正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

It also has exceptional robustness and zero-shot environment generalization; under various disturbances, the model continues to work. Dyna-2 is our first model to achieve an 87% quality and throughput rating during zero-shot deployment at novel customer sites. .

Dyna Robotics

10,335 subscribers

19,038 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Sharing some exciting DYNA-1 result: zero-shot environment generalization We put DYNA-1 under test in a completely different environment from our training distribution – with an entirely different background (Dyna Robotics banner) and metal table. The table has a reflective and smooth surface, creating a wildly different visual appearance as well as interaction dynamics. The model is able to proceed as usual, adeptly folding and recovering from its own mistakes. By focusing on task mastery, we achieve robust generalization out of the box

Sharing some exciting DYNA-1 result: zero-shot environment generalization We put DYNA-1 under test in a completely different environment from our training distribution – with an entirely different background (Dyna Robotics banner) and metal table. The table has a reflective and smooth surface, creating a wildly different visual appearance as well as interaction dynamics. The model is able to proceed as usual, adeptly folding and recovering from its own mistakes. By focusing on task mastery, we achieve robust generalization out of the box

Jason Ma

49,008 次观看 • 1 年前

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Introducing Dynamism v1 (DYNA-1) by Dyna Robotics – the first robot foundation model built for round-the-clock, high-throughput dexterous autonomy. Here is a time-lapse video of our model autonomously folding 850+ napkins in a span of 24 hours with • 99.4% success rate — zero human intervention • 60% human throughput speed • 4.3/5 quality ratings (set by the client) A thread on our motivation, insights and results:

Jason Ma

523,118 次观看 • 1 年前

Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.

Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.

Tony Zhao

1,043,116 次观看 • 1 个月前

Raon-OpenTTS-1B is a new open text-to-speech model for zero-shot voice cloning. It has best overall similarity score and lowest error rate vs other leading TTS models.

Raon-OpenTTS-1B is a new open text-to-speech model for zero-shot voice cloning. It has best overall similarity score and lowest error rate vs other leading TTS models.

AI Search

22,657 次观看 • 25 天前

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.

The Humanoid Hub

15,837 次观看 • 1 个月前

- Lab data is sugar water, not great for true zero-shot generalization - Household data is milk; the genuine chaos, real signal Wang Hao, X Square Robotics CTO and computational physics researcher at Peking University, lays out the philosophy behind the upcoming robotics model

- Lab data is sugar water, not great for true zero-shot generalization - Household data is milk; the genuine chaos, real signal Wang Hao, X Square Robotics CTO and computational physics researcher at Peking University, lays out the philosophy behind the upcoming robotics model

The Humanoid Hub

14,644 次观看 • 4 个月前

With Gen-4.5 you can achieve an unprecedented level of cinematic realism while still achieving novel creative concepts. The model is exceptionally good at generating objects that move with realistic weight, momentum and force. Even when suspended in zero gravity. Gen-4.5 early access is now gradually rolling out and will be available soon to all plans. Learn more about the model and what's to come at the link below.

With Gen-4.5 you can achieve an unprecedented level of cinematic realism while still achieving novel creative concepts. The model is exceptionally good at generating objects that move with realistic weight, momentum and force. Even when suspended in zero gravity. Gen-4.5 early access is now gradually rolling out and will be available soon to all plans. Learn more about the model and what's to come at the link below.

Runway

37,198 次观看 • 9 个月前

Starting today you can try our new foundation research model for audio generation. The demo includes Zero shot TTS, Text to sound effects, Infilling and more! Try Audiobox ➡️

Starting today you can try our new foundation research model for audio generation. The demo includes Zero shot TTS, Text to sound effects, Infilling and more! Try Audiobox ➡️

AI at Meta

515,818 次观看 • 2 年前

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Big News! Meta just released Segment Anything, a new AI model that can "cut out" any object, in any image/video, with a single click. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.

Lior Alexander

290,330 次观看 • 3 年前

We brought Dynasaur to The Clean Show and ran it live, 8 hours a day. Each deployment fuels our robotics foundation model — scaling data, accelerating iteration, and enabling real-world generalization. Embodied intelligence won’t come from lab demos, but from deployment-first robotics running continuously in the wild.

We brought Dynasaur to The Clean Show and ran it live, 8 hours a day. Each deployment fuels our robotics foundation model — scaling data, accelerating iteration, and enabling real-world generalization. Embodied intelligence won’t come from lab demos, but from deployment-first robotics running continuously in the wild.

Dyna Robotics

24,901 次观看 • 1 年前

We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. Aristo Team at Ai2 Ai2 Website: Let's dive in 🧵 (1/n)

We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. Aristo Team at Ai2 Ai2 Website: Let's dive in 🧵 (1/n)

Bodhisattwa Majumder

35,052 次观看 • 2 年前

today we're introducing lipsync-2, the world's first zero-shot lipsyncing model that preserves a speaker's unique style w/o additional training or fine-tuning lipsync-2 is a leap forward in realism, expressiveness, control, quality, and speed across live-action, animated, and AI-generated video lipsync-2 is rolling out in GA today 🧵

today we're introducing lipsync-2, the world's first zero-shot lipsyncing model that preserves a speaker's unique style w/o additional training or fine-tuning lipsync-2 is a leap forward in realism, expressiveness, control, quality, and speed across live-action, animated, and AI-generated video lipsync-2 is rolling out in GA today 🧵

sync. labs

89,640 次观看 • 1 年前

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

LeRobot

42,389 次观看 • 2 个月前

Excited to share our #ICML2023 paper ✨LIV✨! Extending VIP, LIV is at once a pre-training, fine-tuning, and (zero-shot!) multi-modal reward method for (real-world!) language-conditioned robotic control. Project: Code & Model: 🧵:

Excited to share our #ICML2023 paper ✨LIV✨! Extending VIP, LIV is at once a pre-training, fine-tuning, and (zero-shot!) multi-modal reward method for (real-world!) language-conditioned robotic control. Project: Code & Model: 🧵:

Jason Ma

55,068 次观看 • 3 年前

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Introducing RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning. 7 real robot tasks, 900/900 successes. Up to 250 consecutive trials in one task, running 2 hours nonstop without failure. High success rate against physical disturbances, zero-shot, and few-shot adaptation Our first step toward a deployable robot learning system.

Kun Lei

91,914 次观看 • 11 个月前

We just did World’s first on-stage autonomous demo of long-horizon dexterous VLA 🚨 No training. No setup. Performance out of the box. Live demo is hard and unpredictable, but we felt great about our model’s generalization, and it went pretty well! 💯 Zero-shot. 100% success.

We just did World’s first on-stage autonomous demo of long-horizon dexterous VLA 🚨 No training. No setup. Performance out of the box. Live demo is hard and unpredictable, but we felt great about our model’s generalization, and it went pretty well! 💯 Zero-shot. 100% success.

Jason Ma

63,752 次观看 • 11 个月前

How it feels watching Trump and MAGA realize they picked the wrong group to scapegoat 😂🕺💃 We sent their whole approval rating straight into the dumpster 🚮 and now they’ve got basically zero shot at the midterms.🔥

How it feels watching Trump and MAGA realize they picked the wrong group to scapegoat 😂🕺💃 We sent their whole approval rating straight into the dumpster 🚮 and now they’ve got basically zero shot at the midterms.🔥

Fortunately Blessed 🇸🇴

19,566 次观看 • 7 个月前

early results from our latest lipsync model, lipsync-2 its zero-shot so you don’t need to train every character. It edits anyone without having to see them before — while preserving their unique style really excited for this one, extremely proud of the team

early results from our latest lipsync model, lipsync-2 its zero-shot so you don’t need to train every character. It edits anyone without having to see them before — while preserving their unique style really excited for this one, extremely proud of the team

Prady

12,704 次观看 • 1 年前

A world model controlling a drone flying outdoors at 100Hz! 🚁 - Cuts position-tracking error 26-38% and attitude error up to 54% versus predictive baselines - Trained in simulation and deployed zero-shot on hardware. - predicts future dynamics in latent space instead of forecasting raw states, dodging the compounding-error drift that wrecks autoregressive models. A physics-inspired “prober” maps frozen latents back to real position, velocity, and attitude for an onboard MPPI controller. - Why it matters: The first example of JEPA world models surviving the messiness of outdoor deployment. The whole model is ~9K parameters, small enough to run on an embedded flight computer 🧠

A world model controlling a drone flying outdoors at 100Hz! 🚁 - Cuts position-tracking error 26-38% and attitude error up to 54% versus predictive baselines - Trained in simulation and deployed zero-shot on hardware. - predicts future dynamics in latent space instead of forecasting raw states, dodging the compounding-error drift that wrecks autoregressive models. A physics-inspired “prober” maps frozen latents back to real position, velocity, and attitude for an onboard MPPI controller. - Why it matters: The first example of JEPA world models surviving the messiness of outdoor deployment. The whole model is ~9K parameters, small enough to run on an embedded flight computer 🧠

Vai Viswanathan

52,773 次观看 • 2 个月前