Language models predict the next token. Interactive video models... predict the next video frame. We're in the 2022-era of these models, but video feeling sentient is imminent, along with an explosion of applications.show more

Brisbane (Australia) is expected to be directly hit by... a tropical cyclone #Alfred 🙏🧐 The storm will slow down significantly before making landfall, thus resulting in extremely heavy rainfall along the coast. ICON models predict over 500 mm of precipitation in some areas by the end of the week. Flooding is expected. The video shows the progress of the storm over the next 3 days:show more

Predicting the next word "only" is sufficient for language... models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.show more

I think the future of AI-assisted anime is not... video models, but image continuity models like GPT Image 2.5. Predicting the next frame conditioned on the previous frame gives you much better control than predicting the next few seconds of video. You also don't need to predict all 24 frames every second. Since anime is basically layered animation, you can keep the same image for 5seconds while only the hand is waving or the eyes are blinking. Frame by frame prediction is also the nature of 2D anime. I've never really get the idea with turning everything into ultra-smooth 60 FPS animation. The problem with this model right now is that the 'invisible watermark' is too visible, which is really annoying. When you do chained generations, the watermark keeps stacking up to the point where it actually makes the project worse. It also has very poor color consistency.show more

It’s incredible what’s possible to generate with just a... prompt in a few minutes! The progress of video models is astonishing. Imagine the quality and accuracy in the next few years. Prompt ⬇️show more

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:show more

💡 The Age of Foundational AI! In AI, the... base layer matters most. Solidus Ai Tech AI Marketplace offers a curated lineup of foundational models designed to support reasoning, coding, multilingual tasks, and enhanced privacy features. From DeepSeek-R1 to SecretAI, these models provide the infrastructure for the next generation of AI agents and applications. Explore the models here →show more

"old" video models have an incredible sense of motion... that "better" models lack... not constrained by the simulation of reality this one is seedance 1.5, one of my favoritesshow more

Most AI models just predict the next pixel to... build a narrative or an image. Gemini Omni is different. Gemini Omni has an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics for more realistic movements that follow real-world logic.show more

The level of class and elegance in this video... is insane. Highly respectable ladies who carry themselves so well. These are the right role models!show more

and the way you can NEVER predict what the... next lingorm video to hit your timeline is going to be 😭😭😭😭show more

these might be the best video game character models... ever madeshow more

📢Introducing Generated Reality📢 A world model for XR that... turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4show more

Predicting how the environment changes over time is a... key task in robotics, enabling all kinds of downstream tasks. Trace Anything is a very interesting look at how you can train models which predict the trajectory each point will take in the future -- you can use this for robot manipulation, video prediction, and more. Learn more ->show more

We gave AI models one prompt: build an interactive... black hole, physically informed, with the presence of Gargantua from Interstellar.show more

Automating the Search for Artificial Life with Foundation Models... Presents ASAL, the first use of vision-language models in Artificial Life, discovering diverse, novel simulations across substrates proj: abs:show more

Combining the explicit control of 3D software with the... creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools like intangible are built around such a workflow so you don't need to duct-tape apps together. Pretty cool!show more

The "AI video race" is changing. The winners won't... just be models that generate realistic frames. They'll be models that understand: - context - motion - storytelling - creative intent MiniMax H3 is a glimpse of where AI video is heading. #hailuoai #hailuo #MiniMaxH3 #H3 Hailuo AI (MiniMax)show more

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page:... Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.show more