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。

🍎Thinking with Video towards Law-Grounded Physical Intelligence🍎 🥧Apple-π🥧 is the first benchmark that asks video models to reason through explicit physical laws w/ an auditable test of physical intelligence - Project: - Code:

Ziwei Liu

13,420 subscribers

23,376 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 条评论

ReDig 的头像

ReDig2 个月前

name reminds me of a song “pineapple apple pi”🫡

Julien Active 的头像

Julien Active2 个月前

Multi-law composition is the real tell. Models learn isolated motion patterns but can't chain laws together. That's mimicry, not reasoning.

KP bhoomika 的头像

KP bhoomika2 个月前

benchmarking AI on actual physics laws instead of vibes is the upgrade we needed 💀

相关视频

At Physical Intelligence (π) our mission is to bring general-purpose AI into the physical world. We're excited to show the first step towards this mission - our first generalist model π₀ 🧠 🤖 Paper, blog, uncut videos:

At Physical Intelligence (π) our mission is to bring general-purpose AI into the physical world. We're excited to show the first step towards this mission - our first generalist model π₀ 🧠 🤖 Paper, blog, uncut videos:

Physical Intelligence

566,521 次观看 • 1 年前

Alphabet (Google's parent company) acquired a stake in Physical Intelligence. San Francisco-based Physical Intelligence, an AI and robotics startup, has secured $600 million in fresh funding, pushing its post-money valuation to $5.6 billion. - The round was led by Alphabet's independent growth fund CapitalG. - Existing backers who participated in this round include Lux Capital, Thrive Capital, and Jeff Bezos. - New participants include Index Ventures and T. Rowe Price, among others. Physical Intelligence is building general-purpose AI foundation models and learning algorithms designed to act as the "brain" for robots. Here's their latest π*0.6 model in actio

Alphabet (Google's parent company) acquired a stake in Physical Intelligence. San Francisco-based Physical Intelligence, an AI and robotics startup, has secured $600 million in fresh funding, pushing its post-money valuation to $5.6 billion. - The round was led by Alphabet's independent growth fund CapitalG. - Existing backers who participated in this round include Lux Capital, Thrive Capital, and Jeff Bezos. - New participants include Index Ventures and T. Rowe Price, among others. Physical Intelligence is building general-purpose AI foundation models and learning algorithms designed to act as the "brain" for robots. Here's their latest π*0.6 model in actio

The Humanoid Hub

244,972 次观看 • 10 个月前

AI is evolving towards multimodal fusion and embodied intelligence, transitioning from virtual to physical forms. Vertical industry applications are rapidly being implemented, with equal emphasis on security governance and computing efficiency, ultimately advancing toward the era of Artificial General Intelligence (AGI).

AI is evolving towards multimodal fusion and embodied intelligence, transitioning from virtual to physical forms. Vertical industry applications are rapidly being implemented, with equal emphasis on security governance and computing efficiency, ultimately advancing toward the era of Artificial General Intelligence (AGI).

Nevesof

29,892 次观看 • 8 个月前

On Bloomberg last night, I was asked why Amazon drives more than a third of U.S. e-commerce. It is not because of their storefront. It is not because of their payments. It is not even because of product selection. It is because consumers trust their deliveries. That trust is built on physical infrastructure at scale with intelligence layered on top. And that is what Stord is building for every independent merchant. The most defensible companies in the world combine software intelligence with physical execution. Today, 9 of the 10 largest U.S. companies by revenue operate physical networks at scale. Software alone cannot replicate the outcomes created when you control the movement of physical atoms. That is the physical intelligence layer for commerce. And that is what Stord Labs is built to advance. Deploying AI and robotics against real operational complexity, in the real world, across a vertically integrated network operating at scale. Bloomberg TV

On Bloomberg last night, I was asked why Amazon drives more than a third of U.S. e-commerce. It is not because of their storefront. It is not because of their payments. It is not even because of product selection. It is because consumers trust their deliveries. That trust is built on physical infrastructure at scale with intelligence layered on top. And that is what Stord is building for every independent merchant. The most defensible companies in the world combine software intelligence with physical execution. Today, 9 of the 10 largest U.S. companies by revenue operate physical networks at scale. Software alone cannot replicate the outcomes created when you control the movement of physical atoms. That is the physical intelligence layer for commerce. And that is what Stord Labs is built to advance. Deploying AI and robotics against real operational complexity, in the real world, across a vertically integrated network operating at scale. Bloomberg TV

Sean Henry

1,275,331 次观看 • 4 个月前

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

Jon Hernandez

20,592 次观看 • 7 个月前

Building intelligent embodied agents should address the diverse needs of all people, including those with physical constraints! Yet, this crucial aspect has often been overlooked within embodied AI communities. Our NeurIPS project, Constrained Human-AI Cooperation (CHAIC), seeks to fill this gap by introducing an inclusive embodied social intelligence challenge. Project page: Code:

Building intelligent embodied agents should address the diverse needs of all people, including those with physical constraints! Yet, this crucial aspect has often been overlooked within embodied AI communities. Our NeurIPS project, Constrained Human-AI Cooperation (CHAIC), seeks to fill this gap by introducing an inclusive embodied social intelligence challenge. Project page: Code:

Chuang Gan

18,742 次观看 • 1 年前

AI excels in the virtual world, but acting in the physical world is a whole different challenge. Why is it so hard to get a robot to fetch an egg without freezing? 🤔 Check out our new explainer video on Embodied Intelligence. We discuss the gap between robot "Thinking" and "Acting,"

AI excels in the virtual world, but acting in the physical world is a whole different challenge. Why is it so hard to get a robot to fetch an egg without freezing? 🤔 Check out our new explainer video on Embodied Intelligence. We discuss the gap between robot "Thinking" and "Acting,"

Tongyi Lab

5,634,584 次观看 • 3 个月前

I usually skip benchmark comparisons. They're almost always picked to flatter. But EgoSchema is different. It measures first-person, egocentric video understanding. The AI equivalent of “look through the robot's eyes and tell me what happened.” I spent some time testing Perceptron Mk1 (“Mark One”) on the robotics workflows Perceptron walked me through, and the EgoSchema result suddenly made a lot more sense. Perceptron Mk1 scored 80.60% on it. Gemini 3.1 Flash Lite scored 62.4%. That's a completely different level of understanding. Most frontier models were trained on the internet through text, images, and static content. The physical world works differently. Context lives across time. The critical moment rarely exists in a single frame. And that's exactly where production deployments start mattering. Manufacturing QC. Robotics data pipelines. Security footage. Everything is temporal. Native video reasoning. Temporal grounding. Structured output. Perceptron calls it “Mk1” because it marks the beginning of their closed-model series for physical-world intelligence, and honestly, the name fits. It feels engineered for deployment, not just demos. Feels like one of the first video AI systems being built around how the physical world actually behaves instead of adapting static-image intelligence into video later.

I usually skip benchmark comparisons. They're almost always picked to flatter. But EgoSchema is different. It measures first-person, egocentric video understanding. The AI equivalent of “look through the robot's eyes and tell me what happened.” I spent some time testing Perceptron Mk1 (“Mark One”) on the robotics workflows Perceptron walked me through, and the EgoSchema result suddenly made a lot more sense. Perceptron Mk1 scored 80.60% on it. Gemini 3.1 Flash Lite scored 62.4%. That's a completely different level of understanding. Most frontier models were trained on the internet through text, images, and static content. The physical world works differently. Context lives across time. The critical moment rarely exists in a single frame. And that's exactly where production deployments start mattering. Manufacturing QC. Robotics data pipelines. Security footage. Everything is temporal. Native video reasoning. Temporal grounding. Structured output. Perceptron calls it “Mk1” because it marks the beginning of their closed-model series for physical-world intelligence, and honestly, the name fits. It feels engineered for deployment, not just demos. Feels like one of the first video AI systems being built around how the physical world actually behaves instead of adapting static-image intelligence into video later.

Jaymin Shah

116,573 次观看 • 4 个月前

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

Odyssey

2,187,484 次观看 • 5 个月前

Physical AI for defense and intelligence starts with an accurate model of the world – high-fidelity, geometrically grounded, built for the environments where it actually matters. Today, Niantic Spatial 🌎 is awardable on the Department of War 🇺🇸’s Tradewinds Solutions Marketplace for 3D Reconstruction, our second capability to clear that bar after Visual Positioning, announced earlier this month. Together they deliver two critical layers of the spatial stack: high-fidelity 3D models of contested environments, and precise location within them; a foundation for mission-critical operations that need to visualize and navigate the physical world. The capability is ready. The procurement path is open.

Physical AI for defense and intelligence starts with an accurate model of the world – high-fidelity, geometrically grounded, built for the environments where it actually matters. Today, Niantic Spatial 🌎 is awardable on the Department of War 🇺🇸’s Tradewinds Solutions Marketplace for 3D Reconstruction, our second capability to clear that bar after Visual Positioning, announced earlier this month. Together they deliver two critical layers of the spatial stack: high-fidelity 3D models of contested environments, and precise location within them; a foundation for mission-critical operations that need to visualize and navigate the physical world. The capability is ready. The procurement path is open.

asim ᯅ

14,288 次观看 • 4 个月前

🌩️ Edge AI Network on Solana Captures 10 Million Vehicles Daily 375ai processes real-time highway traffic across 40,000 US billboard locations with 250,000+ mobile contributors, turning the physical world into structured data. NVIDIA edge devices compress 1TB of video into 35MB of insights daily while preserving privacy through local processing. "Cities, enterprises, and governments need real-time intelligence to understand the physical world as it unfolds." Full Interview:

🌩️ Edge AI Network on Solana Captures 10 Million Vehicles Daily 375ai processes real-time highway traffic across 40,000 US billboard locations with 250,000+ mobile contributors, turning the physical world into structured data. NVIDIA edge devices compress 1TB of video into 35MB of insights daily while preserving privacy through local processing. "Cities, enterprises, and governments need real-time intelligence to understand the physical world as it unfolds." Full Interview:

Generation Infinity

181,518 次观看 • 7 个月前

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:

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

1,080,061 次观看 • 3 个月前

ELON MUSK: IT'S INCREDIBLY IMPORTANT FOR AI MODELS TO BE GROUNDED IN REALITY - "Physics is the law, and everything else is a recommendation" - People break human-made laws, but no one breaks the laws of physics - AI must be grounded in reality to ensure it is truthful and accurate - Examples of this necessity: Cars: Must drive safely and correctly. Optimus (Humanoid Robot): Must perform the physical tasks it is asked to do - Adhering to the laws of physics is helpful for ensuring the model is truthful - A somewhat overlooked point: To be really intelligent, AI has to make predictions that are in line with reality

ELON MUSK: IT'S INCREDIBLY IMPORTANT FOR AI MODELS TO BE GROUNDED IN REALITY - "Physics is the law, and everything else is a recommendation" - People break human-made laws, but no one breaks the laws of physics - AI must be grounded in reality to ensure it is truthful and accurate - Examples of this necessity: Cars: Must drive safely and correctly. Optimus (Humanoid Robot): Must perform the physical tasks it is asked to do - Adhering to the laws of physics is helpful for ensuring the model is truthful - A somewhat overlooked point: To be really intelligent, AI has to make predictions that are in line with reality

X Freeze

45,446 次观看 • 10 个月前

Yann LeCun says we're never gonna get to human-level intelligence by just training on text AI must learn from high-bandwidth sensory data like video to build true world models Current models look PhD-smart but mostly regurgitate, with no real understanding "even a cat understands the physical world better"

Yann LeCun says we're never gonna get to human-level intelligence by just training on text AI must learn from high-bandwidth sensory data like video to build true world models Current models look PhD-smart but mostly regurgitate, with no real understanding "even a cat understands the physical world better"

Haider.

138,368 次观看 • 11 个月前

'This is his kind of voluntary community work that he’s doing. He’s giving back.' An 18-year-old boy living with complex physical and mental difficulties is promoting the joy of reading through a creative hide-and-seek project.

'This is his kind of voluntary community work that he’s doing. He’s giving back.' An 18-year-old boy living with complex physical and mental difficulties is promoting the joy of reading through a creative hide-and-seek project.

STV News

16,596 次观看 • 2 年前

Fans have flooded PlayStation’s YouTube and social media posts with demands not to abandon physical media. No matter what Sony uploads, game trailers, PS Plus videos, or hardware announcements they are getting spammed with the same message: “Keep physical games.” The campaign has spread so widely that almost every new PlayStation video is now filled with comments about physical games instead of the actual content.

Fans have flooded PlayStation’s YouTube and social media posts with demands not to abandon physical media. No matter what Sony uploads, game trailers, PS Plus videos, or hardware announcements they are getting spammed with the same message: “Keep physical games.” The campaign has spread so widely that almost every new PlayStation video is now filled with comments about physical games instead of the actual content.

Pirat_Nation 🔴

153,276 次观看 • 2 个月前

OpenAI's Chief Futurist Joshua Achiam breaks with the consensus on takeoff, arguing intelligence hits a physical ceiling and then raw compute decides who wins: "People expect that there's no ceiling for the amount of intelligence that you could have in a model, and they think of recursive self-improvement as this loop that's gonna happen at some point or another. RSI starts happening and model intelligence takes off and it goes to the moon, and they don't see a ceiling." "I think on physical grounds, there's gotta be a maximum amount of computation that you can have per unit volume and energy in the physical universe. And that sort of implies there's a maximum amount of intelligence per unit volume and unit of energy." "If that's the case, eventually, seeing how fast AI model capabilities are increasing right now, eventually everyone hits that saturation point and everyone's got roughly equivalently capable models from a raw intelligence perspective." "The open source frontier lags the closed source frontier by some number of months, but the fact that it's months is crazy. So eventually everyone is probably working with equally maximally capable models, and then it's amount of compute that you're able to throw at a problem that determines who wins." Joshua Achiam

OpenAI's Chief Futurist Joshua Achiam breaks with the consensus on takeoff, arguing intelligence hits a physical ceiling and then raw compute decides who wins: "People expect that there's no ceiling for the amount of intelligence that you could have in a model, and they think of recursive self-improvement as this loop that's gonna happen at some point or another. RSI starts happening and model intelligence takes off and it goes to the moon, and they don't see a ceiling." "I think on physical grounds, there's gotta be a maximum amount of computation that you can have per unit volume and energy in the physical universe. And that sort of implies there's a maximum amount of intelligence per unit volume and unit of energy." "If that's the case, eventually, seeing how fast AI model capabilities are increasing right now, eventually everyone hits that saturation point and everyone's got roughly equivalently capable models from a raw intelligence perspective." "The open source frontier lags the closed source frontier by some number of months, but the fact that it's months is crazy. So eventually everyone is probably working with equally maximally capable models, and then it's amount of compute that you're able to throw at a problem that determines who wins." Joshua Achiam

MTS

60,213 次观看 • 2 个月前

Sam Altman just exposed the greatest delusion in the tech sector. We didn’t invent artificial intelligence. We discovered it. Altman: “I think the discovery of deep learning is closer to discovering an element or a fundamental property of physics than it is a secret technology.” This distinction is everything. If intelligence were just human invention, it would be bound by human limits. Fragile code. Endless debugging. But deep learning as a fundamental property of physics means intelligence is an emergent thermodynamic result. Organize silicon in the right pattern, pump enough energy through it, and cognition mathematically materializes. We’re not writing software anymore. We’re mining the raw physics of intelligence. Altman: “There was such a measurable, beautiful correlation between the resources that go into a model and the intelligence of that model that there was just something fundamental going on here as a scientific principle.” When OpenAI published the scaling laws, they proved something brutal about the nature of the universe itself. Synthetic intelligence is directly proportional to compute. Clean, predictable extraction. Tech monopolies are spending hundreds of billions on physical infrastructure right now because they aren’t guessing. The scaling laws proved you don’t need a million genius engineers to hand-code an artificial brain. Just feed the mathematical principle with more energy. The outcome is already hardcoded into the system. Altman: “Like other scientific frontiers, it is simplifying and becoming more clear over time. And eventually, this recipe will be well understood as a scientific principle.” Right now, training a frontier model looks like highly classified black magic restricted to a handful of apex organizations. But physical laws always trend toward simplification. We’re watching the transition from alchemy to chemistry in real time. Once the core scientific principle of intelligence is fully understood, it no longer requires a trillion-dollar monopoly to execute. The foundational recipe for creating a cognitive agent becomes as widely understood and standardized as the laws of thermodynamics. And when that happens, the barrier to creating intelligence doesn’t just drop. It ceases to exist.

Sam Altman just exposed the greatest delusion in the tech sector. We didn’t invent artificial intelligence. We discovered it. Altman: “I think the discovery of deep learning is closer to discovering an element or a fundamental property of physics than it is a secret technology.” This distinction is everything. If intelligence were just human invention, it would be bound by human limits. Fragile code. Endless debugging. But deep learning as a fundamental property of physics means intelligence is an emergent thermodynamic result. Organize silicon in the right pattern, pump enough energy through it, and cognition mathematically materializes. We’re not writing software anymore. We’re mining the raw physics of intelligence. Altman: “There was such a measurable, beautiful correlation between the resources that go into a model and the intelligence of that model that there was just something fundamental going on here as a scientific principle.” When OpenAI published the scaling laws, they proved something brutal about the nature of the universe itself. Synthetic intelligence is directly proportional to compute. Clean, predictable extraction. Tech monopolies are spending hundreds of billions on physical infrastructure right now because they aren’t guessing. The scaling laws proved you don’t need a million genius engineers to hand-code an artificial brain. Just feed the mathematical principle with more energy. The outcome is already hardcoded into the system. Altman: “Like other scientific frontiers, it is simplifying and becoming more clear over time. And eventually, this recipe will be well understood as a scientific principle.” Right now, training a frontier model looks like highly classified black magic restricted to a handful of apex organizations. But physical laws always trend toward simplification. We’re watching the transition from alchemy to chemistry in real time. Once the core scientific principle of intelligence is fully understood, it no longer requires a trillion-dollar monopoly to execute. The foundational recipe for creating a cognitive agent becomes as widely understood and standardized as the laws of thermodynamics. And when that happens, the barrier to creating intelligence doesn’t just drop. It ceases to exist.

Dustin

38,368 次观看 • 6 个月前

Elon Musk explains why it's incredibly important for AI models to be grounded in reality "Physics is the law, and everything else is a recommendation. People break human-made laws, but no one breaks the laws of physics" AI must be grounded in reality to be truthful and accurate Examples: Cars: Must drive safely and correctly Optimus: Must perform real physical tasks A somewhat overlooked point: To be really intelligent, AI has to make predictions in line with reality (in other words, physics)

Elon Musk explains why it's incredibly important for AI models to be grounded in reality "Physics is the law, and everything else is a recommendation. People break human-made laws, but no one breaks the laws of physics" AI must be grounded in reality to be truthful and accurate Examples: Cars: Must drive safely and correctly Optimus: Must perform real physical tasks A somewhat overlooked point: To be really intelligent, AI has to make predictions in line with reality (in other words, physics)

X Freeze

26,391 次观看 • 6 个月前