Загрузка видео...

Не удалось загрузить видео

На главную

This work is not about a new technique. GMT (General Motion Tracking) shows good engineering practices that you can actually train a single unified whole-body control policy for all agile motion, and it works in the real world, directly with sim2real without adaptation. This is different from many existing...

xiaolonw's profile picture

Xiaolong Wang

21,678 subscribers

83,261 просмотров • 1 год назад •via X (Twitter)

Здоровье и велнесНаука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Scott with DigitalStacker.com
Scott with DigitalStacker.com1 год назад

Strong tech!

Фото профиля Aaron Siegel
Aaron Siegel1 год назад

I’m begging you to watch one single movie about this. they’ve made so many!

Фото профиля Felix
Felix1 год назад

How do you train in love, empathy, appreciation for beauty, mercy, and respect?

Фото профиля Valintina
Valintina1 год назад

Mm K

Фото профиля Alchemy & Indians
Alchemy & Indians1 год назад

Can it drive a golf ball like Kai Trump?

Фото профиля Stephen C Pearse
Stephen C Pearse1 год назад

Can robot watch tv exercise (tai chi, yoga, whatever videos yet?

Фото профиля Nancy digregorio
Nancy digregorio1 год назад

This is going to be the police force one day. All the arguments and disgusting behavior will end very poorly.

Фото профиля Travis McTravesty
Travis McTravesty1 год назад

Don't teach them Kung Fu!!

Фото профиля Petronius Arbiter
Petronius Arbiter1 год назад

To what extent? What’s the end game for this?

Фото профиля CopperGhost Guitars
CopperGhost Guitars1 год назад

That looks pretty retarded and terrible compared to some others. 📡

Похожие видео

Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot policies. Two key pieces make it work: •Motion tracking pipeline: robustly turns human mocap into dynamic robot motions (jump spins, sprinting, cartwheels) on real hardware •Guided diffusion policy: distills motion primitives and enables zero-shot downstream tasks with simple cost functions The result: ✅ State-of-the-art motion quality from mocap tracking ✅ Versatile task execution; waypoint navigation, joystick teleop, obstacle avoidance ✅ Stable sim-to-real transfer for diverse humanoid skills Thank you for sharing, Qiayuan Liao! 📍 Paper: Video:
0:42

Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot policies. Two key pieces make it work: •Motion tracking pipeline: robustly turns human mocap into dynamic robot motions (jump spins, sprinting, cartwheels) on real hardware •Guided diffusion policy: distills motion primitives and enables zero-shot downstream tasks with simple cost functions The result: ✅ State-of-the-art motion quality from mocap tracking ✅ Versatile task execution; waypoint navigation, joystick teleop, obstacle avoidance ✅ Stable sim-to-real transfer for diverse humanoid skills Thank you for sharing, Qiayuan Liao! 📍 Paper: Video:

Ilir Aliu - eu/acc

72,522 просмотров • 1 год назад

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

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

Zhengyi “Zen” Luo

62,399 просмотров • 9 месяцев назад

Physics-based Motion Retargeting from Sparse Inputs paper page: Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user's pose. Another challenge is that an avatar might have a different skeleton structure than a human and the mapping between them is unclear. In this work we address both of these challenges. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. Our method uses reinforcement learning to train a policy to control characters in a physics simulator. We only require human motion capture data for training, without relying on artist-generated animations for each avatar. This allows us to use large motion capture datasets to train general policies that can track unseen users from real and sparse data in real-time. We demonstrate the feasibility of our approach on three characters with different skeleton structure: a dinosaur, a mouse-like creature and a human. We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available. We discuss and ablate the important components in our framework, specifically the kinematic retargeting step, the imitation, contact and action reward as well as our asymmetric actor-critic observations. We further explore the robustness of our method in a variety of settings including unbalancing, dancing and sports motions.
7:12

Physics-based Motion Retargeting from Sparse Inputs paper page: Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user's pose. Another challenge is that an avatar might have a different skeleton structure than a human and the mapping between them is unclear. In this work we address both of these challenges. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. Our method uses reinforcement learning to train a policy to control characters in a physics simulator. We only require human motion capture data for training, without relying on artist-generated animations for each avatar. This allows us to use large motion capture datasets to train general policies that can track unseen users from real and sparse data in real-time. We demonstrate the feasibility of our approach on three characters with different skeleton structure: a dinosaur, a mouse-like creature and a human. We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available. We discuss and ablate the important components in our framework, specifically the kinematic retargeting step, the imitation, contact and action reward as well as our asymmetric actor-critic observations. We further explore the robustness of our method in a variety of settings including unbalancing, dancing and sports motions.

AK

106,527 просмотров • 3 лет назад

We asked Angus about the future of robotics and AI training. “I built an industrial-grade kinematic solver for 6 degrees of freedom motion, with full path planning and joint control." "You can stream AI model outputs into it, or run it like a traditional industrial robot." "The benefit of that is all of that information you can stream and record from those joints… you can use that as the training data." "Frankly, moving a robot with a lever is really crap data for training robots. But this gives you smooth, high-quality motion, without needing two robots.”
2:16

We asked Angus about the future of robotics and AI training. “I built an industrial-grade kinematic solver for 6 degrees of freedom motion, with full path planning and joint control." "You can stream AI model outputs into it, or run it like a traditional industrial robot." "The benefit of that is all of that information you can stream and record from those joints… you can use that as the training data." "Frankly, moving a robot with a lever is really crap data for training robots. But this gives you smooth, high-quality motion, without needing two robots.”

TBPN

18,811 просмотров • 1 год назад

A planetary roller screw looks simple, but it’s one of the key enablers for humanoid robots. It converts rotational motion into precise linear motion with high efficiency, high load capacity, and extremely smooth control. In humanoid robots, this is exactly what you need for: joint actuation linear actuators in arms/legs high-force, high-precision movement under continuous cycles Compared to ball screws, it offers better durability and load distribution—critical for robots that must operate 24/7 in the real world. Small component, huge impact. This is the kind of “hidden hardware” that makes humanoid robotics actually work.
0:57

A planetary roller screw looks simple, but it’s one of the key enablers for humanoid robots. It converts rotational motion into precise linear motion with high efficiency, high load capacity, and extremely smooth control. In humanoid robots, this is exactly what you need for: joint actuation linear actuators in arms/legs high-force, high-precision movement under continuous cycles Compared to ball screws, it offers better durability and load distribution—critical for robots that must operate 24/7 in the real world. Small component, huge impact. This is the kind of “hidden hardware” that makes humanoid robotics actually work.

Steven Cheng

69,970 просмотров • 1 месяц назад

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:26

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

59,835 просмотров • 8 месяцев назад

We RL'ed humanoid robots to Cristiano Ronaldo, LeBron James, and Kobe Byrant! These are neural nets running on real hardware at our GEAR lab. Most robot demos you see online speed videos up. We actually *slow them down* so you can enjoy the fluid motions. I'm excited to announce "ASAP", a "real2sim2real" model that masters extremely smooth and dynamic motions for humanoid whole body control. We pretrain the robot in simulation first, but there is a notorious "sim2real" gap: it's very difficult for hand-engineered physics equations to match real world dynamics. Our fix is simple: just deploy a pretrained policy on real hardware, collect data, and replay the motion in sim. The replay will obviously have many errors, but that gives a rich signal to compensate for the physics discrepancy. Use another neural net to learn the delta. Basically, we "patch up" a traditional physics engine, so that the robot can experience almost the real world at scale in GPUs. The future is hybrid simulation: combine the power of classical sim engines refined over decades and the uncanny ability of modern NNs to capture a messy world.
0:50

We RL'ed humanoid robots to Cristiano Ronaldo, LeBron James, and Kobe Byrant! These are neural nets running on real hardware at our GEAR lab. Most robot demos you see online speed videos up. We actually *slow them down* so you can enjoy the fluid motions. I'm excited to announce "ASAP", a "real2sim2real" model that masters extremely smooth and dynamic motions for humanoid whole body control. We pretrain the robot in simulation first, but there is a notorious "sim2real" gap: it's very difficult for hand-engineered physics equations to match real world dynamics. Our fix is simple: just deploy a pretrained policy on real hardware, collect data, and replay the motion in sim. The replay will obviously have many errors, but that gives a rich signal to compensate for the physics discrepancy. Use another neural net to learn the delta. Basically, we "patch up" a traditional physics engine, so that the robot can experience almost the real world at scale in GPUs. The future is hybrid simulation: combine the power of classical sim engines refined over decades and the uncanny ability of modern NNs to capture a messy world.

Jim Fan

566,544 просмотров • 1 год назад

This policy is not sustainable. You can't provide free everything for everybody. I understand why he's putting this out there. It's the mantra for his campaign. The whole idea of a mayoral election is you say anything you can to get elected and then you explain why you can't deliver after you're the mayor. That's how it works in New York and that's how they all did it. They're all guilty of that.
1:05

This policy is not sustainable. You can't provide free everything for everybody. I understand why he's putting this out there. It's the mantra for his campaign. The whole idea of a mayoral election is you say anything you can to get elected and then you explain why you can't deliver after you're the mayor. That's how it works in New York and that's how they all did it. They're all guilty of that.

Kevin O'Leary aka Mr. Wonderful

39,952 просмотров • 10 месяцев назад

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!
53:45

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,334 просмотров • 2 месяцев назад

not sure why nobody is talking about this but kling 2.6 motion control can actually create near perfect ai ugc Real Video (left) vs AI Video (right) you can pretty much create any video if you're willing to hire someone to just act things out, move around and say things you just need a decent base video of someone performing the actions, a starting image of your desired character and clear prompts for what you want changed this video is literally indistinguishable from real footage it even changed facial features, body composition, clothing and everything without me explicitly telling it to the amount of use cases for this are insane if you think about it this is just a sneak peak of the type of tools we will have access to in 2026
0:29

not sure why nobody is talking about this but kling 2.6 motion control can actually create near perfect ai ugc Real Video (left) vs AI Video (right) you can pretty much create any video if you're willing to hire someone to just act things out, move around and say things you just need a decent base video of someone performing the actions, a starting image of your desired character and clear prompts for what you want changed this video is literally indistinguishable from real footage it even changed facial features, body composition, clothing and everything without me explicitly telling it to the amount of use cases for this are insane if you think about it this is just a sneak peak of the type of tools we will have access to in 2026

Miko

110,731 просмотров • 8 месяцев назад

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.
0:21

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,612 просмотров • 2 лет назад

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:
0:47

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,872 просмотров • 9 месяцев назад

A robot that works with 1 to 6 legs? This reconfigurable robot adapts like a spider, switching between different movement styles on the fly. SnapBot isn’t just a legged robot: it’s a shape-shifting machine. With up to 700 configurations, it can walk, crawl, or row its way through any terrain. Why this is exciting: ✅ Changes its setup from one to six legs for different tasks ✅ Moves in multiple ways, including walking, rowing, and crawling ✅ Adapts to its environment like nature’s best climbers and crawlers ✅ A step toward robots that adjust to real-world challenges instantly Nature-inspired robotics is unlocking new ways to move. SnapBot proves that flexibility is key to the future of locomotion.
0:25

A robot that works with 1 to 6 legs? This reconfigurable robot adapts like a spider, switching between different movement styles on the fly. SnapBot isn’t just a legged robot: it’s a shape-shifting machine. With up to 700 configurations, it can walk, crawl, or row its way through any terrain. Why this is exciting: ✅ Changes its setup from one to six legs for different tasks ✅ Moves in multiple ways, including walking, rowing, and crawling ✅ Adapts to its environment like nature’s best climbers and crawlers ✅ A step toward robots that adjust to real-world challenges instantly Nature-inspired robotics is unlocking new ways to move. SnapBot proves that flexibility is key to the future of locomotion.

Ilir Aliu

78,027 просмотров • 1 год назад

NVIDIA MotionBricks brings humanoid robots closer to natural, fluid movement The system combines a modular latent generative model with Smart Primitives, packing more than 350,000 motion skills into a single backbone. It runs in real time at up to 15,000 FPS with just 2ms latency. Navigation, object interaction, sitting, jumping, obstacle crossing, and even different movement styles can be composed zero-shot, like reusable motion modules. It is already being used for whole-body control on the Unitree G1 and serves as the motion layer for NVIDIA GR00T Whole-Body Control. What makes this interesting is the move from training individual behaviors toward building a shared library of motion capabilities. If that approach scales, robot movement could become more modular, transferable, and easier to deploy across different tasks and environments.
1:43

NVIDIA MotionBricks brings humanoid robots closer to natural, fluid movement The system combines a modular latent generative model with Smart Primitives, packing more than 350,000 motion skills into a single backbone. It runs in real time at up to 15,000 FPS with just 2ms latency. Navigation, object interaction, sitting, jumping, obstacle crossing, and even different movement styles can be composed zero-shot, like reusable motion modules. It is already being used for whole-body control on the Unitree G1 and serves as the motion layer for NVIDIA GR00T Whole-Body Control. What makes this interesting is the move from training individual behaviors toward building a shared library of motion capabilities. If that approach scales, robot movement could become more modular, transferable, and easier to deploy across different tasks and environments.

CyberRobo

11,089 просмотров • 2 месяцев назад

🇹🇷 Turkish #energy minister Alparslan Bayraktar: ✅ We want to turn #TPAO into a million-barrel level company. ✅ Our presence in 🇸🇴 #Somalia is part of this endeavor. ✅ Seismic data is suggestive and shows us that there's "something" [beneath the ocean floor]. ✅ We don't definitively know what it is at this time, our prediction is that it is oil. ✅ We won't know for certain whether it is commercially viable or not until after the #drilling work to be carried out by #CagriBey.
0:34

🇹🇷 Turkish #energy minister Alparslan Bayraktar: ✅ We want to turn #TPAO into a million-barrel level company. ✅ Our presence in 🇸🇴 #Somalia is part of this endeavor. ✅ Seismic data is suggestive and shows us that there's "something" [beneath the ocean floor]. ✅ We don't definitively know what it is at this time, our prediction is that it is oil. ✅ We won't know for certain whether it is commercially viable or not until after the #drilling work to be carried out by #CagriBey.

Turkish Century

11,967 просмотров • 4 месяцев назад

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓
0:41

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Charly Wargnier

59,144 просмотров • 7 месяцев назад

15–30 minutes of real-world robot data. That's now enough to go from sim-to-real failure to working robot. Let’s see… You train a robot in simulation. You deploy it in the real world. It fails. The physics don't match. So you try to fine-tune it with real data, but… you never have enough real data, and the fine-tuning breaks everything the simulation taught it. SimDist fixes this with one key decision: don't transfer the policy. Transfer the world model. Keep the reward and value knowledge from simulation frozen. Only update the part that's actually wrong, how the robot predicts physics. Now the robot doesn't have to relearn the entire task in the real world. It already knows what success looks like. It just needs to correct its understanding of how the real world moves. The part that makes this work: they also trained on failures and recoveries; not just perfect demonstrations. Without that, the planner finds the gaps and exploits them. With it, the robot can tell a good future from a bad one. That's all it needs. Results on peg insertion, table leg assembly, locomotion on slippery and uneven surfaces. Tasks that require precision, force, and quick reaction. Thanks for sharing, Tyler Westenbroek ([Tyler Westenbroek]. Interactive visualization + paper: ——- Weekly robotics and AI insights. Subscribe free:
0:41

15–30 minutes of real-world robot data. That's now enough to go from sim-to-real failure to working robot. Let’s see… You train a robot in simulation. You deploy it in the real world. It fails. The physics don't match. So you try to fine-tune it with real data, but… you never have enough real data, and the fine-tuning breaks everything the simulation taught it. SimDist fixes this with one key decision: don't transfer the policy. Transfer the world model. Keep the reward and value knowledge from simulation frozen. Only update the part that's actually wrong, how the robot predicts physics. Now the robot doesn't have to relearn the entire task in the real world. It already knows what success looks like. It just needs to correct its understanding of how the real world moves. The part that makes this work: they also trained on failures and recoveries; not just perfect demonstrations. Without that, the planner finds the gaps and exploits them. With it, the robot can tell a good future from a bad one. That's all it needs. Results on peg insertion, table leg assembly, locomotion on slippery and uneven surfaces. Tasks that require precision, force, and quick reaction. Thanks for sharing, Tyler Westenbroek ([Tyler Westenbroek]. Interactive visualization + paper: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

14,222 просмотров • 3 месяцев назад