Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

1k placements a day—long-horizon tasks—using vision-only—learned behaviors for very precise <1cm sheet metal insertion. Requires intense engineering across multiple disciplines.

The Humanoid Hub

112,843 subscribers

136,724 Aufrufe • vor 1 Jahr •via X (Twitter)

Gesundheit & Wellness Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

7 Kommentare

Profilbild von Brett Adcock

Brett Adcockvor 1 Jahr

This use case is very challenging!

Profilbild von Lieutenant Generalist🇺🇸

Lieutenant Generalist🇺🇸vor 1 Jahr

Crazy how fast they're advancing!

Profilbild von vikramvi

vikramvivor 1 Jahr

would love to see @Tesla_Optimus tasks being done in Gigafactories $TSLA

Profilbild von 🌩️ Sky Nuts and ⚡ Bolts 🦄

🌩️ Sky Nuts and ⚡ Bolts 🦄vor 1 Jahr

'trained programming' better terminology than "learned behavior"

Profilbild von Mr Yuk

Mr Yukvor 1 Jahr

So you replaced a low skilled worker at half the speed. to be replaced with a highly skilled robot fixer.

Profilbild von CV

CVvor 1 Jahr

Sieht nicht gut aus für Sie, lieber @chorherr! 😜

Profilbild von Evgeny Muryshkin

Evgeny Muryshkinvor 1 Jahr

Having a dedicated pick and place machine will increase speed 1000x fold

Ähnliche Videos

🎉 Day-0 support for in vLLM, available today in v0.23.0! Congrats to Z.ai on GLM-5.2, a flagship model built for long-horizon coding agents. ✨ 1M-token context, built to hold project-scale engineering work in a single run ✨ Tuned for long-horizon coding: large-scale implementation, automated research, and performance optimization ✨ One task can carry a full dev workflow, from requirements to a deployable product across platforms ✨ Client-side and mobile engineering, including an on-device debugging loop Try it out running it on vLLM today: 🔗

🎉 Day-0 support for in vLLM, available today in v0.23.0! Congrats to Z.ai on GLM-5.2, a flagship model built for long-horizon coding agents. ✨ 1M-token context, built to hold project-scale engineering work in a single run ✨ Tuned for long-horizon coding: large-scale implementation, automated research, and performance optimization ✨ One task can carry a full dev workflow, from requirements to a deployable product across platforms ✨ Client-side and mobile engineering, including an on-device debugging loop Try it out running it on vLLM today: 🔗

vLLM

36,413 Aufrufe • vor 3 Monaten

How well do today’s frontier models handle long-horizon, multi-step web agent tasks, such as identifying the top 25 U.S. CS PhD programs with ML/AI faculty likely accepting students and compiling the results into a structured sheet? Check out our new work on Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks Paper: Leaderboard: We introduce Odysseys, a benchmark of 200 long-horizon tasks derived from real browsing sessions and evaluated on the live Internet. We show that binary pass/fail is inadequate in this setting and propose rubric-based evaluation, which better aligns with human judgment and provides more informative signals. Across leading models, the best achieves only 44.5% success, leaving substantial headroom. We further introduce a Trajectory Efficiency metric (rubric score per step) and find efficiency remains extremely low (1.15%), highlighting a key bottleneck. Odysseys provides a realistic benchmark for measuring progress toward web agents capable of sustained, efficient, real-world operation. See a more detailed thread by Jing Yu Koh.

How well do today’s frontier models handle long-horizon, multi-step web agent tasks, such as identifying the top 25 U.S. CS PhD programs with ML/AI faculty likely accepting students and compiling the results into a structured sheet? Check out our new work on Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks Paper: Leaderboard: We introduce Odysseys, a benchmark of 200 long-horizon tasks derived from real browsing sessions and evaluated on the live Internet. We show that binary pass/fail is inadequate in this setting and propose rubric-based evaluation, which better aligns with human judgment and provides more informative signals. Across leading models, the best achieves only 44.5% success, leaving substantial headroom. We further introduce a Trajectory Efficiency metric (rubric score per step) and find efficiency remains extremely low (1.15%), highlighting a key bottleneck. Odysseys provides a realistic benchmark for measuring progress toward web agents capable of sustained, efficient, real-world operation. See a more detailed thread by Jing Yu Koh.

Russ Salakhutdinov

22,518 Aufrufe • vor 5 Monaten

🤖 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: 🔗

🤖 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

67,027 Aufrufe • vor 1 Jahr

How precise can a robot get… without ever seeing the object move? Turns out, just a geometric model is enough. A robot hit 73 precise 3D goals in a row, using only a geometric model. No demonstrations. No imitation learning. No fancy vision models. The secret? Sample where the robot could make contact. Let local contact-implicit control take over from there. That’s it. ✅ Real-time performance ✅ Natural contact making and breaking ✅ Works on tricky tasks like pushing and rotating This approach mixes global planning with local MPC. Fast. Accurate. Sample-efficient. Thanks for sharing, Michael Posa ! 📍Watch it in action: Paper:

How precise can a robot get… without ever seeing the object move? Turns out, just a geometric model is enough. A robot hit 73 precise 3D goals in a row, using only a geometric model. No demonstrations. No imitation learning. No fancy vision models. The secret? Sample where the robot could make contact. Let local contact-implicit control take over from there. That’s it. ✅ Real-time performance ✅ Natural contact making and breaking ✅ Works on tricky tasks like pushing and rotating This approach mixes global planning with local MPC. Fast. Accurate. Sample-efficient. Thanks for sharing, Michael Posa ! 📍Watch it in action: Paper:

Ilir Aliu

19,012 Aufrufe • vor 1 Jahr

Journey’s “Only the Young” plays as Louden Swain runs across multiple bridges spanning the Spokane River during the opening credits of VISION QUEST. Director Harold Becker used these bridges as a metaphor for his coming-of-age story where crossing a body of water symbolizes transition, rebirth, and leaving the past behind. If you’d like to support the Full Metal Jacket Diary project, you can bid on one of my original (and signed) VQ soundtrack cassettes here:

Journey’s “Only the Young” plays as Louden Swain runs across multiple bridges spanning the Spokane River during the opening credits of VISION QUEST. Director Harold Becker used these bridges as a metaphor for his coming-of-age story where crossing a body of water symbolizes transition, rebirth, and leaving the past behind. If you’d like to support the Full Metal Jacket Diary project, you can bid on one of my original (and signed) VQ soundtrack cassettes here:

Matthew Modine

226,596 Aufrufe • vor 3 Monaten

We are very proud to announce that we have become the first university on the island of Ireland - and only the second in the UK - to achieve the prestigious #AthenaSwan Gold Award. The @Athena_SWAN award recognises our commitment to advancing #GenderEquality across higher education and beyond. “To have come from a men-only university at the outset, through to the pioneering Riddel sisters who established a hall of residence for women students through to the long list of high achievers in medicine, the arts, engineering and across a full range of disciplines, today feels like the culmination of a long and worthy journey. "But it is not the end. The Gold award is a fantastic achievement for the University and will spur us on to continue this important work.” (Professor Karen McCloskey, Director of Queen’s Gender Initiative and Deputy Director of @QubPGJCCR) Learn more here: #LoveQUB Professor Sir Ian Greer Queen's Staff QUB Equality, Diversity and Inclusion

We are very proud to announce that we have become the first university on the island of Ireland - and only the second in the UK - to achieve the prestigious #AthenaSwan Gold Award. The @Athena_SWAN award recognises our commitment to advancing #GenderEquality across higher education and beyond. “To have come from a men-only university at the outset, through to the pioneering Riddel sisters who established a hall of residence for women students through to the long list of high achievers in medicine, the arts, engineering and across a full range of disciplines, today feels like the culmination of a long and worthy journey. "But it is not the end. The Gold award is a fantastic achievement for the University and will spur us on to continue this important work.” (Professor Karen McCloskey, Director of Queen’s Gender Initiative and Deputy Director of @QubPGJCCR) Learn more here: #LoveQUB Professor Sir Ian Greer Queen's Staff QUB Equality, Diversity and Inclusion

Queen's University Belfast 🎓

26,700 Aufrufe • vor 2 Jahren

Introducing EdgeBench, a benchmark designed to study how agents learn from environments over at least 12~72-hour runs. We find that performance follows a log-sigmoid function of environment interaction time with high precision. EdgeBench is built with three ingredients: - 🌍 Real & Diverse: 134 real-world tasks across 6 task categories, spanning scientific problems, professional knowledge work, software engineering, optimization, formal math, and games. - ⏳ Ultra-Long-Horizon: Each task supports 12–72 hours of agent work. Recorded human effort averages 57.2 hours. - 🔁 Informative Feedback: Agents receive real-world feedback for continuous improvement. After 38,000 hours of agent runs on EdgeBench, a scaling law for learning from environments emerges: - 📈 As agents interact with task environments over time, their aggregate performance is precisely fit by a log-sigmoid function. - 🧠 This phenomenon can be explained by an elegant theory of graph exploration. We are releasing an initial 51 of the 134 tasks, together with the full evaluation framework, to help advance long-horizon agent research. Check our blog & paper for more findings! Blog Paper GitHub Dataset Details below 👇🧵

Introducing EdgeBench, a benchmark designed to study how agents learn from environments over at least 12~72-hour runs. We find that performance follows a log-sigmoid function of environment interaction time with high precision. EdgeBench is built with three ingredients: - 🌍 Real & Diverse: 134 real-world tasks across 6 task categories, spanning scientific problems, professional knowledge work, software engineering, optimization, formal math, and games. - ⏳ Ultra-Long-Horizon: Each task supports 12–72 hours of agent work. Recorded human effort averages 57.2 hours. - 🔁 Informative Feedback: Agents receive real-world feedback for continuous improvement. After 38,000 hours of agent runs on EdgeBench, a scaling law for learning from environments emerges: - 📈 As agents interact with task environments over time, their aggregate performance is precisely fit by a log-sigmoid function. - 🧠 This phenomenon can be explained by an elegant theory of graph exploration. We are releasing an initial 51 of the 134 tasks, together with the full evaluation framework, to help advance long-horizon agent research. Check our blog & paper for more findings! Blog Paper GitHub Dataset Details below 👇🧵

Deyao Zhu

363,887 Aufrufe • vor 3 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."

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

624,973 Aufrufe • vor 8 Monaten

We've raised $100m at a $1.15b valuation from Accel, GV, and existing investors to accelerate deployment of the most capable and accurate accounting agents across CAS, tax, audit, and advisory. Basis is used by 30% of the Top 25 accounting firms and dozens more across the Top 150. Today we're announcing the first accounting agent to complete a business tax workbook end-to-end. Our focus on production-grade, long-horizon agents means that 12 months from now, the work Basis handles will make even this look routine. We're looking for a few very intense people who want to build at the frontier.

We've raised $100m at a $1.15b valuation from Accel, GV, and existing investors to accelerate deployment of the most capable and accurate accounting agents across CAS, tax, audit, and advisory. Basis is used by 30% of the Top 25 accounting firms and dozens more across the Top 150. Today we're announcing the first accounting agent to complete a business tax workbook end-to-end. Our focus on production-grade, long-horizon agents means that 12 months from now, the work Basis handles will make even this look routine. We're looking for a few very intense people who want to build at the frontier.

Basis

382,904 Aufrufe • vor 7 Monaten

Open-source magnetic tactile sensor for $5! 🧲 Researchers introduced a magnetic tactile sensor that's low-cost, and easy to fabricate, democratizing tactile sensing for robotics. Operating in unstructured environments like homes and offices requires robots to sense forces during physical interaction. Yet the lack of a versatile, accessible tactile sensor has led to fragmented solutions and often force-unaware, sensorless approaches. Building an eFlesh sensor requires four components: a hobbyist 3D printer, off-the-shelf magnets (less than $5), a CAD model, and a magnetometer circuit board. The sensor is 3D printed with magnets embedded in the middle layer. Based on chosen mechanical properties, magnets displace in response to contact forces, measured by a magnetometer underneath. An open-source design tool converts simple OBJ/STL files into 3D-printable STLs. This enables application-specific sensors for robot hands, grippers, quadruped feet, and more. Slip detection generalizes to unseen objects with 95% accuracy. Visual-tactile control policies improve manipulation by 40% over vision-only baselines, achieving 90% success on precise tasks like plug insertion and credit card swiping. All design files, code, trained models, and conversion tools are openly available. Project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Open-source magnetic tactile sensor for $5! 🧲 Researchers introduced a magnetic tactile sensor that's low-cost, and easy to fabricate, democratizing tactile sensing for robotics. Operating in unstructured environments like homes and offices requires robots to sense forces during physical interaction. Yet the lack of a versatile, accessible tactile sensor has led to fragmented solutions and often force-unaware, sensorless approaches. Building an eFlesh sensor requires four components: a hobbyist 3D printer, off-the-shelf magnets (less than $5), a CAD model, and a magnetometer circuit board. The sensor is 3D printed with magnets embedded in the middle layer. Based on chosen mechanical properties, magnets displace in response to contact forces, measured by a magnetometer underneath. An open-source design tool converts simple OBJ/STL files into 3D-printable STLs. This enables application-specific sensors for robot hands, grippers, quadruped feet, and more. Slip detection generalizes to unseen objects with 95% accuracy. Visual-tactile control policies improve manipulation by 40% over vision-only baselines, achieving 90% success on precise tasks like plug insertion and credit card swiping. All design files, code, trained models, and conversion tools are openly available. Project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

290,094 Aufrufe • vor 5 Monaten

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,263 Aufrufe • vor 11 Monaten

We're only year 3 of a decade (if not multi-decades) long transformation of work. 3 years ago we bet on building an horizontal platform for work with agents, a chance to invent a new operating system for companies, from scratch, with AI as a fundamental premise. Many people considered us crazy for going after that, praising verticalized AI products as the winning strategy. But here's the thing: the time horizon of tasks successfully handled by agents has been predictively increasing form minutes to hours and will in all likelihood reach the equivalent of days and weeks of human work equivalent in the coming quarters. This is were verticalized and/or single-player AI falls short. Single-player tools, one person, one agent, confined to your machine is the wrong architecture for what's coming. We're shifting from using AI to produce things, to managing fleets of agents that do the producing. 3 years ago I wrote[1]: "ChatGPT is the Pong of LLMs. [...] Imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs. Let alone multiplayer modes." Weeks long tasks in companies are inherently collaborative and mechanically spanning multiple teams. The new bottleneck in harnessing agents within organizations is coordination: multiple humans and multiple agents need to work together, with shared context, shared tools, shared goals. Agents that can hand work off to other agents or surface decisions to the right person at the right time. Humans who can review, steer, and step in without losing the thread. Teams that can run parallel workstreams and actually stay aligned. This is Multiplayer AI, and that's what we've been building at Dust. Across Datadog, Clay, Persona, 1Password, Doctolib and 3,000+ organizations globally, we've watched teams figure out what this looks like in practice. 300,000+ agents deployed. 70% weekly active. 240%+ NRR. Today we're announcing a $40M Series B with Abstract, Sequoia, Snowflake, and Datadog to accelerate our vision. Designing the right interfaces for multiplayer AI is the next frontier. Join us to redefine work by defining multiplayer AI.

We're only year 3 of a decade (if not multi-decades) long transformation of work. 3 years ago we bet on building an horizontal platform for work with agents, a chance to invent a new operating system for companies, from scratch, with AI as a fundamental premise. Many people considered us crazy for going after that, praising verticalized AI products as the winning strategy. But here's the thing: the time horizon of tasks successfully handled by agents has been predictively increasing form minutes to hours and will in all likelihood reach the equivalent of days and weeks of human work equivalent in the coming quarters. This is were verticalized and/or single-player AI falls short. Single-player tools, one person, one agent, confined to your machine is the wrong architecture for what's coming. We're shifting from using AI to produce things, to managing fleets of agents that do the producing. 3 years ago I wrote[1]: "ChatGPT is the Pong of LLMs. [...] Imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs. Let alone multiplayer modes." Weeks long tasks in companies are inherently collaborative and mechanically spanning multiple teams. The new bottleneck in harnessing agents within organizations is coordination: multiple humans and multiple agents need to work together, with shared context, shared tools, shared goals. Agents that can hand work off to other agents or surface decisions to the right person at the right time. Humans who can review, steer, and step in without losing the thread. Teams that can run parallel workstreams and actually stay aligned. This is Multiplayer AI, and that's what we've been building at Dust. Across Datadog, Clay, Persona, 1Password, Doctolib and 3,000+ organizations globally, we've watched teams figure out what this looks like in practice. 300,000+ agents deployed. 70% weekly active. 240%+ NRR. Today we're announcing a $40M Series B with Abstract, Sequoia, Snowflake, and Datadog to accelerate our vision. Designing the right interfaces for multiplayer AI is the next frontier. Join us to redefine work by defining multiplayer AI.

Stanislas Polu

3,206,609 Aufrufe • vor 4 Monaten

A robot performing a chemistry experiment might not sound that surprising. What’s interesting about this demo is how the robot was trained. Chinese embodied AI startup X Square Robot's TwinDEX uses a wearable three-finger end-effector to collect demonstrations from a human, rather than requiring the robot to be teleoperated during data collection. The resulting policy handles a 20+ step chemistry workflow: opening reagent bottles, scooping material, operating a pipette, transferring liquids, handling a glass rod, pouring, and coordinating both hands throughout the process. These are very different from simple pick-and-place tasks. There are continuous contacts, tool use, changing grasps, precise positioning, force control, and long-horizon state transitions. The reported experiments used robot-free demonstrations only, with zero on-robot teleoperation data for training. The bigger idea here is that if the data-collection hardware and deployment hardware are designed to be sufficiently consistent, robot-free demonstrations can still retain the information needed for real dexterous manipulation.

A robot performing a chemistry experiment might not sound that surprising. What’s interesting about this demo is how the robot was trained. Chinese embodied AI startup X Square Robot's TwinDEX uses a wearable three-finger end-effector to collect demonstrations from a human, rather than requiring the robot to be teleoperated during data collection. The resulting policy handles a 20+ step chemistry workflow: opening reagent bottles, scooping material, operating a pipette, transferring liquids, handling a glass rod, pouring, and coordinating both hands throughout the process. These are very different from simple pick-and-place tasks. There are continuous contacts, tool use, changing grasps, precise positioning, force control, and long-horizon state transitions. The reported experiments used robot-free demonstrations only, with zero on-robot teleoperation data for training. The bigger idea here is that if the data-collection hardware and deployment hardware are designed to be sufficiently consistent, robot-free demonstrations can still retain the information needed for real dexterous manipulation.

Sharon Riley

18,036 Aufrufe • vor 1 Monat

Opening The Dam Gates! For the first time in three decades, engineers lifted the gates of a massive dam, unleashing a controlled release of water that had been held back since the mid-1990s. This was not a routine operation. Large dams are kept sealed for years to manage pressure, structural integrity, sediment buildup, and downstream safety. Opening one after this long requires precise engineering calculations to prevent erosion, flooding, or structural damage. As the gates rose, millions of gallons of water surged through the spillway, instantly transforming a dry downstream channel into a powerful river. The force, sound, and volume reveal the sheer scale of infrastructure quietly holding back nature every single day. Operations like this are used to relieve pressure on aging structures, restore natural sediment flow, and rebalance river ecosystems

Opening The Dam Gates! For the first time in three decades, engineers lifted the gates of a massive dam, unleashing a controlled release of water that had been held back since the mid-1990s. This was not a routine operation. Large dams are kept sealed for years to manage pressure, structural integrity, sediment buildup, and downstream safety. Opening one after this long requires precise engineering calculations to prevent erosion, flooding, or structural damage. As the gates rose, millions of gallons of water surged through the spillway, instantly transforming a dry downstream channel into a powerful river. The force, sound, and volume reveal the sheer scale of infrastructure quietly holding back nature every single day. Operations like this are used to relieve pressure on aging structures, restore natural sediment flow, and rebalance river ecosystems

Brian Roemmele

453,377 Aufrufe • vor 9 Monaten

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,513 Aufrufe • vor 2 Monaten

Today I used my Vision Pro for my morning fitness routine and saw the future of home workouts. Before the Dual Knit Band, I never really considered this an option. But since Apple Vision Pro has become so much more comfortable, I decided to give it a try and test out FunFitLand. The app gives you a personal fitness trainer, a variety of beautiful environments, and tons of interactive workouts, from calm meditation sessions to intense HIIT routines. I wanted to see if it really adds that much value compared to just following a YouTube workout – and yes, it absolutely does. It’s so much more fun and feels like playing a game, while still being super effective. It didn’t take long before I started breaking a sweat. While I don’t see myself doing longer or extremely intense workouts with it, it definitely got me excited for the future of AR. Because one day, we’ll have these kinds of experiences on lightweight glasses — and when that day comes, I’ll be using them all the time.

Today I used my Vision Pro for my morning fitness routine and saw the future of home workouts. Before the Dual Knit Band, I never really considered this an option. But since Apple Vision Pro has become so much more comfortable, I decided to give it a try and test out FunFitLand. The app gives you a personal fitness trainer, a variety of beautiful environments, and tons of interactive workouts, from calm meditation sessions to intense HIIT routines. I wanted to see if it really adds that much value compared to just following a YouTube workout – and yes, it absolutely does. It’s so much more fun and feels like playing a game, while still being super effective. It didn’t take long before I started breaking a sweat. While I don’t see myself doing longer or extremely intense workouts with it, it definitely got me excited for the future of AR. Because one day, we’ll have these kinds of experiences on lightweight glasses — and when that day comes, I’ll be using them all the time.

Phil Traut ᯅ

48,766 Aufrufe • vor 11 Monaten

IVERMECTIN: FULL DOSAGE SCHEDULE FOR CANCER & PREVENTION 1000s of people use Dr. William Makis MD’s IVERMECTIN dosing chart. Here’s a clear, categorized breakdown based on body weight (mg/kg per day). LOW DOSE: ≤ 0.5 mg/kg/day **Best for:** - Cancers in remission - Strong family history or genetic predisposition - Prophylaxis (preventive) **Side effects:** No long-term side effects reported. **Example:** Dr. Tess Lawrie reported a Stage 3 ovarian cancer case treated with chemo + 12 mg ivermectin daily. Tumor marker CA125 dropped from 288 to 22 after 2 months and the tumor vanished. MEDIUM DOSE: 1.0 mg/kg/day **Best for:** Starting dose for **most cancers** (lung, pancreatic, renal cell, gastric, etc.). **Side effects:** No long-term side effects reported. **Example:** Dr. Shankara Chetty’s 70-year-old prostate cancer patient (PSA 89) took 45 mg/day (plus lactoferrin). After two months PSA fell to 10.9. HIGH DOSE: 2.0 mg/kg/day **Best for:** Very aggressive cancers (leukemia, pancreatic, brain cancers). **Side effects:** No long-term side effects reported. **Example:** Dr. Allan Landrito’s Stage 4 gallbladder cancer patient took 2 mg/kg daily for 14 months — cancer disappeared. VERY HIGH DOSE: ≥ 2.5 mg/kg/day **Best for:** Extensive metastatic disease, extremely poor prognosis, or certain brain cancers. **Side effects:** Possible short-term & transient visual effects (usually resolve in a few days). **Example:** Dr. Shankara Chetty treated a patient with 2.5 mg/kg/day — no side effects reported. **Quick conversion example (for a 60 kg / 132 lb person):** - Low: ≤30 mg/day - Medium: 60 mg/day (≈5×12 mg tablets or 1 teaspoon liquid) - High: 120 mg/day - Very High: ≥150 mg/day Many anecdotal reports exist of long-term daily use (months to over a year) with no serious toxicity, but individual responses vary. Always work with a knowledgeable clinician, especially if you have pre-existing conditions (e.g., vision issues or glaucoma). This is for educational purposes only. Share to spread awareness — information. Follow for more .

IVERMECTIN: FULL DOSAGE SCHEDULE FOR CANCER & PREVENTION 1000s of people use Dr. William Makis MD’s IVERMECTIN dosing chart. Here’s a clear, categorized breakdown based on body weight (mg/kg per day). LOW DOSE: ≤ 0.5 mg/kg/day Best for: - Cancers in remission - Strong family history or genetic predisposition - Prophylaxis (preventive) Side effects: No long-term side effects reported. Example: Dr. Tess Lawrie reported a Stage 3 ovarian cancer case treated with chemo + 12 mg ivermectin daily. Tumor marker CA125 dropped from 288 to 22 after 2 months and the tumor vanished. MEDIUM DOSE: 1.0 mg/kg/day Best for: Starting dose for most cancers (lung, pancreatic, renal cell, gastric, etc.). Side effects: No long-term side effects reported. Example: Dr. Shankara Chetty’s 70-year-old prostate cancer patient (PSA 89) took 45 mg/day (plus lactoferrin). After two months PSA fell to 10.9. HIGH DOSE: 2.0 mg/kg/day Best for: Very aggressive cancers (leukemia, pancreatic, brain cancers). Side effects: No long-term side effects reported. Example: Dr. Allan Landrito’s Stage 4 gallbladder cancer patient took 2 mg/kg daily for 14 months — cancer disappeared. VERY HIGH DOSE: ≥ 2.5 mg/kg/day Best for: Extensive metastatic disease, extremely poor prognosis, or certain brain cancers. Side effects: Possible short-term & transient visual effects (usually resolve in a few days). Example: Dr. Shankara Chetty treated a patient with 2.5 mg/kg/day — no side effects reported. Quick conversion example (for a 60 kg / 132 lb person): - Low: ≤30 mg/day - Medium: 60 mg/day (≈5×12 mg tablets or 1 teaspoon liquid) - High: 120 mg/day - Very High: ≥150 mg/day Many anecdotal reports exist of long-term daily use (months to over a year) with no serious toxicity, but individual responses vary. Always work with a knowledgeable clinician, especially if you have pre-existing conditions (e.g., vision issues or glaucoma). This is for educational purposes only. Share to spread awareness — information. Follow for more .

mcgill_medicines

106,634 Aufrufe • vor 2 Monaten