Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🎓 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 Aufrufe • vor 1 Jahr •via X (Twitter)

Gesundheit & WellnessBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Jim Fan
Jim Fanvor 1 Jahr

So proud of you!!

Profilbild von Zhengyi “Zen” Luo
Zhengyi “Zen” Luovor 1 Jahr

Thank you boss 🫡

Profilbild von Estadio Deportes
Estadio Deportesvor 1 Jahr

#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

Profilbild von Baixin Guo(Max)
Baixin Guo(Max)vor 1 Jahr

恭喜啊哥🎉

Profilbild von ζ Pedram ζ
ζ Pedram ζvor 1 Jahr

Good stuff, Kung Fu time?

Profilbild von Andrew Carr (e/🤸)
Andrew Carr (e/🤸)vor 1 Jahr

Congrats Zen

Profilbild von Zhengyi “Zen” Luo
Zhengyi “Zen” Luovor 1 Jahr

Thanks Andrew!!!

Profilbild von mansin
mansinvor 1 Jahr

Baller

Profilbild von Markie Kendahl
Markie Kendahlvor 1 Jahr

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

Profilbild von 10
10vor 1 Jahr

good job

Profilbild von SHILONG SUN
SHILONG SUNvor 1 Jahr

Congrats, Dr.

Ähnliche Videos

🤖✨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

13,261 Aufrufe • vor 2 Monaten

🎾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

45,830 Aufrufe • vor 5 Monaten

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

62,208 Aufrufe • vor 9 Monaten

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🤖

41,928 Aufrufe • vor 1 Monat

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 Aufrufe • vor 6 Monaten

🎥 A special message from JISOO just for you! 💜 JISOO is beyond excited to meet her fans at the 2025 JISOO ASIA TOUR: Lights, Love, Action! in Manila!✨ 📅 March 14, 2025 (Friday) 📍 Smart Araneta Coliseum 📌 Get your tickets at: Don’t miss this once-in-a-lifetime chance to see JISOO live! Are you ready, Manila? 💖🔥 #JISOOinMANILA #LIGHTSLOVEACTIONinMNL #JISOO #지수
0:35

🎥 A special message from JISOO just for you! 💜 JISOO is beyond excited to meet her fans at the 2025 JISOO ASIA TOUR: Lights, Love, Action! in Manila!✨ 📅 March 14, 2025 (Friday) 📍 Smart Araneta Coliseum 📌 Get your tickets at: Don’t miss this once-in-a-lifetime chance to see JISOO live! Are you ready, Manila? 💖🔥 #JISOOinMANILA #LIGHTSLOVEACTIONinMNL #JISOO #지수

Collective Touring Philippines

26,844 Aufrufe • vor 1 Jahr

🤖 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 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

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

118,133 Aufrufe • vor 10 Monaten

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 Aufrufe • vor 6 Monaten

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 Aufrufe • vor 11 Monaten

🚀 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 Aufrufe • vor 10 Monaten

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

35,705 Aufrufe • vor 12 Tagen

China’s pretty humanoid robot stuns by opening a car door in a ‘world’s first’ | Jijo Malayil, Interesting Engineering Mornine used onboard sensors and full-body control to locate the handle, adjust posture, and open a car door—no human input needed. AiMOGA Robotics has claimed to have reached a significant milestone in embodied AI with its humanoid robot, Mornine, autonomously opening a car door inside a functioning Chery dealership in China. Relying solely on onboard sensors, full-body motion control, and end-to-end reinforcement learning, Mornine performed the task without any human input. Unlike scripted or teleoperated robots, Mornie identified the door handle, adjusted its posture, and used coordinated force across its limbs and torso to complete the action—demonstrating advanced autonomy in a real-world setting. “The deployment marks one of the first instances of a service robot executing such a high-friction, physical interaction in a live commercial setting,” said the firm in a statement. In April, at the Shanghai Auto Show, automotive brands Omoda and Jaecoo, subsidiaries of Chery Automobile, introduced Mornine, designed for use in car dealerships. From sim to service Opening a car door may seem like a simple task, but AiMOGA Robotics views it as a pivotal moment in robotics—signaling a shift from simulation to real-world service, and from basic command execution to autonomous capability. Using only onboard sensors and full-body motion control, Mornine identified the door handle, adjusted her posture, and applied coordinated force across her limbs to open the door—entirely without human intervention. Mornine’s advanced sensor suite includes 3D LiDAR, depth and wide-angle cameras, and a visual-language model (VLM), enabling real-time perception of door position and opening status. Uniquely, Mornine wasn’t explicitly programmed to recognize door handles. Instead, she learned through reinforcement learning, undergoing millions of simulated cycles to focus on the right region and perform the task independently. “We never explicitly told the robot what a door handle is. It learned to focus on that region by itself,” said the engineering team at AiMOGA Robotics in a statement. The learned model was transferred to the real world using Sim2Real methods. Mornine continuously gathers live sensor data during operation, which feeds into a cloud-based training loop, allowing her to improve through continuous learning in real-world settings, reports Robotics Tomorrow. Now active in multiple Chery 4S dealerships in China, Mornine not only opens car doors but also assists with customer greetings, vehicle introductions, and item delivery—marking a step forward in humanoid robotics for commercial retail environments. AI meets retail Originally introduced as the AiMOGA Robot, Mornine was developed to support dealership sales by performing tasks such as explaining vehicle specifications, leading showroom tours, serving refreshments, and engaging with customers in multiple languages. First conceived by Chery as a virtual character to appeal to Generation Z using metaverse and virtual human technologies, Mornine gradually evolved into a real-world interactive humanoid. After multiple iterations of character and model design, Mornine debuted as a digital persona in animations, livestreams, and promotional content, gaining brand recognition. Chery later expanded the concept beyond the virtual space, resulting in the creation of the AiMOGA humanoid robot. Leveraging Chery’s expertise in autonomous driving, environmental sensing, and control systems, AiMOGA features full-stack capabilities in perception, cognition, decision-making, and execution. It uses multimodal sensing—combining speech, vision, and environmental data—to interpret user gestures, commands, and showroom dynamics. A bionic motion system and automotive-grade hardware enable dexterous movement and upright mobility, while multi-robot collaboration allows for coordinated tasks like guided tours. At the decision-making layer, Deepseek’s large language models enable natural language understanding and personalized interaction. In April 2025, Mornine officially began commercial service as an “Intelligent Sales Consultant” at the OMODA C5 JOYSTAR 4S dealership in Kuala Lumpur, Malaysia—marking her full transition from a virtual concept to a real-world humanoid sales assistant.
0:48

China’s pretty humanoid robot stuns by opening a car door in a ‘world’s first’ | Jijo Malayil, Interesting Engineering Mornine used onboard sensors and full-body control to locate the handle, adjust posture, and open a car door—no human input needed. AiMOGA Robotics has claimed to have reached a significant milestone in embodied AI with its humanoid robot, Mornine, autonomously opening a car door inside a functioning Chery dealership in China. Relying solely on onboard sensors, full-body motion control, and end-to-end reinforcement learning, Mornine performed the task without any human input. Unlike scripted or teleoperated robots, Mornie identified the door handle, adjusted its posture, and used coordinated force across its limbs and torso to complete the action—demonstrating advanced autonomy in a real-world setting. “The deployment marks one of the first instances of a service robot executing such a high-friction, physical interaction in a live commercial setting,” said the firm in a statement. In April, at the Shanghai Auto Show, automotive brands Omoda and Jaecoo, subsidiaries of Chery Automobile, introduced Mornine, designed for use in car dealerships. From sim to service Opening a car door may seem like a simple task, but AiMOGA Robotics views it as a pivotal moment in robotics—signaling a shift from simulation to real-world service, and from basic command execution to autonomous capability. Using only onboard sensors and full-body motion control, Mornine identified the door handle, adjusted her posture, and applied coordinated force across her limbs to open the door—entirely without human intervention. Mornine’s advanced sensor suite includes 3D LiDAR, depth and wide-angle cameras, and a visual-language model (VLM), enabling real-time perception of door position and opening status. Uniquely, Mornine wasn’t explicitly programmed to recognize door handles. Instead, she learned through reinforcement learning, undergoing millions of simulated cycles to focus on the right region and perform the task independently. “We never explicitly told the robot what a door handle is. It learned to focus on that region by itself,” said the engineering team at AiMOGA Robotics in a statement. The learned model was transferred to the real world using Sim2Real methods. Mornine continuously gathers live sensor data during operation, which feeds into a cloud-based training loop, allowing her to improve through continuous learning in real-world settings, reports Robotics Tomorrow. Now active in multiple Chery 4S dealerships in China, Mornine not only opens car doors but also assists with customer greetings, vehicle introductions, and item delivery—marking a step forward in humanoid robotics for commercial retail environments. AI meets retail Originally introduced as the AiMOGA Robot, Mornine was developed to support dealership sales by performing tasks such as explaining vehicle specifications, leading showroom tours, serving refreshments, and engaging with customers in multiple languages. First conceived by Chery as a virtual character to appeal to Generation Z using metaverse and virtual human technologies, Mornine gradually evolved into a real-world interactive humanoid. After multiple iterations of character and model design, Mornine debuted as a digital persona in animations, livestreams, and promotional content, gaining brand recognition. Chery later expanded the concept beyond the virtual space, resulting in the creation of the AiMOGA humanoid robot. Leveraging Chery’s expertise in autonomous driving, environmental sensing, and control systems, AiMOGA features full-stack capabilities in perception, cognition, decision-making, and execution. It uses multimodal sensing—combining speech, vision, and environmental data—to interpret user gestures, commands, and showroom dynamics. A bionic motion system and automotive-grade hardware enable dexterous movement and upright mobility, while multi-robot collaboration allows for coordinated tasks like guided tours. At the decision-making layer, Deepseek’s large language models enable natural language understanding and personalized interaction. In April 2025, Mornine officially began commercial service as an “Intelligent Sales Consultant” at the OMODA C5 JOYSTAR 4S dealership in Kuala Lumpur, Malaysia—marking her full transition from a virtual concept to a real-world humanoid sales assistant.

Owen Gregorian

67,975 Aufrufe • vor 1 Jahr

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

224,085 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 1 Monat

NEW: Here's the walk and talk from after the final pretrial conference leading up to next week's Karen Read retrial. I asked Karen if she was pleased to win a motion preventing her text messages with David Yannetti from coming into evidence (possibly involving a confession that Karen "didn't think she hit John that hard" with her car on the morning of 1/29/22). Although Karen had no comment, Read did mention she does not plan to be silent going forward during trial, when questioned by my colleagues (however her lawyers are subject to a gag order, and only commented on the Celtics). Also, while Aidan TurtleBoy earney was at today's hearing, he left before Read walked out of the courthouse. Kearney, who is on the state's witness list, has already had the contents of his phone handed over to Hank Brennan, as to Kearney's communications with Read, and that may well be a preview of Brennan's upcoming motion for a consciousness of guilt instruction to jurors during Read's retrial. Overall, after a flurry of other motions were decided earlier last week, only two dozen motions remain outstanding before jury empanelment begins on Tuesday April 1, 2025. Judge Cannone still has a number of motions under advisement (including major motions related to the defense being prohibited from, again, raising a third party culprit defense without court permission, along with motions related to introducing evidence of John O'Keefe's state of mind, as to John wanting to end the relationship with Karen because of Karen cheating and because of Karen's views on John's adopted, double-orphaned, niece and nephew). 30 such motions have been decided, and 22 remain outstanding, as of 2pm ET on 3/25/25. I. Motions with rulings: 1. Commonwealth's Motion to Unseal FTR Audio from March 4, 2025 for Counsel of Record Only (Docket 542) Ruling: Allowed (Cannone, J) - Dated 3/4/25 2. Commonwealth's Motion to Unseal Recordings of Gretchen Voss and/or Metro Corp. (Docket 543) Ruling: Allowed without opposition (Cannone, J) - Dated 3/5/25 3. Commonwealth's Motion for Protective Order (Docket 557) Ruling: So Ordered (Cannone, J) - Dated 3/10/25 4. Defendant's Motion in Limine to Exclude Certain Witnesses Before and After Testimony (UNREDACTED) (Docket 562) Ruling: Allowed, except those witnesses exempted by Docket 576. Witnesses are sequestered before and after testimony until the close of evidence. When testimony is concluded, the courtroom is open and no one is excluded. (Cannone, J) - Dated 3/18/25 5. Defendant's Motion in Limine for View (Docket 564) Ruling: Allowed; Counsel need to work out details of exactly how Defendant will attend. (Cannone, J) - Dated 3/18/25 6. Defendant's Motion in Limine to Prohibit Testimony Regarding Funds Paid to Experts for Purposes of Voir Dire (Docket 565) Ruling: Allowed by agreement (Cannone, J) - Dated 3/18/25 7. Defendant's Motion for Attorney-Conducted Panel Voir Dire (Docket 566) Ruling: Denied (Cannone, J) - Dated 3/18/25 8. Defendant's Motion for Order Prohibiting the Commonwealth and its Agents from Speaking with or Having Contact with Any Witnesses Once They Have Taken the Stand (Docket 567) Ruling: Allowed as to both sides (Cannone, J) - Dated 3/18/25 9. Defendant's Motion to Impound Defendant's Motion in Limine to Exclude Irrelevant, Inadmissible, and Prejudicial Evidence Regarding Alleged Harassment and/or Intimidation of Witnesses (Docket 568) Ruling: Allowed (Cannone, J) - Dated 3/18/25 10. Defendant's Motion to Impound Defendant's Motion in Limine to Exclude Witness's Prior Criminal History (Docket 572) Ruling: Allowed (Cannone, J) - Date not specified 11. Defendant's Motion in Limine to Exclude Witness's Prior Criminal History (IMPOUNDED) (Docket 574) Ruling: Allowed without objection (Cannone, J) - Dated 3/18/25 12. Commonwealth's Motion in Limine to Allow In-Court Identification (Docket 577) Ruling: Allowed (Cannone, J) - Dated 3/19/25 13. Commonwealth's Motion in Limine to Admit (1) Victim's Photograph and (2) Photographs of the Victim's Injuries as Observed by Medical Providers on January 29, 2022 from Autopsy (Docket 578) Ruling: Allowed (Cannone, J) - Dated 3/19/25 14. Commonwealth's Motion in Limine to Introduce Certified Records from Registry of Motor Vehicles (Docket 580) Ruling: Allowed (Cannone, J) - Dated 3/18/25 15. Commonwealth's Motion in Limine of Intent to Obtain CORI Records of Potential Jurors (Docket 581) Ruling: Allowed (Cannone, J) - Dated 3/18/25 16. Commonwealth's Motion for Offer of Proof Prior to Defendant Calling or Summoning the Norfolk District Attorney and Victim Witness Advocate as Witnesses and Request for an Order that Neither is Subject to a Sequestration Order (Docket 582) Ruling: Allowed; No objection (Cannone, J) - Dated 3/18/25 17. Commonwealth's Motion in Limine Requesting Use of Chalks and Directing Both Parties to Provide Visual Presentations and Chalks Prior to Using (Docket 583) Ruling: Allowed (Cannone, J) - Dated 3/19/25 18. Commonwealth's Motion in Limine to Allow Expert Cellebrite Demonstration (Docket 584) Ruling: After hearing, Allowed (Cannone, J) - Dated 3/21/25 19. Commonwealth's Motion in Limine to Admit Results of Defendant's Blood Draw at Good Samaritan Hospital and Resulting Serum Conversion and Retrograde Extrapolation (Docket 586) Ruling: After hearing, Allowed (Cannone, J) - Dated 3/21/25 20. Commonwealth's Motion in Limine to Preclude Reference to Any Alleged "Bad Character" and Any Prior "Misconduct" of the Victim or Any Witness (Docket 587) Ruling: If counsel intend to introduce this evidence, Defendant must provide notice to the Commonwealth one week before the evidence begins (Cannone, J) - Dated 3/19/25 21. Defendant's Motion in Limine to Exclude False and Irrelevant Statements of Michael Proctor (Docket 591) Ruling: Commonwealth does not intend to offer this evidence. Stated in open court on 3/20/25 (Cannone, J) - Dated 3/20/25 22. Defendant's Motion in Limine to Allow Counsel to State Grounds for Objections to Promote Judicial Economy and Efficiency and to Adequately Preserve Issues (Docket 595) Ruling: Denied (Cannone, J) - Dated 3/19/25 23. Defendant's Motion to Impound the Defendant's Motion in Limine to Prohibit the Norfolk District Attorney and Massachusetts State Police from Having Juror Contact (Docket 597) Ruling: Allowed in that the Exhibits are Impounded (Cannone, J) - Dated 3/12/25 24. Defendant's Motion in Limine to Prohibit the Norfolk District Attorney and Massachusetts State Police from Having Juror Contact (Docket 599) Ruling: Motion based on a false premise. No one other than Trial Court Security coordinates juror security, and no one other than Court Officers has contact with jurors during trial. Norfolk County DA’s office, State Police, defense counsel, and media will have no contact with trial jurors (Cannone, J) - Dated 3/19/25 25. Defendant's Motion to Impound "Exhibit 1" in Support of Defendant's Motion in Limine to Exclude the Testimony of Commonwealth's Witness Dr. Judson Welcher, M.S., Ph.D., and Request for Voir Dire (Docket 604) Ruling: Allowed (Cannone, J) - Dated 3/14/25 26. Defendant's Supplemental Motion for Admission Pro Hac Vice of Mark A. Bederow (Docket 549) Ruling: Decision and Order [denying motion] issued (Cannone, J) - Dated 3/7/25 (Docket 551) 27. Commonwealth's Motion for Protective Order (Docket 617) Ruling: So Ordered (Cannone, J) - Dated 3/20/25 28. Defendant's Motion to Exclude the Testimony of the Commonwealth's Witness James W. Crosby, MS PhD Ruling: Denied (Cannone, J) - Dated 3/6/25 (Docket 548) 29. Commonwealth's Motion for Records from Dockets 2842CR00043 and 2382CR00313 [Aidan TurtleBoy Kearney open felony cases involving Read trial witnesses and Lindsey Gaetani) addressed to Special Assistant District Attorney Robert Cosgrove (Docket 546) Status: Allowed in part (Sisitsky, A). Memorandum & Order was issued on 3/20/25 (Docket 615) and an Order for Production of Records followed (Docket 616) 30. Commonwealth's Motion to Compel Communications Between the Defendant and Attorney Yannetti Stored within the Defendant's Cell Phone Data (Docket 618) Status: Denied (Cannone, J) - Dated 3/25/25 II. Motions with No Ruling or Taken Under Advisement: 31. Defendant's Motion to Exclude the Purported Expert Testimony of the Commonwealth's Proffered Witness Dr. Aizik L. Wolf and Request Daubert-Lanigan Hearing (Docket 540) Status: No ruling specified 32. Commonwealth's Motion for Extension of Time to File Motions in Limine Related to Defense Expert Reciprocal Discovery (Docket 552) Status: No ruling specified 33. Commonwealth's Motion to Correct the Record (Docket 553) Status: No ruling specified 34. Defendant's Motion in Limine to Present Demonstrative Exhibit Based on Christina Hanley's Testimony (Docket 558) Status: No action taken at this time (Cannone, J) - Dated 3/20/25 35. Defendant's Motion in Limine to Exclude Irrelevant, Inadmissible, and Prejudicial Prior Bad Character and Propensity Evidence (Docket 559) Status: No ruling specified 36. Defendant's Motion to Impound Portions of Defendant's Motion in Limine to Exclude Certain Witnesses Before and After Testimony (Docket 560) Status: No ruling specified 37. Defendant's Motion in Limine to Exclude Serum/Plasma Ethanol Concentration, Blood Ethanol Concentration Conversion, and Corresponding Retrograde Extrapolation Analysis (Docket 571) Status: No ruling specified 38. Commonwealth's Motion in Limine to Appoint Court Stenographer, Prevent Identification of Jurors, and Impound Juror Names During Trial (Docket 575) Status: No ruling specified 39. Commonwealth's Motion in Limine for Sequestration Order and for Relief from that Order for Family Members of the Victim (Docket 576) Status: No ruling specified (though referenced in Docket 562 as exempting certain witnesses, indicating 576 may soon be allowed) 40. Commonwealth's Motion in Limine to Preclude Reference to and Redact the Manner of Death Contained on the Victim's Death Certificate (Docket 579) Status: No ruling specified 41. Commonwealth's Motion in Limine to Admit the Victim's Out of Court Statements Relating to His State of Mind (Docket 585) Status: No action taken - Need to see how the evidence develops (Cannone, J) - Dated 3/20/25 42. Commonwealth's Motion in Limine to Prohibit Reference to Any Pending Internal Affairs Investigations; Sustained Findings Unrelated to This Case; or Unfounded Allegations of Misconduct (Docket 588) Status: No action (Cannone, J) - Dated 3/19/25 43. Commonwealth's Motion in Limine to Preclude the Defendant from Raising a Third-Party Culprit Defense (Docket 589) Status: No ruling specified (Defense filed opposition, 3/25/25, Docket 625) 44. Commonwealth's Motion for Attorney-Conducted and Individual Voir Dire of Potential Jurors and Proposed Jury Questionnaire (Docket 590) Status: No ruling specified 45. Defendant's Motion in Limine to Allow Evidence of Lack of Bias (Docket 593) Status: No ruling specified (Commonwealth filed opposition, 3/17/25, Docket 610) 46. Defendant's Motion for Reconsideration of March 6, 2025 Court Order Denying Defendant's Motion to Exclude the Testimony of the Commonwealth's Witness James W. Crosby, MS PhD (Docket 601) Status: No ruling specified 47. Defendant's Motion in Limine to Exclude the Testimony of Commonwealth's Witness Dr. Judson Welcher, M.S., Ph.D., and Request for Voir Dire (Docket 606) Status: No ruling specified (Commonwealth filed opposition, 3/17/25, Docket 609) 48. Commonwealth's Motion in Limine to Exclude Expert Testimony of Garrett Wing (Docket 607) Status: No ruling specified 49. Commonwealth's Motion in Limine to Exclude Defense's Expert Michael Easter's Opinion of the Investigation (Docket 608) Status: No ruling specified 50. Commonwealth's Motion for Buffer Zone and Order Prohibiting Signs or Clothing in Favor of Either Party or Law Enforcement (Docket 611) Status: No ruling specified 51. Defendant's Assented to Motion to Continue Trial Date on or After April 25, 2025 (Docket 613) Status: Denied without prejudice. Trial will begin with empanelment on April 1, 2025 as scheduled. If a jury is selected before April 28, 2025, counsel may renew the motion prior to the jury being sworn (Cannone, J) - Dated 3/19/25 51. Commonwealth's Motion for Records: Unsolved Productions, INC (Docket 620) Status: No ruling specified 52. Defendant 's Motion to Dismiss for Extraordinary Governmental Misconduct (REDACTED) (Docket 519) Status: No ruling specified (Commonwealth filed opposition 2/28/25, Docket 526) Please let me know if I missed any rulings, or if any information is misplaced. This content may be reposted, with attribution and a link to the original post.
3:36

NEW: Here's the walk and talk from after the final pretrial conference leading up to next week's Karen Read retrial. I asked Karen if she was pleased to win a motion preventing her text messages with David Yannetti from coming into evidence (possibly involving a confession that Karen "didn't think she hit John that hard" with her car on the morning of 1/29/22). Although Karen had no comment, Read did mention she does not plan to be silent going forward during trial, when questioned by my colleagues (however her lawyers are subject to a gag order, and only commented on the Celtics). Also, while Aidan TurtleBoy earney was at today's hearing, he left before Read walked out of the courthouse. Kearney, who is on the state's witness list, has already had the contents of his phone handed over to Hank Brennan, as to Kearney's communications with Read, and that may well be a preview of Brennan's upcoming motion for a consciousness of guilt instruction to jurors during Read's retrial. Overall, after a flurry of other motions were decided earlier last week, only two dozen motions remain outstanding before jury empanelment begins on Tuesday April 1, 2025. Judge Cannone still has a number of motions under advisement (including major motions related to the defense being prohibited from, again, raising a third party culprit defense without court permission, along with motions related to introducing evidence of John O'Keefe's state of mind, as to John wanting to end the relationship with Karen because of Karen cheating and because of Karen's views on John's adopted, double-orphaned, niece and nephew). 30 such motions have been decided, and 22 remain outstanding, as of 2pm ET on 3/25/25. I. Motions with rulings: 1. Commonwealth's Motion to Unseal FTR Audio from March 4, 2025 for Counsel of Record Only (Docket 542) Ruling: Allowed (Cannone, J) - Dated 3/4/25 2. Commonwealth's Motion to Unseal Recordings of Gretchen Voss and/or Metro Corp. (Docket 543) Ruling: Allowed without opposition (Cannone, J) - Dated 3/5/25 3. Commonwealth's Motion for Protective Order (Docket 557) Ruling: So Ordered (Cannone, J) - Dated 3/10/25 4. Defendant's Motion in Limine to Exclude Certain Witnesses Before and After Testimony (UNREDACTED) (Docket 562) Ruling: Allowed, except those witnesses exempted by Docket 576. Witnesses are sequestered before and after testimony until the close of evidence. When testimony is concluded, the courtroom is open and no one is excluded. (Cannone, J) - Dated 3/18/25 5. Defendant's Motion in Limine for View (Docket 564) Ruling: Allowed; Counsel need to work out details of exactly how Defendant will attend. (Cannone, J) - Dated 3/18/25 6. Defendant's Motion in Limine to Prohibit Testimony Regarding Funds Paid to Experts for Purposes of Voir Dire (Docket 565) Ruling: Allowed by agreement (Cannone, J) - Dated 3/18/25 7. Defendant's Motion for Attorney-Conducted Panel Voir Dire (Docket 566) Ruling: Denied (Cannone, J) - Dated 3/18/25 8. Defendant's Motion for Order Prohibiting the Commonwealth and its Agents from Speaking with or Having Contact with Any Witnesses Once They Have Taken the Stand (Docket 567) Ruling: Allowed as to both sides (Cannone, J) - Dated 3/18/25 9. Defendant's Motion to Impound Defendant's Motion in Limine to Exclude Irrelevant, Inadmissible, and Prejudicial Evidence Regarding Alleged Harassment and/or Intimidation of Witnesses (Docket 568) Ruling: Allowed (Cannone, J) - Dated 3/18/25 10. Defendant's Motion to Impound Defendant's Motion in Limine to Exclude Witness's Prior Criminal History (Docket 572) Ruling: Allowed (Cannone, J) - Date not specified 11. Defendant's Motion in Limine to Exclude Witness's Prior Criminal History (IMPOUNDED) (Docket 574) Ruling: Allowed without objection (Cannone, J) - Dated 3/18/25 12. Commonwealth's Motion in Limine to Allow In-Court Identification (Docket 577) Ruling: Allowed (Cannone, J) - Dated 3/19/25 13. Commonwealth's Motion in Limine to Admit (1) Victim's Photograph and (2) Photographs of the Victim's Injuries as Observed by Medical Providers on January 29, 2022 from Autopsy (Docket 578) Ruling: Allowed (Cannone, J) - Dated 3/19/25 14. Commonwealth's Motion in Limine to Introduce Certified Records from Registry of Motor Vehicles (Docket 580) Ruling: Allowed (Cannone, J) - Dated 3/18/25 15. Commonwealth's Motion in Limine of Intent to Obtain CORI Records of Potential Jurors (Docket 581) Ruling: Allowed (Cannone, J) - Dated 3/18/25 16. Commonwealth's Motion for Offer of Proof Prior to Defendant Calling or Summoning the Norfolk District Attorney and Victim Witness Advocate as Witnesses and Request for an Order that Neither is Subject to a Sequestration Order (Docket 582) Ruling: Allowed; No objection (Cannone, J) - Dated 3/18/25 17. Commonwealth's Motion in Limine Requesting Use of Chalks and Directing Both Parties to Provide Visual Presentations and Chalks Prior to Using (Docket 583) Ruling: Allowed (Cannone, J) - Dated 3/19/25 18. Commonwealth's Motion in Limine to Allow Expert Cellebrite Demonstration (Docket 584) Ruling: After hearing, Allowed (Cannone, J) - Dated 3/21/25 19. Commonwealth's Motion in Limine to Admit Results of Defendant's Blood Draw at Good Samaritan Hospital and Resulting Serum Conversion and Retrograde Extrapolation (Docket 586) Ruling: After hearing, Allowed (Cannone, J) - Dated 3/21/25 20. Commonwealth's Motion in Limine to Preclude Reference to Any Alleged "Bad Character" and Any Prior "Misconduct" of the Victim or Any Witness (Docket 587) Ruling: If counsel intend to introduce this evidence, Defendant must provide notice to the Commonwealth one week before the evidence begins (Cannone, J) - Dated 3/19/25 21. Defendant's Motion in Limine to Exclude False and Irrelevant Statements of Michael Proctor (Docket 591) Ruling: Commonwealth does not intend to offer this evidence. Stated in open court on 3/20/25 (Cannone, J) - Dated 3/20/25 22. Defendant's Motion in Limine to Allow Counsel to State Grounds for Objections to Promote Judicial Economy and Efficiency and to Adequately Preserve Issues (Docket 595) Ruling: Denied (Cannone, J) - Dated 3/19/25 23. Defendant's Motion to Impound the Defendant's Motion in Limine to Prohibit the Norfolk District Attorney and Massachusetts State Police from Having Juror Contact (Docket 597) Ruling: Allowed in that the Exhibits are Impounded (Cannone, J) - Dated 3/12/25 24. Defendant's Motion in Limine to Prohibit the Norfolk District Attorney and Massachusetts State Police from Having Juror Contact (Docket 599) Ruling: Motion based on a false premise. No one other than Trial Court Security coordinates juror security, and no one other than Court Officers has contact with jurors during trial. Norfolk County DA’s office, State Police, defense counsel, and media will have no contact with trial jurors (Cannone, J) - Dated 3/19/25 25. Defendant's Motion to Impound "Exhibit 1" in Support of Defendant's Motion in Limine to Exclude the Testimony of Commonwealth's Witness Dr. Judson Welcher, M.S., Ph.D., and Request for Voir Dire (Docket 604) Ruling: Allowed (Cannone, J) - Dated 3/14/25 26. Defendant's Supplemental Motion for Admission Pro Hac Vice of Mark A. Bederow (Docket 549) Ruling: Decision and Order [denying motion] issued (Cannone, J) - Dated 3/7/25 (Docket 551) 27. Commonwealth's Motion for Protective Order (Docket 617) Ruling: So Ordered (Cannone, J) - Dated 3/20/25 28. Defendant's Motion to Exclude the Testimony of the Commonwealth's Witness James W. Crosby, MS PhD Ruling: Denied (Cannone, J) - Dated 3/6/25 (Docket 548) 29. Commonwealth's Motion for Records from Dockets 2842CR00043 and 2382CR00313 [Aidan TurtleBoy Kearney open felony cases involving Read trial witnesses and Lindsey Gaetani) addressed to Special Assistant District Attorney Robert Cosgrove (Docket 546) Status: Allowed in part (Sisitsky, A). Memorandum & Order was issued on 3/20/25 (Docket 615) and an Order for Production of Records followed (Docket 616) 30. Commonwealth's Motion to Compel Communications Between the Defendant and Attorney Yannetti Stored within the Defendant's Cell Phone Data (Docket 618) Status: Denied (Cannone, J) - Dated 3/25/25 II. Motions with No Ruling or Taken Under Advisement: 31. Defendant's Motion to Exclude the Purported Expert Testimony of the Commonwealth's Proffered Witness Dr. Aizik L. Wolf and Request Daubert-Lanigan Hearing (Docket 540) Status: No ruling specified 32. Commonwealth's Motion for Extension of Time to File Motions in Limine Related to Defense Expert Reciprocal Discovery (Docket 552) Status: No ruling specified 33. Commonwealth's Motion to Correct the Record (Docket 553) Status: No ruling specified 34. Defendant's Motion in Limine to Present Demonstrative Exhibit Based on Christina Hanley's Testimony (Docket 558) Status: No action taken at this time (Cannone, J) - Dated 3/20/25 35. Defendant's Motion in Limine to Exclude Irrelevant, Inadmissible, and Prejudicial Prior Bad Character and Propensity Evidence (Docket 559) Status: No ruling specified 36. Defendant's Motion to Impound Portions of Defendant's Motion in Limine to Exclude Certain Witnesses Before and After Testimony (Docket 560) Status: No ruling specified 37. Defendant's Motion in Limine to Exclude Serum/Plasma Ethanol Concentration, Blood Ethanol Concentration Conversion, and Corresponding Retrograde Extrapolation Analysis (Docket 571) Status: No ruling specified 38. Commonwealth's Motion in Limine to Appoint Court Stenographer, Prevent Identification of Jurors, and Impound Juror Names During Trial (Docket 575) Status: No ruling specified 39. Commonwealth's Motion in Limine for Sequestration Order and for Relief from that Order for Family Members of the Victim (Docket 576) Status: No ruling specified (though referenced in Docket 562 as exempting certain witnesses, indicating 576 may soon be allowed) 40. Commonwealth's Motion in Limine to Preclude Reference to and Redact the Manner of Death Contained on the Victim's Death Certificate (Docket 579) Status: No ruling specified 41. Commonwealth's Motion in Limine to Admit the Victim's Out of Court Statements Relating to His State of Mind (Docket 585) Status: No action taken - Need to see how the evidence develops (Cannone, J) - Dated 3/20/25 42. Commonwealth's Motion in Limine to Prohibit Reference to Any Pending Internal Affairs Investigations; Sustained Findings Unrelated to This Case; or Unfounded Allegations of Misconduct (Docket 588) Status: No action (Cannone, J) - Dated 3/19/25 43. Commonwealth's Motion in Limine to Preclude the Defendant from Raising a Third-Party Culprit Defense (Docket 589) Status: No ruling specified (Defense filed opposition, 3/25/25, Docket 625) 44. Commonwealth's Motion for Attorney-Conducted and Individual Voir Dire of Potential Jurors and Proposed Jury Questionnaire (Docket 590) Status: No ruling specified 45. Defendant's Motion in Limine to Allow Evidence of Lack of Bias (Docket 593) Status: No ruling specified (Commonwealth filed opposition, 3/17/25, Docket 610) 46. Defendant's Motion for Reconsideration of March 6, 2025 Court Order Denying Defendant's Motion to Exclude the Testimony of the Commonwealth's Witness James W. Crosby, MS PhD (Docket 601) Status: No ruling specified 47. Defendant's Motion in Limine to Exclude the Testimony of Commonwealth's Witness Dr. Judson Welcher, M.S., Ph.D., and Request for Voir Dire (Docket 606) Status: No ruling specified (Commonwealth filed opposition, 3/17/25, Docket 609) 48. Commonwealth's Motion in Limine to Exclude Expert Testimony of Garrett Wing (Docket 607) Status: No ruling specified 49. Commonwealth's Motion in Limine to Exclude Defense's Expert Michael Easter's Opinion of the Investigation (Docket 608) Status: No ruling specified 50. Commonwealth's Motion for Buffer Zone and Order Prohibiting Signs or Clothing in Favor of Either Party or Law Enforcement (Docket 611) Status: No ruling specified 51. Defendant's Assented to Motion to Continue Trial Date on or After April 25, 2025 (Docket 613) Status: Denied without prejudice. Trial will begin with empanelment on April 1, 2025 as scheduled. If a jury is selected before April 28, 2025, counsel may renew the motion prior to the jury being sworn (Cannone, J) - Dated 3/19/25 51. Commonwealth's Motion for Records: Unsolved Productions, INC (Docket 620) Status: No ruling specified 52. Defendant 's Motion to Dismiss for Extraordinary Governmental Misconduct (REDACTED) (Docket 519) Status: No ruling specified (Commonwealth filed opposition 2/28/25, Docket 526) Please let me know if I missed any rulings, or if any information is misplaced. This content may be reposted, with attribution and a link to the original post.

Grant Smith Ellis

16,809 Aufrufe • vor 1 Jahr

When I was 8 years old, my favorite thing in the world was making mixtapes for my Walkman from my big sister’s CDs. That evolved into Lego stop-motion videos, and later, I fell down the rabbit hole of editing Naruto anime clips to Evanescence & Linkin Park beats. Looking back, it’s obvious: Sound and Video were always the main drivers in my life. I think that obsession also led me to my true love: Motion Design. A huge shoutout to Kevin who showed me +10 years ago the world of Motion Design. And honestly, look at where we are now. Who would have thought that there would be such a massive hype around Motion Design and UI promo videos? From giants like Airbnb to the new generation of creators like sutoxoriginals. The visual standard in 2026 is insane. But there was always one part of the process that felt like a grind to me: Sound Design. I love the result, but I hated the process. I was spending 4-5 hours per project just searching for the right sound effects. "Key typing effect" "Mouse click" "Subtle Whoosh" and so on.. So, I decided to fix it. I sat down with a Dev friend and we spent the last few weekends building a native AI tool right inside After Effects. The concept is simple: SoundDesigner AI watches your video. It understands the vibe and exactly what’s happening and when its happening. It sees a clock ticking or a text appearing, and it generates the perfect sound for it in seconds, synced to the action in your timeline. I’ve been using it on my own projects for a few days now, and it’s wild. My sound design workflow went actually from 5 hours to 20 minutes. We are launching this in February (fingers crossed for the approval at aescripts+aeplugins) If you want to see where this goes and try it out yourself, drop me a DM
0:30

When I was 8 years old, my favorite thing in the world was making mixtapes for my Walkman from my big sister’s CDs. That evolved into Lego stop-motion videos, and later, I fell down the rabbit hole of editing Naruto anime clips to Evanescence & Linkin Park beats. Looking back, it’s obvious: Sound and Video were always the main drivers in my life. I think that obsession also led me to my true love: Motion Design. A huge shoutout to Kevin who showed me +10 years ago the world of Motion Design. And honestly, look at where we are now. Who would have thought that there would be such a massive hype around Motion Design and UI promo videos? From giants like Airbnb to the new generation of creators like sutoxoriginals. The visual standard in 2026 is insane. But there was always one part of the process that felt like a grind to me: Sound Design. I love the result, but I hated the process. I was spending 4-5 hours per project just searching for the right sound effects. "Key typing effect" "Mouse click" "Subtle Whoosh" and so on.. So, I decided to fix it. I sat down with a Dev friend and we spent the last few weekends building a native AI tool right inside After Effects. The concept is simple: SoundDesigner AI watches your video. It understands the vibe and exactly what’s happening and when its happening. It sees a clock ticking or a text appearing, and it generates the perfect sound for it in seconds, synced to the action in your timeline. I’ve been using it on my own projects for a few days now, and it’s wild. My sound design workflow went actually from 5 hours to 20 minutes. We are launching this in February (fingers crossed for the approval at aescripts+aeplugins) If you want to see where this goes and try it out yourself, drop me a DM

Markus Gavrilov

20,299 Aufrufe • vor 6 Monaten