正在加载视频...

视频加载失败

返回首页

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie...

_akhaliq's profile picture

AK

503,476 subscribers

684,259 次观看 • 2 年前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

AK 的头像
AK2 年前

paper page:

AK 的头像
AK2 年前

project page:

XR Multiverse 的头像
XR Multiverse2 年前

Google's warehouse of unused tech

crispyshh 的头像
crispyshh2 年前

@apples_jimmy Text to Mario achieved externally

meowbooks --🩸/acc 的头像
meowbooks --🩸/acc2 年前

that's so cool

Matt Griswold 的头像
Matt Griswold2 年前

Can it make Wolfenstein? If not, why not.

Smoke-away 的头像
Smoke-away2 年前

🔥🔥🔥

Mat 的头像
Mat2 年前

all these papers, no public releases 🫠

Ollin Boer Bohan 的头像
Ollin Boer Bohan2 年前

Demo page with more videos.

相关视频

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →
0:34

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Google DeepMind

1,440,696 次观看 • 1 年前

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

102,408 次观看 • 10 个月前

Today, we're joined by Jack Parker-Holder and Shlomi Fruchter, researchers at Google DeepMind, to discuss the recent release of Genie 3, a model capable of generating “playable” virtual worlds. We dig into the evolution of the Genie project and review the current model’s scaled-up capabilities, including creating real-time, interactive, and high-resolution environments. Jack and Shlomi share their perspectives on what defines a world model, the model's architecture, and key technical challenges and breakthroughs, including Genie 3’s visual memory and ability to handle “promptable world events.” Jack, Shlomi, and Sam share their favorite Genie 3 demos, and discuss its potential as a dynamic training environment for embodied AI agents. Finally, we will explore future directions for Genie research. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 7:11 - What is a world model? 14:49 - Milestones of Genie research 24:32 - Genie 3 27:46 - Challenges 30:07 - Genie 3 examples 33:48 - Model capabilities 35:49 - Key aspects of the model 39:40 - Consistency as an emergent property 42:11 - Promptable word events 47:24 - SIMA agent 50:56 - Limitations 56:08 - Future directions
1:00:31

Today, we're joined by Jack Parker-Holder and Shlomi Fruchter, researchers at Google DeepMind, to discuss the recent release of Genie 3, a model capable of generating “playable” virtual worlds. We dig into the evolution of the Genie project and review the current model’s scaled-up capabilities, including creating real-time, interactive, and high-resolution environments. Jack and Shlomi share their perspectives on what defines a world model, the model's architecture, and key technical challenges and breakthroughs, including Genie 3’s visual memory and ability to handle “promptable world events.” Jack, Shlomi, and Sam share their favorite Genie 3 demos, and discuss its potential as a dynamic training environment for embodied AI agents. Finally, we will explore future directions for Genie research. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 7:11 - What is a world model? 14:49 - Milestones of Genie research 24:32 - Genie 3 27:46 - Challenges 30:07 - Genie 3 examples 33:48 - Model capabilities 35:49 - Key aspects of the model 39:40 - Consistency as an emergent property 42:11 - Promptable word events 47:24 - SIMA agent 50:56 - Limitations 56:08 - Future directions

The TWIML AI Podcast

12,043 次观看 • 9 个月前

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.
1:14

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 次观看 • 3 个月前

The World Model as NEO's Cognitive Core 1X has revealed a major AI development where the NEO humanoid can translate any natural language prompt into robotic action. It demonstrates this capability even for novel tasks, objects, and environments not found in its robot dataset. - the 1X World Model is trained on internet-scale human interaction videos and fine-tuned with robot data to ground its understanding in physics and in NEO's embodiment - from a simple voice or text prompt, the world model generates a visualization of future actions - a built-in inverse dynamics model then translates these into precise motor movements for NEO
1:02

The World Model as NEO's Cognitive Core 1X has revealed a major AI development where the NEO humanoid can translate any natural language prompt into robotic action. It demonstrates this capability even for novel tasks, objects, and environments not found in its robot dataset. - the 1X World Model is trained on internet-scale human interaction videos and fine-tuned with robot data to ground its understanding in physics and in NEO's embodiment - from a simple voice or text prompt, the world model generates a visualization of future actions - a built-in inverse dynamics model then translates these into precise motor movements for NEO

The Humanoid Hub

68,453 次观看 • 4 个月前

Google's Genie 3 was just announced. This is a world model capable of generating fully interactive 3D worlds. This has major implications for video games and giving agents infinite self-play environments.
12:05

Google's Genie 3 was just announced. This is a world model capable of generating fully interactive 3D worlds. This has major implications for video games and giving agents infinite self-play environments.

Matthew Berman

76,291 次观看 • 10 个月前

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

366,858 次观看 • 1 年前

GameFactory Creating New Games with Generative Interactive Videos present GameFactory, a generalizable world model that learns from a small-scale dataset of Minecraft game videos. By leveraging the prior knowledge of a pretrained video diffusion model, it can create new games in an open domain.
1:14

GameFactory Creating New Games with Generative Interactive Videos present GameFactory, a generalizable world model that learns from a small-scale dataset of Minecraft game videos. By leveraging the prior knowledge of a pretrained video diffusion model, it can create new games in an open domain.

AK

70,029 次观看 • 1 年前

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵
2:22

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

Google DeepMind

3,730,944 次观看 • 10 个月前

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
0:34

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

Jack Parker-Holder

2,605,299 次观看 • 1 年前

🎮 AI from Google creates entire worlds in seconds Google DeepMind has unveiled a new AI model called Genie 3, which generates three-dimensional interactive environments based on a simple text prompt. The model creates fully functional virtual worlds — like in a video game — where you can freely move around. The main difference from previous versions: these worlds last not just seconds, but several minutes. That’s enough time to explore, test, or even train another AI.
0:37

🎮 AI from Google creates entire worlds in seconds Google DeepMind has unveiled a new AI model called Genie 3, which generates three-dimensional interactive environments based on a simple text prompt. The model creates fully functional virtual worlds — like in a video game — where you can freely move around. The main difference from previous versions: these worlds last not just seconds, but several minutes. That’s enough time to explore, test, or even train another AI.

NEXTA

41,985 次观看 • 10 个月前

Genie 3 from Google could compress robotics R&D, generate synthetic trajectories at scale then fine tune once on hardware. This is truly a turning point for world models 🌍 — we can now build real-time, fully interactive simulations that run for several minutes and bring any world we can imagine to life. This might be the missing puzzle piece for embodied AGI. ⚡ Real-time engine under the hood During generation the network predicts a fresh frame every 42 milliseconds while looking back over the entire action history. That history grows each step, so the compute graph must cache and retrieve past features fast or the frame rate tanks. The team built a custom attention window that skims for “landmarks” in the latent space, letting the model fetch relevant context quickly enough to hit real-time speed. With Genie 3, environment becomes a latent variable, agents overfit less because benchmark turns into distribution. Some truly wild examples 👇
0:57

Genie 3 from Google could compress robotics R&D, generate synthetic trajectories at scale then fine tune once on hardware. This is truly a turning point for world models 🌍 — we can now build real-time, fully interactive simulations that run for several minutes and bring any world we can imagine to life. This might be the missing puzzle piece for embodied AGI. ⚡ Real-time engine under the hood During generation the network predicts a fresh frame every 42 milliseconds while looking back over the entire action history. That history grows each step, so the compute graph must cache and retrieve past features fast or the frame rate tanks. The team built a custom attention window that skims for “landmarks” in the latent space, letting the model fetch relevant context quickly enough to hit real-time speed. With Genie 3, environment becomes a latent variable, agents overfit less because benchmark turns into distribution. Some truly wild examples 👇

Rohan Paul

16,124 次观看 • 10 个月前

🔥 Pixels won't be rendered but generated. Well, we are there already! Genie 3 from Deepmind: world model that creates interactive, playable environments from a single text prompt! 🧵👇
0:59

🔥 Pixels won't be rendered but generated. Well, we are there already! Genie 3 from Deepmind: world model that creates interactive, playable environments from a single text prompt! 🧵👇

Javi Lopez ⛩️

152,550 次观看 • 10 个月前

One nice thing you can do with an interactive world model, look down and see your footwear ... and if the model understands what puddles are. Genie 3 creation.
0:30

One nice thing you can do with an interactive world model, look down and see your footwear ... and if the model understands what puddles are. Genie 3 creation.

Matt McGill

1,620,315 次观看 • 10 个月前

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.
2:05

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

The Humanoid Hub

20,968 次观看 • 10 个月前

1/ NitroGen: NVIDIA's new image-to-action model! NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. Gaming is a significant factor in AI training. Google DeepMind trained AI early on Starcraft 2, and OpenAI on Dota 2. This new product from NVIDIA is therefore extremely important. Why it matters and how it works:
0:50

1/ NitroGen: NVIDIA's new image-to-action model! NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. Gaming is a significant factor in AI training. Google DeepMind trained AI early on Starcraft 2, and OpenAI on Dota 2. This new product from NVIDIA is therefore extremely important. Why it matters and how it works:

Chubby♨️

55,280 次观看 • 5 个月前

AI agents are about to redefine the internet. The mistake we made with Large Language Models? We let a handful of corporations capture all the value. Action Model is building a different path. By training through our extension, users gain fractional ownership in the Large Action Model, giving them a real stake in the future of AI. When LLMs emerged, the upside flowed to Big Tech. This time, it doesn’t have to. They’re building AI on our data, and keeping the upside for themselves. Community-owned Large Action Model is how we take it back.
0:49

AI agents are about to redefine the internet. The mistake we made with Large Language Models? We let a handful of corporations capture all the value. Action Model is building a different path. By training through our extension, users gain fractional ownership in the Large Action Model, giving them a real stake in the future of AI. When LLMs emerged, the upside flowed to Big Tech. This time, it doesn’t have to. They’re building AI on our data, and keeping the upside for themselves. Community-owned Large Action Model is how we take it back.

Action Model

76,072 次观看 • 3 个月前

Diffusion has shown great promise for generating robot **actions**, can it act as a **world model** to generate the future conditioned on actions? In our work led by han qi Haocheng Yin and in collaboration with Yilun Du, we show a **controllable** action-conditioned video diffusion model can produce photorealistic and (near) physics-accurate future predictions. This ability strengthens the policy via: - ranking different action proposals and selecting the best, or - **visual** trajectory optimization by optimizing the action proposals using gradient ascent. Learn more about Generative Predictive Control (GPC) at:
1:37

Diffusion has shown great promise for generating robot **actions**, can it act as a **world model** to generate the future conditioned on actions? In our work led by han qi Haocheng Yin and in collaboration with Yilun Du, we show a **controllable** action-conditioned video diffusion model can produce photorealistic and (near) physics-accurate future predictions. This ability strengthens the policy via: - ranking different action proposals and selecting the best, or - **visual** trajectory optimization by optimizing the action proposals using gradient ascent. Learn more about Generative Predictive Control (GPC) at:

Heng Yang

38,390 次观看 • 1 年前

🔘 Real-time capabilities Genie 3 is our first world model to allow live interaction, while also improving consistency and realism compared to Genie 2. It can generate dynamic worlds at 720p and 24 FPS, with each frame created in response to user actions.
0:59

🔘 Real-time capabilities Genie 3 is our first world model to allow live interaction, while also improving consistency and realism compared to Genie 2. It can generate dynamic worlds at 720p and 24 FPS, with each frame created in response to user actions.

Google DeepMind

224,367 次观看 • 10 个月前