正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We trained a graph-native AI, then let it reason for days, forming a dynamic relational world model on its own - no pre-programming. Emergent hubs, small-world properties, modularity, & scale-free structures arose naturally. The model then exploited compositional reasoning & uncovered uncoded properties from deep synthesis: Materials with memory,... show more

Markus J. Buehler

20,650 subscribers

359,512 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

12 条评论

benferrum - e/jounce 的头像

benferrum - e/jounce1 年前

Hello sir, is there a paper/code available?

Markus J. Buehler 的头像

Markus J. Buehler1 年前

Yes - here it is:

InterSystems Developers 的头像

InterSystems Developers1 年前

📺 Watch this #video to learn how #OpenSource vs. proprietary #AI models compare one to another. We explore how proprietary models dominate leaderboards like Chatbot Arena, but open-source models are quickly catching up. Plus, we discuss how businesses can start with proprietary models and transition to open-source alternatives over time 👇 Fit AI into your development strategy!

Leonidas Pitsoulis 的头像

Leonidas Pitsoulis1 年前

very interesting work, exciting to see graph reasoning as a paradigm

Markus J. Buehler 的头像

Markus J. Buehler1 年前

Thanks @LPitsoulis !

Ryan Freel 的头像

Ryan Freel1 年前

For the normies imagine you build a machine to organize your sock drawer, but instead of just sorting socks, it spends a few days thinking and suddenly figures out physics, biology, and self-repairing materials all on its own. You didn’t program it to do that. It just happened.

Ali Ihsan Nergiz 的头像

Ali Ihsan Nergiz1 年前

Interesting project as always Markus, really loved the graphics around it. It kind of reminds evolutional process

Markus J. Buehler 的头像

Markus J. Buehler1 年前

Thank you @aihsannergiz !

Brian Hershey 的头像

Brian Hershey1 年前

This is next level proof of concept Markus, you kinda shifted my gears with this one 🙏

Markus J. Buehler 的头像

Markus J. Buehler1 年前

Thanks 😀 we were blown away by this result also!

👾Moritz Rietschel 的头像

👾Moritz Rietschel1 年前

what did you use grok for? the graphics?

Markus J. Buehler 的头像

Markus J. Buehler1 年前

Yes, the 3D graphics - to visualize how the graphs formed over the thinking period evolve.

相关视频

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

Hongyu Li

105,628 次观看 • 10 个月前

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Robot Learning needs 4D world models! Robot Learning needs 4D world models! Robot Learning needs 4D world models! We introduce TesserAct, a 4D embodied world model that can simulate how agents interact with the 3D world over time! We achieve this by simply extending a pre-trained 2D video generation model to jointly predict RGB, depth, and surface normals. It enables: 1️⃣ Much better policy learning in the wild 2️⃣ Temporal + spatial coherence in 4D dynamic prediction 3️⃣ Novel view synthesis for embodied scenes Code: Paper Link: Project page:

Chuang Gan

43,265 次观看 • 1 年前

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

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 • 6 个月前

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran MiniMax (official) M3 locally with Parallax, right on our desk. Then GenericAgent took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran MiniMax (official) M3 locally with Parallax, right on our desk. Then GenericAgent took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

Gradient

147,197 次观看 • 1 个月前

🚨 AI just crossed into reality. A single human eye reflects an entire AI-generated world — futuristic cities, robots, and digital landscapes forming in real time. We are no longer imagining the future. We are actively creating it. Made with AI video generation (Kling model) on Yapper “This is not the future. It’s now.”

🚨 AI just crossed into reality. A single human eye reflects an entire AI-generated world — futuristic cities, robots, and digital landscapes forming in real time. We are no longer imagining the future. We are actively creating it. Made with AI video generation (Kling model) on Yapper “This is not the future. It’s now.”

Mimu | AI Tools & News

72,897 次观看 • 3 个月前

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

#WATCH | Bengaluru, Karnataka: Co-founder, Sarvam AI, Pratyush Kumar says, "... It's been three years now. We started off building on top of the Llama model, which was the best open model at that time. Sarvam was the only company outside, or maybe in Asia, that contributed to the Llama 3 Series. We understood how to add language skills into models, and Llama 3 was reasonable in Indian languages. When the first set of GPUs arrived in India, we pre-trained from scratch a 2-billion model and worked with Infosys to make it useful for IT services. Then we recognised the importance of scaling up reinforcement learning and built a reasoning model called Sarvam M on top of Mistral's small model. Over the last year, we pre-trained from scratch in India on 4,000 Hopper Series GPUs a 100-billion-plus-parameter model..."

ANI

162,564 次观看 • 8 天前

“ xAI team is currently working heavily on coding models. Right now, the main focus is training a specialized coding model that will be both fast and smart. I believe we’ll share it with you guys in a few weeks. That’s exciting. Second ,after coding, we all see that the main weakness of Grok 4 is its multimodal capabilities. In fact, it was so bad that Grok was effectively looking at the world while squinting through glass trying to see blurry features and make sense of them. The most immediate improvement we’re stepping on with the next generation pre trained model is huge gains in image understanding, video understanding, and audio. Right now, the model can hear and see the world just like any of you. And with all the tools and other agents it can talk to, we’re going to see a huge unlock for many different application layers once multimodal agents arrive.” — xAI Team

“ xAI team is currently working heavily on coding models. Right now, the main focus is training a specialized coding model that will be both fast and smart. I believe we’ll share it with you guys in a few weeks. That’s exciting. Second ,after coding, we all see that the main weakness of Grok 4 is its multimodal capabilities. In fact, it was so bad that Grok was effectively looking at the world while squinting through glass trying to see blurry features and make sense of them. The most immediate improvement we’re stepping on with the next generation pre trained model is huge gains in image understanding, video understanding, and audio. Right now, the model can hear and see the world just like any of you. And with all the tools and other agents it can talk to, we’re going to see a huge unlock for many different application layers once multimodal agents arrive.” — xAI Team

Apurv Kochara

88,142 次观看 • 5 个月前

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.

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

11,641 次观看 • 2 个月前

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.

AK

161,478 次观看 • 3 年前

We set out to collect 10M hours of on-embodiment data as a starting point for robotics models, but couldn’t find a robot reliable enough at a price that made it possible. So, we built one. Meet Pandroid: an accessible hardware platform for AI. Small enough to safely experiment with, durable enough to run in fleets. Connect it to any model or coding agent over SSH to let it interact with the world. Join the waitlist:

We set out to collect 10M hours of on-embodiment data as a starting point for robotics models, but couldn’t find a robot reliable enough at a price that made it possible. So, we built one. Meet Pandroid: an accessible hardware platform for AI. Small enough to safely experiment with, durable enough to run in fleets. Connect it to any model or coding agent over SSH to let it interact with the world. Join the waitlist:

Pantograph

118,847 次观看 • 2 天前

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

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

@levelsio

119,210 次观看 • 1 年前

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

Om Patel

29,606 次观看 • 1 个月前

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,812 次观看 • 9 个月前

The cool thing about talking with Bernt is that he isn’t just a robotics CEO, he’s a deep AI thinker who’s been obsessed with this for decades. It's obvious to me that this is his life's purpose. While most robotic labs are chasing narrow, pre-programmed behaviors, 1X built a dynamics-first world model trained on video + robot sensors. It lets NEO generalize to completely new tasks out of the box, and get smarter through every failure - the same way humans do. Bernt says NEO doesn’t need to have seen every chore. It needs a World Model with enough human experience to imagine what should happen, a body dexterous enough to attempt it, and a real-world feedback loop sharp enough to correct it. That’s how we go from task automation to general-purpose labor.

The cool thing about talking with Bernt is that he isn’t just a robotics CEO, he’s a deep AI thinker who’s been obsessed with this for decades. It's obvious to me that this is his life's purpose. While most robotic labs are chasing narrow, pre-programmed behaviors, 1X built a dynamics-first world model trained on video + robot sensors. It lets NEO generalize to completely new tasks out of the box, and get smarter through every failure - the same way humans do. Bernt says NEO doesn’t need to have seen every chore. It needs a World Model with enough human experience to imagine what should happen, a body dexterous enough to attempt it, and a real-world feedback loop sharp enough to correct it. That’s how we go from task automation to general-purpose labor.

Roberto Nickson

26,039 次观看 • 2 个月前

This is something no other AI and no other car company can do right now, except Grok, fully integrated with FSD (Supervised) v14.2.25. Today, I gave it a wild, real-world task: • Drive to Apple HQ • Then Tesla Engineering HQ • Then a Warriors game at Chase Center SF • Then the beach • Then Asian dinner It got it all ready from the beginning. Mid-route I said I really needed to use the bathroom! It added it as the first stop. Then I added a Tesla Supercharger on the fly for after the Warriors game. It added it. AND stopped for grandparents and baby crossing the street. Then I asked for the weather and exactly how much I should $ budget for the entire day. No friction. No talking back. Just getting it done insanely fast. It just handled it all naturally, intelligently, all in real time. Better than any driver, for sure… This is reasoning + autonomy + AI + real life, all working beautifully in synch. No other car, AI, is close to this capability imo. This is a MAJOR update. I honestly feel if this was any other company, they would’ve had a whole event just to showcase this feature.

This is something no other AI and no other car company can do right now, except Grok, fully integrated with FSD (Supervised) v14.2.25. Today, I gave it a wild, real-world task: • Drive to Apple HQ • Then Tesla Engineering HQ • Then a Warriors game at Chase Center SF • Then the beach • Then Asian dinner It got it all ready from the beginning. Mid-route I said I really needed to use the bathroom! It added it as the first stop. Then I added a Tesla Supercharger on the fly for after the Warriors game. It added it. AND stopped for grandparents and baby crossing the street. Then I asked for the weather and exactly how much I should $ budget for the entire day. No friction. No talking back. Just getting it done insanely fast. It just handled it all naturally, intelligently, all in real time. Better than any driver, for sure… This is reasoning + autonomy + AI + real life, all working beautifully in synch. No other car, AI, is close to this capability imo. This is a MAJOR update. I honestly feel if this was any other company, they would’ve had a whole event just to showcase this feature.

Teslaconomics

258,178 次观看 • 7 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.

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

367,110 次观看 • 1 年前

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a declaration form Output: 736 tokens · Input: 1,847 tokens · Time: ~31s The model analyzed both inputs, streamed its reasoning, and then called three tools: write_field for text fields, mark for Yes/No checkboxes, and sign for the signature and date. It extracted the required information, mapped it to the correct fields and completed the form without any manual input

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a declaration form Output: 736 tokens · Input: 1,847 tokens · Time: ~31s The model analyzed both inputs, streamed its reasoning, and then called three tools: write_field for text fields, mark for Yes/No checkboxes, and sign for the signature and date. It extracted the required information, mapped it to the correct fields and completed the form without any manual input

atomic.chat

109,369 次观看 • 1 个月前

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.

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 次观看 • 6 个月前

The most powerful AI model on earth was alive for 3 days then the US government turned it off. for everyone. on the planet. Anthropic launched Claude Fable 5 on june 9th. their best model ever. june 12th: the Commerce Department issued an export control order blocking foreign nationals Anthropic couldn’t filter foreign users in real time so they shut it down. worldwide. in hours. including for their own employees the irony: Anthropic begged for regulation. sat with the Pope. donated millions for AI rules… the government regulated them.. by killing their best product overnight the most powerful AI in the world has an off switch?? and the company doesn’t hold it first time in history a government force-killed a PUBLIC AI model it won’t be the last.

The most powerful AI model on earth was alive for 3 days then the US government turned it off. for everyone. on the planet. Anthropic launched Claude Fable 5 on june 9th. their best model ever. june 12th: the Commerce Department issued an export control order blocking foreign nationals Anthropic couldn’t filter foreign users in real time so they shut it down. worldwide. in hours. including for their own employees the irony: Anthropic begged for regulation. sat with the Pope. donated millions for AI rules… the government regulated them.. by killing their best product overnight the most powerful AI in the world has an off switch?? and the company doesn’t hold it first time in history a government force-killed a PUBLIC AI model it won’t be the last.

Mika

49,171 次观看 • 1 个月前