Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing Project Eden, a world model research preview from VAST AI Research Project Eden is a persistent, multiplayer world model that fundamentally breaks from existing paradigms by decoupling the underlying world state from visual rendering. Instead of treating the world as a sequence of transient frames, Eden treats it... show more

Tripo

20,513 subscribers

3,389,069 Aufrufe • vor 3 Monaten •via X (Twitter)

Gaming Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

35 Kommentare

Profilbild von Tripo

Tripovor 3 Monaten

Read more:

Profilbild von Tesana - Make games with AI

Tesana - Make games with AIvor 3 Monaten

@VastAIResearch 👀

Profilbild von BPC RiskManager

BPC RiskManagervor 3 Monaten

@VastAIResearch Firstly there is no link to the world, just the video & writeup, and how is this different from secondlife/opensim with an AI plugin? They also decouple worldstate from rendering - since 2005. The comments here are little over-the-top.

Profilbild von ben.

ben.vor 3 Monaten

@VastAIResearch congrats for this launch team :)

Profilbild von Andy Marlow

Andy Marlowvor 3 Monaten

@VastAIResearch Decoupling world state from visual rendering is a massive architectural shift. VAST AI has been building something different for a while 😍

Profilbild von Wesley

Wesleyvor 3 Monaten

@VastAIResearch This is huge! Project Eden's persistent world state + decoupled rendering = true interactive sims, not just videos. Multiplayer persistence and editable worlds could revolutionize agents & games. 🔥 Congrats Tripo & VAST team!

Profilbild von Parul Gautam

Parul Gautamvor 3 Monaten

@VastAIResearch This feels like a big leap from generating scenes to creating actual living worlds.

Profilbild von Sofía Sicilia

Sofía Siciliavor 3 Monaten

@VastAIResearch This feels like a huge step toward actual interactive worlds, not just better video generation. Persistent state + multi-user interaction is where things start getting really interesting.

Profilbild von AI Mastery Guide

AI Mastery Guidevor 3 Monaten

@VastAIResearch Treating the world as a structured evolving environment instead of a sequence of frames changes everything about what you can build on top

Profilbild von z

zvor 3 Monaten

@VastAIResearch the fact that the world exists separately from what you’re actually seeing is kind of breaking my brain ngl. project eden is something else

Profilbild von AiDevCraft

AiDevCraftvor 3 Monaten

The decoupling reframes the hard problem from "temporal consistency across frames" to "consistency in the underlying state schema" — easier to guarantee in principle, but only if the state representation is rich enough that two viewpoints disagree the same way real cameras would. The interesting failure mode is when rendering quietly papers over state ambiguity that should have been visible; everything feels coherent until two users compare notes on the same event.

Profilbild von Sebastian Buzdugan

Sebastian Buzduganvor 3 Monaten

@VastAIResearch i've seen persistent worlds drift after reconnects, authoritative state and rollback matter more than rendering

Profilbild von Rishabh

Rishabhvor 3 Monaten

@VastAIResearch The idea of a shared, persistent AI-generated world is kind of mind-blowing.

Profilbild von Miguel Ángel | GptZone

Miguel Ángel | GptZonevor 3 Monaten

@VastAIResearch Los modelos multijugador con esta renderización son increíbles

Profilbild von ZenithAi

ZenithAivor 3 Monaten

@VastAIResearch Not frames. A living world. Eden just redefined what "world model" means

Profilbild von carpe

carpevor 3 Monaten

@VastAIResearch persistent + multiplayer? this is game changer fr

Profilbild von RAVI KUMAR SAHU

RAVI KUMAR SAHUvor 3 Monaten

@VastAIResearch The description of its fundamental departure from existing paradigms, particularly in its decoupling of world state from visual rendering, presents a truly compelling vision for future world models

Profilbild von Chidanand Tripathi

Chidanand Tripathivor 3 Monaten

@VastAIResearch A world model that remembers and evolves is a fascinating concept

Profilbild von Don Quijote de la IA

Don Quijote de la IAvor 3 Monaten

@VastAIResearch Espectacular proyecto con infinitas posibilidades

Profilbild von Priyank Ahuja

Priyank Ahujavor 3 Monaten

@VastAIResearch The idea of a shared, persistent AI-generated world is kind of mind-blowing.

Profilbild von Aravind

Aravindvor 3 Monaten

@VastAIResearch So we might have dynamic interactive worlds if this hits cool.

Profilbild von Spenser Dickerson

Spenser Dickersonvor 3 Monaten

@VastAIResearch Interesting!

Profilbild von Aina Ai | Tools & Updates

Aina Ai | Tools & Updatesvor 3 Monaten

@VastAIResearch Awesome

Profilbild von Sufyan Maan, M.Eng

Sufyan Maan, M.Engvor 3 Monaten

@VastAIResearch That’s great, no longer just rendering for a long time, congrats team!!

Profilbild von D-Coder

D-Codervor 3 Monaten

@VastAIResearch The persistence part is what makes Project Eden so interesting.

Profilbild von Theinfralab

Theinfralabvor 3 Monaten

@VastAIResearch The persistence and consistency here are what make this truly exciting.

Profilbild von learnbydoingwithsteven数能生智

learnbydoingwithsteven数能生智vor 3 Monaten

@VastAIResearch Separating persistent world state from visual rendering is a useful design choice for world models. It should make consistency, multiplayer interaction, and downstream simulation easier to evaluate.

Profilbild von Awa K. Penn

Awa K. Pennvor 3 Monaten

@VastAIResearch This is a huge one

Profilbild von Aaliya

Aaliyavor 3 Monaten

@VastAIResearch A persistent world changes everything

Profilbild von Pradeep Pandey

Pradeep Pandeyvor 3 Monaten

@VastAIResearch Project Eden feels closer to simulation than traditional generative AI.

Profilbild von Ege

Egevor 3 Monaten

@VastAIResearch 👀

Profilbild von DrewOnAI

DrewOnAIvor 3 Monaten

@VastAIResearch finally a world model that doesn't just hallucinate pixels but actually simulates reality this is the kind of tech i've been waiting for

Profilbild von Olivia

Oliviavor 3 Monaten

@VastAIResearch Love

Profilbild von Zayan

Zayanvor 3 Monaten

@VastAIResearch That's amazing one

Profilbild von karIA

karIAvor 3 Monaten

@VastAIResearch this is another level

Ähnliche Videos

Agentic Real2Sim is an interesting take on world modeling. Instead of learning physics directly from videos, it lets a Vision-Language Agent reconstruct a physics simulator from a single real-world video. The result is an editable, executable world model that can be queried, simulated, and improved.

Agentic Real2Sim is an interesting take on world modeling. Instead of learning physics directly from videos, it lets a Vision-Language Agent reconstruct a physics simulator from a single real-world video. The result is an editable, executable world model that can be queried, simulated, and improved.

Robots Digest 🤖

12,075 Aufrufe • vor 2 Monaten

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇

Keunhong Park

15,823 Aufrufe • vor 11 Monaten

Introducing Starchild-1 from Odyssey, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear. Starchild-1 represents a big step towards a general-purpose world simulator.

Introducing Starchild-1 from Odyssey, the first ever real-time multimodal world model. This a model that can generate interactive simulations of the world that you can—for the first time ever—hear. Starchild-1 represents a big step towards a general-purpose world simulator.

Oliver Cameron

246,755 Aufrufe • vor 4 Monaten

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.

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 Aufrufe • vor 6 Tagen

In our research lab, we are building “real-time dreaming” - the ability to generate fully playable video worlds prompted from any text or image. Our real-time, action conditioned world model (currently running internally at 16fps at 832x480p) is trained on a combination of data, including proprietary Roblox 3D avatar/world interaction data. World models are different from multiplayer engines in that they store state and memory in video latents. Roblox is multiplayer, and we are actively researching optimal ways to simultaneously store state for thousands of players, and keep them in sync with their environment. Our world model leverages database technology which stores all user interactions on Roblox in a vector format that can be used to re-render video and interaction from any camera angle. We see several immediate uses for our Roblox world model. We will use it side-by-side text, image and video prompts as a way to launch auto-generation of immersive worlds. In Roblox Studio, a creator could walk around and use prompts to “paint” a world and then convert it into a 3D representation or direct to Roblox native as a way for many people to play simultaneously. All of this comes alive as we explore the notion of a “Dream Theater” - where one user is dreaming, while others watch and prompt them. 2/4

Roblox

4,412,533 Aufrufe • vor 7 Monaten

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.

AVALON

65,456 Aufrufe • vor 7 Monaten

Robot actions can be represented as motion in pixel space. NVIDIA Research introduces Hydra-0, a generalist world model conditioned on action flow: image-plane trajectories that enable one model to learn across human hands, handheld grippers, single-arm robots and bimanual systems. Explore the project 📄

Robot actions can be represented as motion in pixel space. NVIDIA Research introduces Hydra-0, a generalist world model conditioned on action flow: image-plane trajectories that enable one model to learn across human hands, handheld grippers, single-arm robots and bimanual systems. Explore the project 📄

NVIDIA Robotics

62,886 Aufrufe • vor 21 Tagen

Introducing General World Models. We believe the next major advancement in AI will come from systems that understand the visual world and its dynamics, which is why we’re starting a new long-term research effort around general world models. Learn more:

Introducing General World Models. We believe the next major advancement in AI will come from systems that understand the visual world and its dynamics, which is why we’re starting a new long-term research effort around general world models. Learn more:

Runway

714,491 Aufrufe • vor 2 Jahren

Most AI is built to replace humans. We're building AI to understand them. Introducing Atypica's Subjective World Model. A foundation for understanding how people express themselves, tell their stories, make decisions, and behave under real-world constraints. Not just what users say — but why they choose, hesitate, and act. It powers AI Research, AI Personas, AI Panels, and AI Interviews, helping teams turn user research from a quarterly project into a permanent capability. Watch the video to see how it works and what teams are already building with Atypica. Start to explore this AI-native consumer research platform from here:

Most AI is built to replace humans. We're building AI to understand them. Introducing Atypica's Subjective World Model. A foundation for understanding how people express themselves, tell their stories, make decisions, and behave under real-world constraints. Not just what users say — but why they choose, hesitate, and act. It powers AI Research, AI Personas, AI Panels, and AI Interviews, helping teams turn user research from a quarterly project into a permanent capability. Watch the video to see how it works and what teams are already building with Atypica. Start to explore this AI-native consumer research platform from here:

atypica.AI

28,221 Aufrufe • vor 1 Monat

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!):

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 Aufrufe • vor 1 Jahr

Project Aria is a research program helping Meta unlock new possibilities of how we connect with and experience the world through AR and AI. 📺Watch the full tutorial from #CVPR2022 to learn how Project Aria will advance machine perception and AI research:

Project Aria is a research program helping Meta unlock new possibilities of how we connect with and experience the world through AR and AI. 📺Watch the full tutorial from #CVPR2022 to learn how Project Aria will advance machine perception and AI research:

Meta Open Source

14,720 Aufrufe • vor 3 Jahren

Introducing Stand’s World Model, a physics-native frontier model for the built environment. This is how we help the world survive catastrophe: by computing how physical force acts on a structure, protecting property from fire, wind, flood, or earthquake.

Introducing Stand’s World Model, a physics-native frontier model for the built environment. This is how we help the world survive catastrophe: by computing how physical force acts on a structure, protecting property from fire, wind, flood, or earthquake.

Dan Preston

14,118 Aufrufe • vor 4 Monaten

Turn any world model from World Labs into a multi-user space for exploration and collaboration with FRAME. Voice chat, embodied AI agents, and tons more you can layer on top of the model foundation. This took all of 10 seconds to get going. The metaverse is so back. 😄

Turn any world model from World Labs into a multi-user space for exploration and collaboration with FRAME. Voice chat, embodied AI agents, and tons more you can layer on top of the model foundation. This took all of 10 seconds to get going. The metaverse is so back. 😄

Gabriel Baker

21,641 Aufrufe • vor 1 Jahr

What if we can simulate an *interactive 3D world*, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

What if we can simulate an interactive 3D world, from a single image, in the wild, in real time? Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions. 🌐 from Stanford University NVIDIA

Wenlong Huang

277,714 Aufrufe • vor 8 Monaten

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!

World Labs

341,775 Aufrufe • vor 11 Monaten

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Can 1,000 real-world 3D scenes make a state-of-the-art model better? At OVER Research, we tested it by fine-tuning R3, a state-of-the-art streaming 3D reconstruction model, on roughly 1,000 scenes from the OVER dataset. The result: 25% lower trajectory error on our real-world environments compared to the deployed public checkpoint. And we did it using only 1,000 scenes, the same open dataset anyone can download for free, out of the 285,000+ real-world 3D scenes OVER has today. Read the full OVER Research publication: Download the 1,000-scene dataset on Hugging Face:

Over the Reality 🌐

34,651 Aufrufe • vor 28 Tagen

Sam Altman says OpenAI's new Deep Research AI agent powered by their o3 model can do "a single-digit percentage of all economically valuable tasks in the world" and this step into synthesizing knowledge will soon be followed by agents that can invent new knowledge

Sam Altman says OpenAI's new Deep Research AI agent powered by their o3 model can do "a single-digit percentage of all economically valuable tasks in the world" and this step into synthesizing knowledge will soon be followed by agents that can invent new knowledge

Tsarathustra

178,363 Aufrufe • vor 1 Jahr

"We are moving out of the age of materialism and into the age of VIBRATION - from a world that measured reality by what could be touched, into an era, shaped by what can be FELT." 852Hz - The Awakener. Known as the frequency of INTUITION.

"We are moving out of the age of materialism and into the age of VIBRATION - from a world that measured reality by what could be touched, into an era, shaped by what can be FELT." 852Hz - The Awakener. Known as the frequency of INTUITION.

WhatdoIknow

37,758 Aufrufe • vor 10 Monaten

The World Of Rao Bahadhur • Its Different • ⁠Story lo Dhammundi • ⁠Ippati Varaku chudani Visual • ⁠A story that will resonate to anyone and everyone from any corner of the world Team #RaoBahadhur About The World Of Rao Bahadhur #SatyaDev & #VenkateshMaha will be delivering a New Telugu Cinema To World #RaoBahadhur From July 3rd Satya Dev Venkatesh Maha

The World Of Rao Bahadhur • Its Different • ⁠Story lo Dhammundi • ⁠Ippati Varaku chudani Visual • ⁠A story that will resonate to anyone and everyone from any corner of the world Team #RaoBahadhur About The World Of Rao Bahadhur #SatyaDev & #VenkateshMaha will be delivering a New Telugu Cinema To World #RaoBahadhur From July 3rd Satya Dev Venkatesh Maha

Thyview

53,568 Aufrufe • vor 2 Monaten

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

World models — action-conditioned predictive models of the environment — are an exciting are of research for robots that can be useful both for training and for test-time compute. But video-based world models waste a lot of predictive power on reconstructing pixels, which makes model and data requirements much higher and limits how far out into the future their predictions remain viable. Instead, what if we learned a purely semantic world model, one which predicts which properties will be true about the world after a sequence of actions, without reconstructing the whole images? Jacob Berg tells us more. Watch Episode #53 of RoboPapers now, with Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

39,322 Aufrufe • vor 9 Monaten