural prior for stable, natural motion. • New classes of dexterity: With Figure 03’s embedded tactile sensing and palm cameras, Helix 02 performs manipulation that was previously out of reach: extracting individual pills, dispensing precise syringe volumes, and singulating small, irregular objects from clutter despite self‑occlusion. Helix 02 is trained on over 1,000 hours of human motion data and integrates vision, touch, and proprioception."
3:25

NEWS: Humanoid robotics company Figure has released Helix 02, what they claim in their most capable humanoid model yet. "A single neural system that controls the full body directly from pixels, enabling dexterous, long horizon autonomy across an entire room: • Autonomous, long‑horizon loco-manipulation: Helix 02 unloads and reloads a dishwasher across a full-sized kitchen - a four-minute, end-to-end autonomous task that integrates walking, manipulation, and balance with no resets and no human intervention. We believe this is the longest horizon, most complex task completed autonomously by a humanoid robot to date. • All sensors in. All actuators out: Helix 02 connects every onboard sensor - vision, touch, and proprioception - directly to every actuator through a single unified visuomotor neural network. • Human-like whole body control from human data: All results are enabled by System 0, a learned whole‑body controller trained on over 1,000 hours of human motion data and sim‑to‑real reinforcement learning. System 0 replaces 109,504 lines of hand‑engineered C++ with a single neural prior for stable, natural motion. • New classes of dexterity: With Figure 03’s embedded tactile sensing and palm cameras, Helix 02 performs manipulation that was previously out of reach: extracting individual pills, dispensing precise syringe volumes, and singulating small, irregular objects from clutter despite self‑occlusion. Helix 02 is trained on over 1,000 hours of human motion data and integrates vision, touch, and proprioception."

Sawyer Merritt

624,770 görüntüleme • 7 ay önce

This marks the sixth time one of my scooters has been stolen, and the sixth successful recovery. The theft was a crime of opportunity, not connected to any protesters. Still, I’m sharing this footage because it happened at a demonstration. It’s just one entry in a wild archive of scooter retrievals, including alleyway stakeouts, a McDonald’s parking lot, and even a crack house in Hamilton. Moral of the story? Don’t mess with my ride. 📸 Aug 25, 2025 #Toronto #ProtestMania
1:13

This marks the sixth time one of my scooters has been stolen, and the sixth successful recovery. The theft was a crime of opportunity, not connected to any protesters. Still, I’m sharing this footage because it happened at a demonstration. It’s just one entry in a wild archive of scooter retrievals, including alleyway stakeouts, a McDonald’s parking lot, and even a crack house in Hamilton. Moral of the story? Don’t mess with my ride. 📸 Aug 25, 2025 #Toronto #ProtestMania

Caryma Sa'd - Lawyer + Political Satirist

33,320 görüntüleme • 1 yıl önce

🚀 The full HUMOTO dataset is now licensed to leading universities around the world — including Stanford, MIT, KAIST, CMU, UCLA, Tel Aviv University, University of Tübingen & MPI, Queen Mary University of London, and many more across the US, Europe, and Asia 🌍 Since launch, HUMOTO has received 90+ license requests from universities, companies, and individuals. After countless forms and approvals 😅, we’ve finally completed all the university applications — companies are next, while personal licenses… might take a bit longer 🤦‍♀️ HUMOTO has also been updated to meet the Adobe Commercially Safe standard — the go-to choice for high-integrity research 🧑‍🔬✨ 📍 Our paper will be presented this month at ICCV 2025 in Hawaii (poster session) and the Wild3D Workshop (🤯) — come check it out! 🔗 Find the full list of licensed institutions here:
0:28

🚀 The full HUMOTO dataset is now licensed to leading universities around the world — including Stanford, MIT, KAIST, CMU, UCLA, Tel Aviv University, University of Tübingen & MPI, Queen Mary University of London, and many more across the US, Europe, and Asia 🌍 Since launch, HUMOTO has received 90+ license requests from universities, companies, and individuals. After countless forms and approvals 😅, we’ve finally completed all the university applications — companies are next, while personal licenses… might take a bit longer 🤦‍♀️ HUMOTO has also been updated to meet the Adobe Commercially Safe standard — the go-to choice for high-integrity research 🧑‍🔬✨ 📍 Our paper will be presented this month at ICCV 2025 in Hawaii (poster session) and the Wild3D Workshop (🤯) — come check it out! 🔗 Find the full list of licensed institutions here:

Yi Zhou

13,433 görüntüleme • 10 ay önce

New framework: Kick down your robot, it will get back up every time 🥋 Chinese startup RoboParty is a Beijing startup founded April 2025 by Huang Yi, originally shipping ROBOTO ORIGIN, the world's first full-stack open-source bipedal humanoid. They released UFO: Unsupervised Reinforcement Learning Framework for Humanoid Control. DEFINITIONS -> what differs is where the learning signal comes from: - SUPERVISED: humans supply the right answers (labels), the model imitates them. - UNSUPERVISED: no answer key, the model finds structure in raw data on its own. - REINFORCEMENT LEARNING: no answer key either, the model tries things and a reward scores each attempt. → UNSUPERVISED RL: trial and error where the agent invents its own rewards, instead of engineers hand-writing one per task. REPRESENTATION LEARNING: compress raw states into a useful internal map. TEMPORAL DISTANCE: distance on that map is "how many steps from A to B." CONTRASTIVE: trained by pulling together what's close in time, pushing apart what isn't. -> CONTRASTIVE TEMPORAL-DISTANCE REPRESENTATION LEARNING: the model builds an internal map of body states where distance means how many steps it takes to get from one to another. It is trained by contrast: states that occur close together in a movement get pulled together in the map, randomly paired states get pushed apart. UFO is an open-source training framework that teaches humanoid robots skills, like getting up, walking, goal-reaching, teleoperation, without reference motions -> no motion-capture or human-video demonstrations to imitate. Its core is TeCH, a contrastive temporal-distance representation-learning algorithm: the robot explores, builds pseudo-goals by temporal rolling, and learns goal-conditioned policies from a single unified progress reward. One framework trains five different robots (Unitree G1/H1, RoboParty RP0/RP1, AgiBot X2) with automatic config conversion in ~2–3 hours per robot! The real novelty here "no demonstrations at all". No data-collection arms race,the dominant humanoid-locomotion recipe is tracking: imitate mocap/retargeted-human reference trajectories. The robot self-generates goals from its own exploration and learns from a progress reward, needing zero reference motion data. Everybody else is fighting over data acquisition, while this team just teleports out of the race entirely (inb4 "competition is for losers 💀 ). This strategy reminds me of the DeepSeek playbook applied to robots: open-source the whole stack to become the global default and commoditize everyone else. RoboParty is giving away hardware and now control software (UFO) to be the Android of humanoids. Yet another reason for the US to ban Chinese open models perhaps 🥶 ? What I also really like about this approach is the cross-embodiment infrastructure, one framework trains Unitree G1/H1, RoboParty RP0/RP1, and AgiBot X2 with automatic configuration conversion. Just like Physical Intelligence, RoboParty seems to place itself as a neutral hardware agnostic middle man. Also woth mentioning: their ability ot perform stable skill injection, e.g. adding a cartwheel without forgetting how to walk. A common failure of RL humanoid policies is that teaching a new agile skill destabilizes the existing ones (catastrophic forgetting). UFO claims you can inject rare motions (cartwheel) without collapsing learned behavior. If it holds, that's a significant incremental/continual skill-learning! But again, I have to underline it: no arXiv, no external validation, no success-rate numbers. -> robotics badely needs an independent unbiased evaluator imho. Still, look at that cool demo: robot is getting kicked and pushed around (serious disturbance) during teleoperation (controlled the person at the back wearing the VR headset), and still managed to always get back up. This is some serious demonstration of stability and robustness!
0:49

New framework: Kick down your robot, it will get back up every time 🥋 Chinese startup RoboParty is a Beijing startup founded April 2025 by Huang Yi, originally shipping ROBOTO ORIGIN, the world's first full-stack open-source bipedal humanoid. They released UFO: Unsupervised Reinforcement Learning Framework for Humanoid Control. DEFINITIONS -> what differs is where the learning signal comes from: - SUPERVISED: humans supply the right answers (labels), the model imitates them. - UNSUPERVISED: no answer key, the model finds structure in raw data on its own. - REINFORCEMENT LEARNING: no answer key either, the model tries things and a reward scores each attempt. → UNSUPERVISED RL: trial and error where the agent invents its own rewards, instead of engineers hand-writing one per task. REPRESENTATION LEARNING: compress raw states into a useful internal map. TEMPORAL DISTANCE: distance on that map is "how many steps from A to B." CONTRASTIVE: trained by pulling together what's close in time, pushing apart what isn't. -> CONTRASTIVE TEMPORAL-DISTANCE REPRESENTATION LEARNING: the model builds an internal map of body states where distance means how many steps it takes to get from one to another. It is trained by contrast: states that occur close together in a movement get pulled together in the map, randomly paired states get pushed apart. UFO is an open-source training framework that teaches humanoid robots skills, like getting up, walking, goal-reaching, teleoperation, without reference motions -> no motion-capture or human-video demonstrations to imitate. Its core is TeCH, a contrastive temporal-distance representation-learning algorithm: the robot explores, builds pseudo-goals by temporal rolling, and learns goal-conditioned policies from a single unified progress reward. One framework trains five different robots (Unitree G1/H1, RoboParty RP0/RP1, AgiBot X2) with automatic config conversion in ~2–3 hours per robot! The real novelty here "no demonstrations at all". No data-collection arms race,the dominant humanoid-locomotion recipe is tracking: imitate mocap/retargeted-human reference trajectories. The robot self-generates goals from its own exploration and learns from a progress reward, needing zero reference motion data. Everybody else is fighting over data acquisition, while this team just teleports out of the race entirely (inb4 "competition is for losers 💀 ). This strategy reminds me of the DeepSeek playbook applied to robots: open-source the whole stack to become the global default and commoditize everyone else. RoboParty is giving away hardware and now control software (UFO) to be the Android of humanoids. Yet another reason for the US to ban Chinese open models perhaps 🥶 ? What I also really like about this approach is the cross-embodiment infrastructure, one framework trains Unitree G1/H1, RoboParty RP0/RP1, and AgiBot X2 with automatic configuration conversion. Just like Physical Intelligence, RoboParty seems to place itself as a neutral hardware agnostic middle man. Also woth mentioning: their ability ot perform stable skill injection, e.g. adding a cartwheel without forgetting how to walk. A common failure of RL humanoid policies is that teaching a new agile skill destabilizes the existing ones (catastrophic forgetting). UFO claims you can inject rare motions (cartwheel) without collapsing learned behavior. If it holds, that's a significant incremental/continual skill-learning! But again, I have to underline it: no arXiv, no external validation, no success-rate numbers. -> robotics badely needs an independent unbiased evaluator imho. Still, look at that cool demo: robot is getting kicked and pushed around (serious disturbance) during teleoperation (controlled the person at the back wearing the VR headset), and still managed to always get back up. This is some serious demonstration of stability and robustness!

Léo

35,855 görüntüleme • 28 gün önce

Everybody is talking about recursive self-improvement (RSI) and meta learning. Here is my old 2020 talk about this [1]. It has aged well. Example: humans still define the starts & ends of trials of many modern meta learners. My RSI systems since 1994 LEARN to (re)define them [2]! [1] Meta Learning Machines in a Single Lifelong Trial (talk for workshops at ICML 2020 and NeurIPS 2021, based on earlier talks since 1994). Abstract: the most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987 [2]. Here I summarize our work on meta reinforcement learning with self-modifying policies in a single lifelong trial (since 1994), and mathematically optimal meta-learning through the self-referential Gödel Machine (since 2003). Many additional publications on meta-learning since 1987 can be found in the RSI overview [2]. [2] J. Schmidhuber (AI Blog, 2020-2025). 1/3 century anniversary of first publication on recursive self-improvement (RSI) and meta learning machines that learn to learn (1987). For its cover I drew a robot that bootstraps itself. 1992-: gradient descent-based neural meta learning. 1994-: meta reinforcement learning with self-modifying policies. 1997: meta RL plus artificial curiosity and intrinsic motivation. 2002-: asymptotically optimal meta learning for curriculum learning. 2003-: mathematically optimal Gödel Machine. 2020-: new stuff!
23:42

Everybody is talking about recursive self-improvement (RSI) and meta learning. Here is my old 2020 talk about this [1]. It has aged well. Example: humans still define the starts & ends of trials of many modern meta learners. My RSI systems since 1994 LEARN to (re)define them [2]! [1] Meta Learning Machines in a Single Lifelong Trial (talk for workshops at ICML 2020 and NeurIPS 2021, based on earlier talks since 1994). Abstract: the most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987 [2]. Here I summarize our work on meta reinforcement learning with self-modifying policies in a single lifelong trial (since 1994), and mathematically optimal meta-learning through the self-referential Gödel Machine (since 2003). Many additional publications on meta-learning since 1987 can be found in the RSI overview [2]. [2] J. Schmidhuber (AI Blog, 2020-2025). 1/3 century anniversary of first publication on recursive self-improvement (RSI) and meta learning machines that learn to learn (1987). For its cover I drew a robot that bootstraps itself. 1992-: gradient descent-based neural meta learning. 1994-: meta reinforcement learning with self-modifying policies. 1997: meta RL plus artificial curiosity and intrinsic motivation. 2002-: asymptotically optimal meta learning for curriculum learning. 2003-: mathematically optimal Gödel Machine. 2020-: new stuff!

Jürgen Schmidhuber

232,164 görüntüleme • 5 ay önce

Found the suppressed video of Charlie Kirk at the Andy Biggs launch rally May 31, 2025. It’s been scrubbed from TPUSA outlets. In it, Charlie spoke of a long 10-year journey and the wild ride ahead pushing toward 2026. He urged: keep the narrative and the story straight. Frank Turek claimed they were “mentoring Charlie to be better.” Bullshit. Charlie was the best-flawed like any man, but a powerhouse. What they meant was narrative control. Charlie started breaking free, telling his own story. He never got to finish it. The truth got him killed on Sept. 10, 2025. He wasn’t perfect. He was controlled. This was his last major TPAction rally. They couldn’t control him forever. Rest in power and peace, Charlie. The fight continues.
0:38

Found the suppressed video of Charlie Kirk at the Andy Biggs launch rally May 31, 2025. It’s been scrubbed from TPUSA outlets. In it, Charlie spoke of a long 10-year journey and the wild ride ahead pushing toward 2026. He urged: keep the narrative and the story straight. Frank Turek claimed they were “mentoring Charlie to be better.” Bullshit. Charlie was the best-flawed like any man, but a powerhouse. What they meant was narrative control. Charlie started breaking free, telling his own story. He never got to finish it. The truth got him killed on Sept. 10, 2025. He wasn’t perfect. He was controlled. This was his last major TPAction rally. They couldn’t control him forever. Rest in power and peace, Charlie. The fight continues.

Matt Tucciarone

59,476 görüntüleme • 2 ay önce