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: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

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.show more

World modeling and imitation learning have largely been considered... two disparate worlds. In our recent work, Unified World Models, just accepted to #RSS2025, Chuning Zhu provides a dead-simple unifying solution: just train a joint diffusion model over actions and future states, but with *decoupled* diffusion time steps across these modalities. Manipulating these decoupled time steps then allows for marginalization or conditioning on actions or states; a single model can serve as a policy, forward dynamics model, video prediction model, or inverse dynamics model by simply setting diffusion timesteps carefully. The resulting model can leverage video datasets along with robot training data much more effectively, and shows improved robustness, generalization, and flexibility. This is exciting because it is frustratingly simple, scalable, and shows strong improvement on real-world robotics problems. Please refer to Chuning Zhu 's excellent thread for more details! More details/code can be found on our website and in the paper -show more

I can't believe how good this turned out. Recently,... I put out my first physics paper proposing that life and the universe might be the result of a law governing how oscillators sync up and couple together. I find it beautiful, awe-inspiring, and deeply meaningful. It aligns with how I have always seen the world. It suggests that there is an arrow of negative entropy, a law governing how life forms in all of its complexity. Learning about it is intimidating. I am self-taught, and have struggled for months to understand and articulate the core concepts and framework. After I put out the paper, I was challenged by Danielle Fong 🔆 to make an 'explorable explanation'. A guide you can walk through, and which will hold your hand through each concept, equation, and principle. It was amazing to make. In fact, I plan to make many more covering the wide range of topics I have been researching and exploring. Both to help me, and because I believe that this is something the world needs right now. Link in commentsshow more

Imagine making 2D concept art for a game world... –pressing a button – and suddenly you can walk around an interactive 3D world. That's what Google DeepMind's new paper Genie 2 can do – simulate virtual worlds, including the consequences of any action (e.g. unlock door, jump, swim etc). Right now Genie 2 can generate consistent worlds for up to a minute. And this world model seems to generate larger 3D worlds than what World Labs showcased yesterday. Plus they're dynamic vs. static worlds – the foliage moves in the wind, the water ripples etc. Not quite ready for prime time, but promising on two fronts: 1. For game developers: enabling rapid prototyping of interactive experiences straight from concept art 2. For AI research: providing unlimited, diverse 3D environments for training and testing AI agents The race for building the biggest, baddest world model is very much on. Meanwhile, all I can think is "if only Stadia was still around!"show more

Great end of the week with over 350 Global... Model World Health Organization (WHO) Youth Delegates, who concluded their first gathering in Geneva today and adopted a declaration on the urgent need for a #PandemicAccord to protect the world from future pandemics: This generation is instrumental in shaping a safer, fairer, and healthier world. Their voices are essential in driving effective solutions for global health crises. I hope that the Member States will listen to their voices as they gather next week to conclude the Pandemic Agreement negotiations.show more

The architecture of this new world model is one... of the most interesting things I've seen lately: Let me first explain how most world models work: They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment. Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore. Tripo AI is releasing its Project Eden model, which works very differently: The model builds the world first, and then renders it based on that map. That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map. This architecture flips the whole thing. Now, you get the following: 1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw. 2. You can edit the world, and those changes persist for anyone who enters later. 3. Multiple people and AI agents can coexist in the world and see it from different perspectives. This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out. Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.show more

✨ Every time the video models get better, the... try on model on Photo AI also becomes a lot more useful, as a large % of my customers now are e-commerce store And showing clothes in a video is nice for sales! With AI this means stores don't need to do expensive shoots flying a model and entire camera and light crew around the world They can just upload a few photos of their models, then upload the clothes, and describe the setting (like a beach in Thailand) and in less than 10 seconds it's generated, for a video in less than a minute! Below is the input: a dress laid flat, and output: a full video shootshow more

🚀 We introduce Neural Theorizer (NEO) — a new... type of world model that learns to theorize the world from observation, without language or LLM supervision. Selected as an ICML 2026 oral presentation — 0.7% of submitted papers. The paper asks: "What does it mean to understand the world and build a world model?" Today’s world models are often trained to predict the future: the next frame, next latent state, or next observation. But is prediction enough? We argue that a world model should be a theory-building system: one that discovers reusable primitives, composes them into executable explanations, and transfers those explanations to novel phenomena. NEO is our first step toward this vision — a World Theory Model that learns explicit, compositional theories from raw observation. This work was led by my wonderful students: Doojin Baek*(Doojin Baek), Gyubin Lee* (GyuBin Lee), Junyeob Baek (Junyeob Baek), and Hosung Lee (Hosung Lee). For more details, take a look at the paper — and if you’re attending ICML, let’s talk there! 📄 arXiv: 🌐 Project page:show more

✨ Made a new mini feature on Photo AI:... [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!show more

🎙️🇧🇷 Aitana Bonmatí on the 2027 Women’s World Cup... in Brasil “What can I say about Brasil? I think it is a country that is absolutely passionate about football. The prospect of playing a World Cup there really excites me because, when you think of football, Brasil is one of the countries that comes to mind. So, I hope to enjoy that World Cup and successfully defend the title, though that will be the hardest part.”show more

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!show more

" A mattress. Well Maybe for some individuals. "... This is something based on a comic I made with Ai in the past. I had the comic animated with Atlabs AI The video pretty much says what everything is about. I honestly like silly comics like this. I really should make more and have them as videos as well. That's another things for a long list of things I need done... Also I plan on running more tests with Omniflash in the future especially when Seedance models may not do things a certain way or have things looking a certain way. Also if anybody is planning on using Atlabs for anything I plan on making a video next month on how I use certain video models and which I typically use. This is specifically on how I use certain models for certain things. Not MG. I plan on having it in a tutorial section. I have hopes this will provide people that use any video models with some needed help when choosing what they should get started with because a Sora video model is no longer an option, which was very integral involving how I would use video models in general. Anyway I have an atlabs link below. If you make an account or have one already I hope what I plan on making next month and showing you, helps a lot. This was made with AtlabsAi. This was all done with Ai. #furrycomedyvideo #furryvideo #aianimation #aifurryshow more

This is what men with low self esteem who... are not confident in their sexuality do in their free time. They are so scared of being called "gay" or are not sure if they might be that they have to prove to the world and themselves that they are not. This is not a turn-on for women by the way. At least not any I have ever met.show more

⚔️ Kingdom Come Deliverance first impressions ⚔️ Loving it... so far, basically a medieval detective simulator that really doesn't care that you are the main character. And I'm all here for it. ▪️The WORLD is the real star of the show here and even though it's got plenty of jank and lots of copy and paste NPC faces, it just feels so IMMERSIVE. Even the UI just transports me to the times with a bright colourful medieval art style. ▪️The MUSIC I love, absolutely sells the world and basically ASMR as you trot around on your horse through the world. ▪️THE Combat is a real interesting one, it's got quite the learning curve which I actually LIKE, it definitely has some jank to it as well but I really appreciate the attempt at an original and nuanced combat system. (Having to stop your bleeding with bandages is really cool) ▪️The Story has gripped me (19 hours in so far) And while it seems a simple revenge story on the face of it, I think the story is more about Henry making his way through the world after the horrors of Skallitz. The writing quality is top notch as well as the quest design also. ▪️The CHARACTERS are amazing and the humour is top notch. I'm not sure the last time I laughed so much at a game. Henry is great and so well voiced by Tom McKay This really feels like Warhorse Studios have put a lot of love and work into making an authentic medieval world and as a bit of a medieval nerd I can't get enough of this game. A True RPG as well by all accounts, the game really makes me think hard about how to approach situations. Also I can't wait to get to KCD2.show more

3 years ago Refik Anadol & Efsun, together with... the royal family of the forest, the Yawanawa, dreamed of a project that could share the crossover of traditional indigenous art with futuristic pigments of AI. They dreamed of building a community to not only host their family, but also bring together their indigenous brothers and sisters from around the world. Aldeia Sagrada was reimagined. We 1OF1 are very honoured & deeply grateful that Refik Anadol & the Yawanawa family have chosen us to be the steward of their historic collaborative art work, the Winds of Yawanawa 1of1. Last week my family & I had the privilege to join Indigenous Nations from across the Amazon basin & around the world as they came together for a truly historic & deeply beautiful moment at the Indigenous Ayahuasca Conference in Acre, Brasil, where Indigenous leaders shared their ancient wisdom, beautiful art & wonderful energy with each other. As someone who has built infra in Brazil, I can confirm that what Refik Anadol and the Yawanawa family have built in Aldeia Sagrada is absolutely breathtaking & indescribable. The infrastructure & organization of their wonderful community is incredible. They have proven to the world a model for synergistic alliances between traditional Indigenous nations with new technologists, creatives and builders that can both massively support these native communities as well as celebrate the preservation of their way of life. I found myself overwhelmed with emotion at points throughout the week witnessing how amazing this place and these people are. It is with all of the lessons of 1OF1’s global tours in hand & our hearts filled with a deep sense of mission, that we commit to share this iconic work of art with the world in conversation with other works of Amazonian indigenous art. We promise to share the inspiring message of the Yawanawa across the globe through the power of art.show more

VTubing is for everyone! I don't like to bring... this up, but recent events in the VTuber community made some people really vile. I had my M&G at HolMat last week and had people come up and just yell at me for being a girl in the "womans world", that is VTubing, no idea about who I was, or why I was there. I had the same group return to my handler multiple times, I felt really worried about the person carrying me around having to deal with this repeatedly and tried to steer them away from the group. It seems they found my YT and left me a handful of the same comments, luckily all caught by moderation tools. While I will refrain from M&G's for a little until this calms down I want to say this; I have been managing for over 1.5 years now, I deliberately take on male VTubers to show them that they can still do it. I take on people that have babiniku accounts, those that are changing from one gender presentation to another and want help, and those that have no gender presentation in their avatar. A lot of male VTubers struggle to find a manager because the stereotype is that all male VTubers are evil and it perpetuates a stereotype that extends beyond entertainment industry subcultures like streaming. VTubing has always been a medium, while character and marketing matters, it's about what makes you happy, YOU are the person that makes the content. Use whatever you want as an avatar, use a voice changer if that's what you want to do. Every month I have a male client bring up they can't do it the same way, that it's easier if jiggle physics or a cute voice is the answer to fast growth. And I tell them yeah, I can also do ASMR, I can do drama content, collab with a larger person, and get to x amount of viewers. There are shortcuts in every entertainment profession and subculture. Does it last? Do quick fixes for anything ever last? Yes, great physics and an expensive model can get people in, but if your value, your way of interacting with people, your content plan and marketing is ass, you can pack up. Most of us start on a small budget, premade or resold models, and it's the same in the big league entertainment industry too. Can I take out a loan and put myself on a billboard tomorrow, can I pay the most expensive model artist and rigger and get in along corporate VTubers tomorrow? Sure. Will it last, will it be genuine, will people trust me? Hell no. Genuine communities and growth build trust. I think streaming, creative industries, entertainment, are full of people, regardless of gender, that will see success and call it "easy", because of what they see as the end product. They don't see most VTubers working a second job, they don't see the managers, they don't see 100+ hours a month going into content production, years invested in singing and voice lessons, model redebut after redebut. I think a lot of male VTubers get a bad rep, because so many boys are raised without putting emphasis on empathy and creativity, watching my brothers be told they should not pursue art, that theatre class is a waste of time, and that they needed to go study x or y to make money for their families in the future was heartbreaking. Nobody should have to look at others and feel so much hatred for society they turn against a whole group of people. If you want to pursue entertainment, please do. If you want to grow and try and make a name for yourself, you should start there, not with yelling about how you already failed. "Oh but I can't", "Oh but the odds are stacked against me", look at the big streamers, look at Ironmouse who overcame everything with hard work, look at Kiara who rose from the ashes, look at everyone that fights against their odds every day and give it your all. If you already think you lost, then you have nothing to lose. Don't give up on your dreams because others tell you to.show more

i think it’s been enough time & we can... finally address this particular discourse, and i think there’s a healthy discussion we can have about it. i genuinely think a fully traditional rendition in 2026, by artists operating at a global pop level, would have changed how the project was received internationally. there’s a very real possibility it would’ve been boxed into “world music,” treated more like cultural exhibition than a modern musical statement, keeping in mind that Arirang Album is not for 'aesthetics' nor is it a history lesson. using 808s, trap production, pop structures, and english hooks while still centering Arirang was actually a significant artistic choice. historically, Arirang was the song of ordinary people. in today’s world, pop culture/pop music is the common language. using contemporary pop to carry that sentiment to millions of listeners across countries feels very aligned with the spirit of what Arirang represented in its own time. and ‘unapologetically korean’ does not have to mean “only in korean” or “frozen in tradition.” it can also mean Korean artists having full control over how their culture is presented, modernized, exported, and understood. i also think if they had leaned entirely into historical styling and traditional presentation, western media may have reduced it to a “cultural curiosity” instead of engaging with it as a current, competitive pop release. critics likely would’ve framed it as heritage performance before artistry. i am glad they chose this route for the album.show more

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely... on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:show more