Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Interfaces that are generated, not coded. Solaris is our first step toward our vision of end-to-end neural software, where user interfaces are streamed directly onto your screen by a real-time video model, without any intermediate code or HTML/CSS. Today we're releasing a technical report and opening it up for... show more

Anastasis Germanidis

6,657 subscribers

217,892 views • 2 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NEURALINK: REWIRING THE FUTURE OF HUMAN PERCEPTION Neuralink begins by restoring sight. •⁠ ⁠It bypasses damaged eyes and speaks directly to the brain •⁠ ⁠Future applications may unlock vision beyond human capability •⁠ ⁠Interfaces designed to read and write neural signals in real time •⁠ ⁠Potential to restore mobility, memory, and sensory function Neural interfaces are transitioning from lab testing to human integration. A new era of brain-machine connection is underway. Source: Neuralink, Elon Musk

NEURALINK: REWIRING THE FUTURE OF HUMAN PERCEPTION Neuralink begins by restoring sight. •⁠ ⁠It bypasses damaged eyes and speaks directly to the brain •⁠ ⁠Future applications may unlock vision beyond human capability •⁠ ⁠Interfaces designed to read and write neural signals in real time •⁠ ⁠Potential to restore mobility, memory, and sensory function Neural interfaces are transitioning from lab testing to human integration. A new era of brain-machine connection is underway. Source: Neuralink, Elon Musk

Mario Nawfal

89,562 views • 10 months ago

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,917 views • 3 years ago

Interfaces that are generated, not coded. Excited to finally share Solaris. Video is the universal interface. Eventually, all UI will be chat and gestures in, chat and video out. Solaris opens new ways to build websites, apps and other interfaces. And most importantly, it gives new ways to train agents in much more dynamic environments.

Interfaces that are generated, not coded. Excited to finally share Solaris. Video is the universal interface. Eventually, all UI will be chat and gestures in, chat and video out. Solaris opens new ways to build websites, apps and other interfaces. And most importantly, it gives new ways to train agents in much more dynamic environments.

Cristóbal Valenzuela

250,894 views • 2 months ago

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

Sean Strong

115,751 views • 1 year ago

Today, we're launching the Runway Game Worlds Beta. Over the last few months, we have been working on research and products that are moving us closer toward a future where you will be able to explore any character, story or world in real time. While generating the pixels of these experiences is one aspect of this new frontier, another is the need for novel mechanics and interfaces. From how stories unfold to how your choices affect the worlds you’re simulating. Today’s beta release marks a first step in this direction, learn more below. (1/5)

Today, we're launching the Runway Game Worlds Beta. Over the last few months, we have been working on research and products that are moving us closer toward a future where you will be able to explore any character, story or world in real time. While generating the pixels of these experiences is one aspect of this new frontier, another is the need for novel mechanics and interfaces. From how stories unfold to how your choices affect the worlds you’re simulating. Today’s beta release marks a first step in this direction, learn more below. (1/5)

Runway

118,997 views • 1 year ago

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️

AI at Meta

3,571,979 views • 3 years ago

Implemented the basic workflow for the new lineart renderer... I decided to release it before the end of this year, and till that time, I won't do any research but to improve the stability and user interfaces. Please comment below if you want any features :)

Implemented the basic workflow for the new lineart renderer... I decided to release it before the end of this year, and till that time, I won't do any research but to improve the stability and user interfaces. Please comment below if you want any features :)

jwtstone

74,287 views • 2 years ago

🐯 by the end of december, i'm gonna use another leave from my commendation and gather with my members for our monthly meeting 🐯 jihoonie is gonna [take a leave] by then too! it just so happened that jihoon and i ended up having our leave at the same time, for the first time

🐯 by the end of december, i'm gonna use another leave from my commendation and gather with my members for our monthly meeting 🐯 jihoonie is gonna [take a leave] by then too! it just so happened that jihoon and i ended up having our leave at the same time, for the first time

🌌

51,525 views • 11 months ago

🇬🇷🇮🇱 GRETA THUNBERG IN GREECE: “ISRAEL IS ESCALATING GENOCIDE WITH GENOCIDAL INTENT” “I could talk for a very, very long time about our mistreatment and abuses in our imprisonment. Trust me, but that is not the story. Israel is escalating genocide and mass destruction with genocidal intent, attempting to erase an entire population in front of our eyes. What we are doing is the bare minimum. This genocide and others are being enabled by our governments, institutions, media, and companies. It is our responsibility to end that complicity.” Source: Clash Report

🇬🇷🇮🇱 GRETA THUNBERG IN GREECE: “ISRAEL IS ESCALATING GENOCIDE WITH GENOCIDAL INTENT” “I could talk for a very, very long time about our mistreatment and abuses in our imprisonment. Trust me, but that is not the story. Israel is escalating genocide and mass destruction with genocidal intent, attempting to erase an entire population in front of our eyes. What we are doing is the bare minimum. This genocide and others are being enabled by our governments, institutions, media, and companies. It is our responsibility to end that complicity.” Source: Clash Report

Mario Nawfal

332,010 views • 1 year ago

Today we are sharing our most complex #assembloid to date: a 4-part model of the human ascending neural somatosensory pathway generated by functionally integrating stem cell-derived cerebral cortical, thalamic, spinal and sensory #organoids. Check out the bioRxiv and a short video of activity as these parts self-assemble Work led by the multi-talented Ji-il Kim & Kent Imaizumi

Today we are sharing our most complex #assembloid to date: a 4-part model of the human ascending neural somatosensory pathway generated by functionally integrating stem cell-derived cerebral cortical, thalamic, spinal and sensory #organoids. Check out the bioRxiv and a short video of activity as these parts self-assemble Work led by the multi-talented Ji-il Kim & Kent Imaizumi

Sergiu P. Pasca

39,775 views • 2 years ago

Trick-or-Treating is not dead, just concentrated and organized. In our neighborhood, residents are advised to buy 1500 pieces of candy. That is usually not enough, so we end up closing early. The line in this video will last for two hours, and at a strict one piece per child, will consume our 30-lb stockpile. We are the White neighborhood surrounded by non-white neighborhoods. If you want this for your neighborhood, you must make a production of it. Ask the police to barricade the street, and announce it in the newspaper.

Trick-or-Treating is not dead, just concentrated and organized. In our neighborhood, residents are advised to buy 1500 pieces of candy. That is usually not enough, so we end up closing early. The line in this video will last for two hours, and at a strict one piece per child, will consume our 30-lb stockpile. We are the White neighborhood surrounded by non-white neighborhoods. If you want this for your neighborhood, you must make a production of it. Ask the police to barricade the street, and announce it in the newspaper.

Dr. Insensitive Jerk

52,401 views • 1 year ago

HTML enters 3D! Or vice versa? With the new HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?

HTML enters 3D! Or vice versa? With the new HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?

Gábor Pribék

176,784 views • 6 months ago

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

113,347 views • 3 months ago

1XBET is the best place for sports betting in Nigeria! Sign up now and get the biggest first deposit bonus in Nigeria of up to $260 using our promo code. Use it to increase the size of your first deposit by 100% and place bets without restrictions on withdrawals.

1XBET is the best place for sports betting in Nigeria! Sign up now and get the biggest first deposit bonus in Nigeria of up to $260 using our promo code. Use it to increase the size of your first deposit by 100% and place bets without restrictions on withdrawals.

1хBet

836,173 views • 3 years ago

The love and frenzy for our local cricketers reflect the spirit of our youth .These players are our true heroes, celebrated by the entire community at Bakshi stadium srinagar

The love and frenzy for our local cricketers reflect the spirit of our youth .These players are our true heroes, celebrated by the entire community at Bakshi stadium srinagar

Nuzhat gull

12,678 views • 1 year ago

At Google DeepMind, we believe one of AI's most transformative impacts is empowering scientists to solve society's hardest problems. Over the past year, we've evolved our coding agent, Google Google Antigravity, to accelerate end-to-end scientific workflows combining our latest Gemini models with science-specific: • breakthrough models like AlphaFold and AlphaGenome • new interfaces like the Biomolecular Structure Viewer The impact of this integration has been transformative for the pace of our research. As an example, in a single session using Antigravity, our researchers working on antimicrobial resistance surfaced a novel antimicrobial peptide candidate. To support academic researchers leverage these tools, we've launched an Antigravity for Science credits program and are looking forward to what this enables: Read the antimicrobial resistance case study:

At Google DeepMind, we believe one of AI's most transformative impacts is empowering scientists to solve society's hardest problems. Over the past year, we've evolved our coding agent, Google Google Antigravity, to accelerate end-to-end scientific workflows combining our latest Gemini models with science-specific: • breakthrough models like AlphaFold and AlphaGenome • new interfaces like the Biomolecular Structure Viewer The impact of this integration has been transformative for the pace of our research. As an example, in a single session using Antigravity, our researchers working on antimicrobial resistance surfaced a novel antimicrobial peptide candidate. To support academic researchers leverage these tools, we've launched an Antigravity for Science credits program and are looking forward to what this enables: Read the antimicrobial resistance case study:

Pushmeet Kohli

40,422 views • 27 days ago

✨ FURSUIT COMMISSIONS OPEN! ✨ We're opening up our 2025 commission slots, with an estimated delivery time by the end of the year! (Early submissions will be finished sooner 👀) Fill out a form using the link below, or DM for questions Commission Forms

✨ FURSUIT COMMISSIONS OPEN! ✨ We're opening up our 2025 commission slots, with an estimated delivery time by the end of the year! (Early submissions will be finished sooner 👀) Fill out a form using the link below, or DM for questions Commission Forms

Homebrewed Suits

11,422 views • 1 year ago

We know you're waiting for our End of Summer release, and we're excited to let you know that it will finally be LIVE by the end of October. We apologize this is later than our communicated window, however we hope that the extended wait is worth it.

We know you're waiting for our End of Summer release, and we're excited to let you know that it will finally be LIVE by the end of October. We apologize this is later than our communicated window, however we hope that the extended wait is worth it.

Session: Skate Sim

13,195 views • 1 year ago

We always listen to and value the voice of our community, treating every piece of feedback as an opportunity for progress. We remain committed to staying on track and delivering on our vision. Our goals are aligned with our users, and together, we’re moving forward toward even greater success! 🚀 While we understand that NFTs may still raise questions for some, rest assured that $XCOIN and NFTs are vital to the continued growth of NebX_Land. Whether you're ready to dive in or prefer to observe from the sidelines, we respect your choice. As the development team, our vision for NebX_Land remains strong, and with testing coming next month, exciting possibilities await. Join us in shaping the future! 🌟

We always listen to and value the voice of our community, treating every piece of feedback as an opportunity for progress. We remain committed to staying on track and delivering on our vision. Our goals are aligned with our users, and together, we’re moving forward toward even greater success! 🚀 While we understand that NFTs may still raise questions for some, rest assured that $XCOIN and NFTs are vital to the continued growth of NebX_Land. Whether you're ready to dive in or prefer to observe from the sidelines, we respect your choice. As the development team, our vision for NebX_Land remains strong, and with testing coming next month, exciting possibilities await. Join us in shaping the future! 🌟

NebX

68,753 views • 2 years ago

Only one Adobe Firefly video prompt from our research hit production-ready on the first generation. Prompt in comments 👀 It looks you have to direct the camera as much as the model to get the most out of Firefly. Every other video session in our research needed a revision. Revising the first frame is where Firefly broke: >motion failures (temporal flicker, motion continuity, physics in motion) carried 60% of video's issue mix once designers re-prompted. TLDR: in Adobe Firefly, the camera does a lot of the work. Bake it into the first prompt and the video lands. Its by far the best time to be a creative.

Only one Adobe Firefly video prompt from our research hit production-ready on the first generation. Prompt in comments 👀 It looks you have to direct the camera as much as the model to get the most out of Firefly. Every other video session in our research needed a revision. Revising the first frame is where Firefly broke: >motion failures (temporal flicker, motion continuity, physics in motion) carried 60% of video's issue mix once designers re-prompted. TLDR: in Adobe Firefly, the camera does a lot of the work. Bake it into the first prompt and the video lands. Its by far the best time to be a creative.

ben @ CVPR

12,847 views • 5 months ago