Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-world engine. The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer....

XGEN_labs's profile picture

XGEN Labs

1,329 subscribers

1,473,125 görüntüleme • 5 gün önce •via X (Twitter)

EğitimOyunBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

33 Yorum

XGEN Labs profil fotoğrafı
XGEN Labs5 gün önce

More on the technical thinking behind our generative world simulation approach, including JING and DAO: 📖 Read the full blog:

Sevan Bomar profil fotoğrafı
Sevan Bomar5 gün önce

I think we need to grow up as a species and start making things that will help the world before its gone.

Otto Gradkowski profil fotoğrafı
Otto Gradkowski4 gün önce

@_akhaliq These kinds of simulations will basically render GTA obsolete. If I can go around any world I construct and do anything I want, why the fuck would I play LBGTA: Girl Boss Edition? 😂

Lean profil fotoğrafı
Lean4 gün önce

Back in 2003, as an 11-year-old kid, I dreamed about this. Now, at almost 34, I’m so hyped to see how far we’ve come. You made a young boy really happy. I’m available as a beta tester if you need one! Love you guys!

火箭手Neo profil fotoğrafı
火箭手Neo5 gün önce

Naming the model JING and the engine DAO means when the simulation inevitably glitches, you can just blame it on Buddhist karma

Nisarg Bhatt profil fotoğrafı
Nisarg Bhatt5 gün önce

Has to be a top 3 demos I've watched

ST John profil fotoğrafı
ST John4 gün önce

Westworld?

JonRods profil fotoğrafı
JonRods4 gün önce

Simulating an evolving world that continues to exist and compute state changes independently of the observer is the real holy grail. This architecture feels less like generating next frames and more like building autonomous virtual societies. Congrats

Hari Dangi profil fotoğrafı
Hari Dangi5 gün önce

Is it real

Mawk profil fotoğrafı
Mawk5 gün önce

How is it shared? How is there persistence?

Cellarius profil fotoğrafı
Cellarius5 gün önce

In our occupation as reality creators our days millennia eternities will be spent constructing innumerable worlds for us to occupy, for our avatars to be trained in, for other world-creating immortals, for our created beings to evolve in.

山海AI profil fotoğrafı
山海AI4 gün önce

First-person perspective, interactivity, and dialogue, combined with a shared state machine, feels like a significant step towards creating a truly playable game world.

Rafael Estrela | IA profil fotoğrafı
Rafael Estrela | IA4 gün önce

There's a big difference between predicting the next frame and keeping a world coherent after dozens of actions have already happened.

Zoe profil fotoğrafı
Zoe5 gün önce

The combination of an interactive experience model and a persistent shared-world engine is fascinating. Congrats on ranking #1 on WBench’s Full split! 🎉

Krishna Thakur profil fotoğrafı
Krishna Thakur4 gün önce

At this pace, by 2030, if we can’t simulate the entire universe, we’ll at least be able to simulate our own Milky Way Galaxy with remarkable detail.

Shraddha Bharuka profil fotoğrafı
Shraddha Bharuka4 gün önce

The fact that the world keeps evolving beyond the observer is the part I keep thinking about.

Tulsi Soni profil fotoğrafı
Tulsi Soni4 gün önce

We're used to AI generating what comes next. What's more interesting here is asking what exists behind that frame—and what keeps happening when nobody is watching.

Aastha profil fotoğrafı
Aastha4 gün önce

The distinction between what the agent sees and what actually exists in the world is fascinating.

Yash profil fotoğrafı
Yash4 gün önce

⁠Different agents, different perspectives, same underlying world. I like this setup.

Shushant Lakhyani profil fotoğrafı
Shushant Lakhyani5 gün önce

wow wow wow wow wow

Vaidehi profil fotoğrafı
Vaidehi4 gün önce

First-person experience + a persistent world is a pretty interesting combination.

Dr. Josh C. Simmons profil fotoğrafı
Dr. Josh C. Simmons4 gün önce

@grok what system specs am i gonna need to run this

(identity '[:pankaj :λ]) profil fotoğrafı
(identity '[:pankaj :λ])5 gün önce

WoW, the world of warcraft could be reimagined in this.

Dhairya Karekar profil fotoğrafı
Dhairya Karekar4 gün önce

A world that doesn't stop when you stop looking at it. That's interesting.

Devon profil fotoğrafı
Devon5 gün önce

Very cool

Bartek Wlodarczyk profil fotoğrafı
Bartek Wlodarczyk5 gün önce

World simulation? um.. nope. It has nothing to do with that.

LEX profil fotoğrafı
LEX4 gün önce

Splitting the interactive render from a computable rules layer is what DeepMind pointed at with Genie 3. If DAO is real rules and not retrieval, this is the first Chinese lab to ship that split.

Altiam Kabir profil fotoğrafı
Altiam Kabir4 gün önce

What caught my attention isn't the generated scene. It's the fact that the agent can only act on what it actually experiences.

Eliana 🇺🇸 profil fotoğrafı
Eliana 🇺🇸4 gün önce

The subjective/objective separation makes a lot of sense for this kind of simulation.

kieran Drew profil fotoğrafı
kieran Drew4 gün önce

Congrats on hitting #1 on WBench Full split! Huge milestone for XGEN Labs! 🎉

Parul Gautam profil fotoğrafı
Parul Gautam4 gün önce

The shared world state is the really interesting part here.

Mark Yu profil fotoğrafı
Mark Yu5 gün önce

This kinda gives me Westworld vibes. Same world, but everyone experiences a different story depending on where they go and what they choose.

Raya profil fotoğrafı
Raya5 gün önce

The idea of a world continuing to evolve even when an agent isn't observing it is seriously compelling. 🚀

Benzer Videolar

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.
1:31

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,676 görüntüleme • 4 ay önce

🌎Create, Tokenize, and Trade Your Own Worlds This is one way we envision the World Engine. It’s an engine designed to let you create without limits, supported by an AI master agent that assists across every aspect of development. The agent can spawn assets, generate complete scenes and levels, and help with placement, styling, mechanics and coding, all within a single engine. With these capabilities, you can seamlessly build your own world. From there, the launchpad enables you to tokenize that world, pair its token with $NEURAL, create a liquidity pool, and release a tradable token directly tied to your world. 🖥 Watch the video for the full breakdown!
0:53

🌎Create, Tokenize, and Trade Your Own Worlds This is one way we envision the World Engine. It’s an engine designed to let you create without limits, supported by an AI master agent that assists across every aspect of development. The agent can spawn assets, generate complete scenes and levels, and help with placement, styling, mechanics and coding, all within a single engine. With these capabilities, you can seamlessly build your own world. From there, the launchpad enables you to tokenize that world, pair its token with $NEURAL, create a liquidity pool, and release a tradable token directly tied to your world. 🖥 Watch the video for the full breakdown!

NeuralAI

14,565 görüntüleme • 1 yıl önce

🌎Making Game Development Simple with the World Engine The World Engine is revolutionizing how game engines work in many ways. If you create a game, it's a lot of single work that you're doing, and then you're pushing it to other people, and then they work with it. But with the World Engine, you build together in real time, like in a shared sandbox. It’s faster, easy to use, runs on JavaScript/TypeScript, and includes AI tools that help both developers and non-coders create games easily. 🖥 Watch the video for the full breakdown!
1:19

🌎Making Game Development Simple with the World Engine The World Engine is revolutionizing how game engines work in many ways. If you create a game, it's a lot of single work that you're doing, and then you're pushing it to other people, and then they work with it. But with the World Engine, you build together in real time, like in a shared sandbox. It’s faster, easy to use, runs on JavaScript/TypeScript, and includes AI tools that help both developers and non-coders create games easily. 🖥 Watch the video for the full breakdown!

NeuralAI

24,349 görüntüleme • 1 yıl önce

Yann LeCun (Yann LeCun) just revealed why he left Meta, Why are LLMs an extremely narrow field, and how "World model" is the way to build really meaningful agentic future. 🎯 Beautiful and simple in 1.5 mints. "I can’t imagine we can build agentic systems without those systems having the ability to predict, in advance, what the consequences of their actions are going to be. The way we act in the world is that we can predict the consequences of our actions, and that’s what allows us to plan. So what is a world model? Given the state of an environment, a system you want to control at time t, and given an action or intervention you imagine taking, can you predict the state of the world (or the system) at time t + 1? If you can, that’s a world model. You don’t do this at a pixel level, if it’s video. You do this in an abstract representation space, and that’s a crucial key insight." --- From 'AI House Davos" YT channel (full link in comment)
1:40

Yann LeCun (Yann LeCun) just revealed why he left Meta, Why are LLMs an extremely narrow field, and how "World model" is the way to build really meaningful agentic future. 🎯 Beautiful and simple in 1.5 mints. "I can’t imagine we can build agentic systems without those systems having the ability to predict, in advance, what the consequences of their actions are going to be. The way we act in the world is that we can predict the consequences of our actions, and that’s what allows us to plan. So what is a world model? Given the state of an environment, a system you want to control at time t, and given an action or intervention you imagine taking, can you predict the state of the world (or the system) at time t + 1? If you can, that’s a world model. You don’t do this at a pixel level, if it’s video. You do this in an abstract representation space, and that’s a crucial key insight." --- From 'AI House Davos" YT channel (full link in comment)

Rohan Paul

383,490 görüntüleme • 8 ay önce

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:
0:44

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,079,898 görüntüleme • 3 ay önce

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.
1:29

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

The Humanoid Hub

17,065 görüntüleme • 7 ay önce

LARP: Language-Agent Role Play for Open-World Games paper page: Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios.
1:03

LARP: Language-Agent Role Play for Open-World Games paper page: Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios.

AK

143,974 görüntüleme • 2 yıl önce

Many have said that the differences and divisions in our world are too great for us to come together for the common good. But the Summit of the Future showed that with a spirit of dialogue and compromise, we can join forces to steer our world to a more sustainable path. As this year’s #UNGA activities wind down, we must remember that this is not the end. It is in all our interests to choose the future we want and to guide our world towards it. The journey continues. Let’s keep going.
0:42

Many have said that the differences and divisions in our world are too great for us to come together for the common good. But the Summit of the Future showed that with a spirit of dialogue and compromise, we can join forces to steer our world to a more sustainable path. As this year’s #UNGA activities wind down, we must remember that this is not the end. It is in all our interests to choose the future we want and to guide our world towards it. The journey continues. Let’s keep going.

António Guterres

110,811 görüntüleme • 2 yıl önce

#WATCH | Jonathan Granoff, President, Global Security Institute says, " I don't think we can have peace in the world unless we have peace amongst and within the world's religions...a country such as India...which has over its Parliament the model 'world is one family'. We just saw in Times Square, a statement by PM of India, 'to be inclusive, to honour the sacredness of the natural world that shared environment'. If India goes on the path of being an example of unity and multiplicity, an example of respecting the human rights and dignity of all religions and all people, it will be the most powerful statement to the world of becoming the world we have to live in..."
1:11

#WATCH | Jonathan Granoff, President, Global Security Institute says, " I don't think we can have peace in the world unless we have peace amongst and within the world's religions...a country such as India...which has over its Parliament the model 'world is one family'. We just saw in Times Square, a statement by PM of India, 'to be inclusive, to honour the sacredness of the natural world that shared environment'. If India goes on the path of being an example of unity and multiplicity, an example of respecting the human rights and dignity of all religions and all people, it will be the most powerful statement to the world of becoming the world we have to live in..."

ANI

14,021 görüntüleme • 2 yıl önce

Our world is vast, but we are all in it together. And this is our shared cause – peace. 🇺🇦 proposed its Peace Formula to the world. As long as invaders remain on our land, no one will sit down at the negotiating table with 🇷🇺. The colonizer must get out. And the world has enough power to force 🇷🇺 to restore peace step by step. We have developed the Peace Formula in a way that ensures each of its points is backed by United Nations 🇺🇳 resolutions. And in a way that everyone in the world can choose the track they can contribute to. From Japan to the Arab countries, from Europe to Latin America, we find support for our Formula. And we continue this work.
0:53

Our world is vast, but we are all in it together. And this is our shared cause – peace. 🇺🇦 proposed its Peace Formula to the world. As long as invaders remain on our land, no one will sit down at the negotiating table with 🇷🇺. The colonizer must get out. And the world has enough power to force 🇷🇺 to restore peace step by step. We have developed the Peace Formula in a way that ensures each of its points is backed by United Nations 🇺🇳 resolutions. And in a way that everyone in the world can choose the track they can contribute to. From Japan to the Arab countries, from Europe to Latin America, we find support for our Formula. And we continue this work.

Volodymyr Zelenskyy / Володимир Зеленський

2,286,871 görüntüleme • 3 yıl önce

FIFA President Gianni Infantino: ""The benefits that we can generate from a (FIFA) World Cup, from a (FIFA) Club World Cup, from a (FIFA) Women’s World Cup, from a (FIFA) Women’s Club World Cup, and so on and forth, go back to the entire world, because we want to give every child, in every corner of the world, an opportunity, a chance, a possibility to dream and to believe that he can make it. And even if he or she doesn’t make it, at least to spend a happy moment together in playing football."
1:22

FIFA President Gianni Infantino: ""The benefits that we can generate from a (FIFA) World Cup, from a (FIFA) Club World Cup, from a (FIFA) Women’s World Cup, from a (FIFA) Women’s Club World Cup, and so on and forth, go back to the entire world, because we want to give every child, in every corner of the world, an opportunity, a chance, a possibility to dream and to believe that he can make it. And even if he or she doesn’t make it, at least to spend a happy moment together in playing football."

FIFA Media

10,636 görüntüleme • 4 ay önce

Attention all citizens of the world! We are excited to announce that in just 20 days, the Perfect World will be launching! This revolutionary project is set to change the way we experience gaming and virtual reality forever! The Perfect World project will be launched on multiple launchpads, multi chains and will be listed on top exchanges, making it accessible to gamers and investors alike. With this multi-platform launch, the project is set to be the talk of the town, and everyone is eagerly anticipating its release. The Perfect World project is not just any ordinary game. It's an immersive, never-ending adventure that allows players to become anyone or anything they desire. With state-of-the-art AI technologies, players can create their characters based on their unique preferences and interests. They can then explore a vast open world, complete challenges, and even create their own games using the AI-powered imagination engine. To make this project even more exciting, the Perfect World team is partnering with some of the most prominent names in the industry. We are collaborating with top gaming studios, blockchain developers, and AI experts to create the ultimate gaming experience. We invite you to join us on this incredible journey as we explore the limitless possibilities of the Perfect World. Get ready to experience gaming like never before, with the perfect blend of innovation, creativity, and technology. Stay tuned for more updates on this groundbreaking project, and get ready to enter the perfect world! $PA #GameFi #AI #PerfectWorld #DAO
0:40

Attention all citizens of the world! We are excited to announce that in just 20 days, the Perfect World will be launching! This revolutionary project is set to change the way we experience gaming and virtual reality forever! The Perfect World project will be launched on multiple launchpads, multi chains and will be listed on top exchanges, making it accessible to gamers and investors alike. With this multi-platform launch, the project is set to be the talk of the town, and everyone is eagerly anticipating its release. The Perfect World project is not just any ordinary game. It's an immersive, never-ending adventure that allows players to become anyone or anything they desire. With state-of-the-art AI technologies, players can create their characters based on their unique preferences and interests. They can then explore a vast open world, complete challenges, and even create their own games using the AI-powered imagination engine. To make this project even more exciting, the Perfect World team is partnering with some of the most prominent names in the industry. We are collaborating with top gaming studios, blockchain developers, and AI experts to create the ultimate gaming experience. We invite you to join us on this incredible journey as we explore the limitless possibilities of the Perfect World. Get ready to experience gaming like never before, with the perfect blend of innovation, creativity, and technology. Stay tuned for more updates on this groundbreaking project, and get ready to enter the perfect world! $PA #GameFi #AI #PerfectWorld #DAO

Perfect World

372,086 görüntüleme • 3 yıl önce

Thank you team Prachyam for making this wonderful video which captures the spirit and journey of World Hindu Congress (WHC) thus far. WHC is a platform for Hindus across the world to come together, express together; to deliberate on challenges and opportunities facing us a community; and to organize ourselves with a shared vision and purpose to work for the progress and prosperity of Hindus, and the betterment of humanity and the world. The 7 thematic parallel conferences during WHC are dedicated to the critical areas that determine the strength, acceptability and respectability of any community: Economy, Education, Media, Politics and Organizations, combined with the unique leadership and contribution of Women and Youth. After the inaugural WHC 2014 @ New Delhi, followed by WHC 2018 @ Chicago, Hindus from different corners of the world will come together in Bangkok from 24-26 November for the World Hindu Congress 2023, to reaffirm our commitment to a world that is prosperous, just, and peaceful—a vision rooted in the core values of Hindu Dharma. To register for WHC 2023, visit #WorldHinduCongress2023
1:26

Thank you team Prachyam for making this wonderful video which captures the spirit and journey of World Hindu Congress (WHC) thus far. WHC is a platform for Hindus across the world to come together, express together; to deliberate on challenges and opportunities facing us a community; and to organize ourselves with a shared vision and purpose to work for the progress and prosperity of Hindus, and the betterment of humanity and the world. The 7 thematic parallel conferences during WHC are dedicated to the critical areas that determine the strength, acceptability and respectability of any community: Economy, Education, Media, Politics and Organizations, combined with the unique leadership and contribution of Women and Youth. After the inaugural WHC 2014 @ New Delhi, followed by WHC 2018 @ Chicago, Hindus from different corners of the world will come together in Bangkok from 24-26 November for the World Hindu Congress 2023, to reaffirm our commitment to a world that is prosperous, just, and peaceful—a vision rooted in the core values of Hindu Dharma. To register for WHC 2023, visit #WorldHinduCongress2023

World Hindu Congress

27,744 görüntüleme • 2 yıl önce

Odyssey is now previewing Odyssey-3, a world model that it calls a Physics Agent! The model was designed to learn how the world behaves from visual observation and then apply that understanding to control both real and simulated systems. Odyssey-3 can run across different machines and games, with a small amount of task-specific experience teaching it each set of controls. The preview covers humanoids, robot arms, a car and a drone being controlled by an AI model, playable video games, and training runs for other AI agents.
0:30

Odyssey is now previewing Odyssey-3, a world model that it calls a Physics Agent! The model was designed to learn how the world behaves from visual observation and then apply that understanding to control both real and simulated systems. Odyssey-3 can run across different machines and games, with a small amount of task-specific experience teaching it each set of controls. The preview covers humanoids, robot arms, a car and a drone being controlled by an AI model, playable video games, and training runs for other AI agents.

🚨 AI News | TestingCatalog

23,779 görüntüleme • 7 gün önce

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):
0:24

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):

Etched

24,718,114 görüntüleme • 1 yıl önce

🚀 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:
0:00

🚀 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:

Sungjin Ahn

100,193 görüntüleme • 2 ay önce

I am stocked to announce that I won the OpenAI Developers Codex x Mollie Hacka Worldwide Hackathon in Paris. 60+ builders, every one of us working solo, one day to ship. I built mine around a single question: who gets to own intelligence? The default answer is scary. You hand your data to a handful of labs, they train the model, they own it, and you rent back a thin slice of what your own data made possible. That is the bargain on the table today. I do not accept it. So I built Lensemble: a Tapestry like distributed training platform for JEPA based World Models. What does it enable: World Models that a community improves together, keeps sovereign, and co-owns. Two bets sit underneath it. First, the paradigm. Language models predict the next token. Powerful for text, a dead end for the physical world. A robot does not need to autocomplete sentences, it needs to predict what happens next in the world. That is what JEPA does: it learns by predicting representations instead of pixels or tokens. I am convinced world models are the most underrated paradigm in AI right now, and the closest thing we have to a ChatGPT moment for robotics. Second, the politics. Your raw trajectories never leave your machine. Each participant trains locally against a shared protocol and ships only an update, never the data. A federated round folds those updates into one shared world model, a LeWorldModel based model, and the gain is measured, not claimed: a 12k-parameter adapter on a frozen backbone, held-out prediction error down about 12 percent, the model measurably less surprised by the world. Then the upside is split by contribution weight, so the people who improved the model own a share of what it earns. This is the thesis behind Project Tapestry, the AI Alliance and Yann LeCun's push for federated, sovereign frontier AI, carried into world models and robotics. Call it Tapestry for the physical world. All of it built solo, in a single day, with Codex as my pair the whole way. Thank you to OpenAI Codex and Mollie for backing builders who ship real things, and to Boris and the organizing crew for the room and the standard you set. Intelligence the world improves, and the world owns. That is the future I want for my kids, and the one I will keep building.
1:13

I am stocked to announce that I won the OpenAI Developers Codex x Mollie Hacka Worldwide Hackathon in Paris. 60+ builders, every one of us working solo, one day to ship. I built mine around a single question: who gets to own intelligence? The default answer is scary. You hand your data to a handful of labs, they train the model, they own it, and you rent back a thin slice of what your own data made possible. That is the bargain on the table today. I do not accept it. So I built Lensemble: a Tapestry like distributed training platform for JEPA based World Models. What does it enable: World Models that a community improves together, keeps sovereign, and co-owns. Two bets sit underneath it. First, the paradigm. Language models predict the next token. Powerful for text, a dead end for the physical world. A robot does not need to autocomplete sentences, it needs to predict what happens next in the world. That is what JEPA does: it learns by predicting representations instead of pixels or tokens. I am convinced world models are the most underrated paradigm in AI right now, and the closest thing we have to a ChatGPT moment for robotics. Second, the politics. Your raw trajectories never leave your machine. Each participant trains locally against a shared protocol and ships only an update, never the data. A federated round folds those updates into one shared world model, a LeWorldModel based model, and the gain is measured, not claimed: a 12k-parameter adapter on a frozen backbone, held-out prediction error down about 12 percent, the model measurably less surprised by the world. Then the upside is split by contribution weight, so the people who improved the model own a share of what it earns. This is the thesis behind Project Tapestry, the AI Alliance and Yann LeCun's push for federated, sovereign frontier AI, carried into world models and robotics. Call it Tapestry for the physical world. All of it built solo, in a single day, with Codex as my pair the whole way. Thank you to OpenAI Codex and Mollie for backing builders who ship real things, and to Boris and the organizing crew for the room and the standard you set. Intelligence the world improves, and the world owns. That is the future I want for my kids, and the one I will keep building.

abdel

20,191 görüntüleme • 3 ay önce

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.
0:51

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

AK

367,249 görüntüleme • 2 yıl önce

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!
2:41

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 görüntüleme • 5 ay önce

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️
0:33

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Google AI

102,711 görüntüleme • 1 yıl önce