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.

Odyssey-3 is live. One world model trained on visual data that can drive cars, fly drones, control robots, and even play video games. The basic premise is that it's better to train a single model across different systems instead of a new model for each system. It's sort of... show more

Ian Miles

1,244,334 subscribers

24,978 Aufrufe • vor 3 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Odyssey raised $310M just three months ago. Now they’ve dropped Odyssey-3 one model that can drive cars, control robots, pilot drones, power humanoids and even play video games. This is seriously wild🔥

Odyssey raised $310M just three months ago. Now they’ve dropped Odyssey-3 one model that can drive cars, control robots, pilot drones, power humanoids and even play video games. This is seriously wild🔥

Science girl

169,182 Aufrufe • vor 3 Tagen

Odyssey raised $310M only three months ago. Now they’ve shipped Odyssey-3. One model that can control everything! cars, drones, robot arms, humanoids and even play video games. This feels like a huge step toward AI that doesn’t just understand the world, but can actually interact with it. Crazy cool.

Odyssey raised $310M only three months ago. Now they’ve shipped Odyssey-3. One model that can control everything! cars, drones, robot arms, humanoids and even play video games. This feels like a huge step toward AI that doesn’t just understand the world, but can actually interact with it. Crazy cool.

HOW THINGS WORK

77,516 Aufrufe • vor 3 Tagen

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.

Super excited about Hydra-0 from Hongyu Li and team! The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.

Yunzhu Li

10,695 Aufrufe • vor 28 Tagen

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is? Checkout "Evaluating Robot Policies in a World Model". Paper: Demo: Code:

Evaluating policies on a real robot can be painful. Can we use a world model to get a rough estimate of how good a policy is? Checkout "Evaluating Robot Policies in a World Model". Paper: Demo: Code:

Sherry Yang

37,028 Aufrufe • vor 1 Jahr

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Robotics keeps hitting the same wall. Single task RL works, but... it does not scale to hundreds of tasks or new embodiments. This new paper looks like a real step toward fixing that. The team introduces MMBench, a benchmark with 200 tasks across many domains and robots, and Newt, a language conditioned world model trained online across all 200 tasks at once. The simple idea behind Newt: The model learns from demos to get the right priors It trains across many tasks through online interaction It uses language to ground the goal It adapts fast when a new task shows up What stood out to me: ✅ One model trained on 200 tasks at the same time ✅ Language conditioned control for both states and RGB ✅ Better data efficiency than strong baselines ✅ Strong open loop control ✅ Fast adaptation to new tasks and embodiments ✅ Full release of 200 checkpoints, 4000 demos, code, and benchmark This is a good push toward general control instead of one model per task. If you want the full paper: Project page: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

70,090 Aufrufe • vor 9 Monaten

Diffusion for virtual worlds: we've trained a new model to create 3D objects from text. And it's 50x faster than any alternative. We made each of these cute characters in just one minute with Genmo's new text-to-3D model. Build your own world at

Diffusion for virtual worlds: we've trained a new model to create 3D objects from text. And it's 50x faster than any alternative. We made each of these cute characters in just one minute with Genmo's new text-to-3D model. Build your own world at

Genmo

18,532 Aufrufe • vor 3 Jahren

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.

Brian Roemmele

57,454 Aufrufe • vor 10 Monaten

Very strange behavior in Claude Code: after specifically telling Claude to use gemini-3-flash-preview, (and even explaining that it's a new model that just came out), Claude refuses to use it, getting stuck in a loop of making non-edits which keep the old version. It gets skeptical and apparently doesn't believe that the model exists (?)

Very strange behavior in Claude Code: after specifically telling Claude to use gemini-3-flash-preview, (and even explaining that it's a new model that just came out), Claude refuses to use it, getting stuck in a loop of making non-edits which keep the old version. It gets skeptical and apparently doesn't believe that the model exists (?)

Benjamin De Kraker

34,305 Aufrufe • vor 8 Monaten

Here is the second outfit of our customizable 3D vtuber model! <3 The model will launch in 5 days! -^u^- Now that most of the coding is done, we can focus on making more assets for the model like ears, tails, wings, and accessories! 🩷

Here is the second outfit of our customizable 3D vtuber model! <3 The model will launch in 5 days! -^u^- Now that most of the coding is done, we can focus on making more assets for the model like ears, tails, wings, and accessories! 🩷

Pastell & Palette🤍 3D Customizable Model!

24,793 Aufrufe • vor 10 Monaten

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

NVIDIA AI

341,322 Aufrufe • vor 3 Monaten

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

Jim Fan

594,014 Aufrufe • vor 2 Jahren

Our next-gen interactive video model is shaping up to be so exciting. Check out these early outputs. AI-imagined video that you can play like a game feels like a totally new form of media. The YouTube of interactive video must be built to enjoy it 🥰

Our next-gen interactive video model is shaping up to be so exciting. Check out these early outputs. AI-imagined video that you can play like a game feels like a totally new form of media. The YouTube of interactive video must be built to enjoy it 🥰

Oliver Cameron

33,399 Aufrufe • vor 1 Jahr

DeepSeek R1 is *the* best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

DeepSeek R1 is the best model available right now. It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.

Santiago

1,224,409 Aufrufe • vor 1 Jahr

MIMO: Advanced Video-to-Video Model by Alibaba This is insane! With this v2v model, we can take a video of ourselves and use it to animate any character we create, all while keeping the original background from the video. It's like we're putting ourselves into any other new worlds! 6 Example:

MIMO: Advanced Video-to-Video Model by Alibaba This is insane! With this v2v model, we can take a video of ourselves and use it to animate any character we create, all while keeping the original background from the video. It's like we're putting ourselves into any other new worlds! 6 Example:

el.cine

118,771 Aufrufe • vor 2 Jahren

What happens next? We took a photo with Lens and asked Nano Banana to generate the next 5 seconds of a scene. While it’s not predicting the future in a literal sense, the model draws upon its vast world knowledge to generate a plausible outcome in each of these examples. It's a fun peek at how our latest AI image editing model can be used for creative forecasting and storytelling. Nano Banana is now live in Search – accessible through Lens and AI Mode – so you can try this out for yourself!

What happens next? We took a photo with Lens and asked Nano Banana to generate the next 5 seconds of a scene. While it’s not predicting the future in a literal sense, the model draws upon its vast world knowledge to generate a plausible outcome in each of these examples. It's a fun peek at how our latest AI image editing model can be used for creative forecasting and storytelling. Nano Banana is now live in Search – accessible through Lens and AI Mode – so you can try this out for yourself!

Rajan Patel

74,826 Aufrufe • vor 11 Monaten

Seedance 2.0 is now completely free to use. It's available on GlobalGPT and it's the same model ByteDance charges premium pricing for, except now you can generate unlimited videos without paying a cent. No credits system. No watermark. No 5-second teaser clips that force you to upgrade.

Seedance 2.0 is now completely free to use. It's available on GlobalGPT and it's the same model ByteDance charges premium pricing for, except now you can generate unlimited videos without paying a cent. No credits system. No watermark. No 5-second teaser clips that force you to upgrade.

Hasan Toor

96,518 Aufrufe • vor 4 Monaten

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Introducing RL Environment Creator Skill Now any one can create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.

Adithya S K

46,948 Aufrufe • vor 4 Monaten