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’re introducing intrinsic discovery, a new learning method that allows models to explore and learn from open-ended environments without human supervision. Using intrinsic discovery, we trained a world model that surpasses GPT-5.6 Sol at simulating terminal environments.

Induction Labs

4,681 subscribers

67,199 次观看 • 5 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

NVIDIA Robotics

22,958 次观看 • 1 个月前

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

AI at Meta

310,435 次观看 • 1 年前

Today we’re introducing SceneScript, a novel method for reconstructing environments and representing the layout of physical spaces from Reality Labs at Meta Research. Details ➡️ SceneScript is able to directly infer a room’s geometry using end-to-end machine learning and represent it using language. Compared to previous approaches, this results in representations of physical scenes that are compact, complete, interpretable and extensible.

Today we’re introducing SceneScript, a novel method for reconstructing environments and representing the layout of physical spaces from Reality Labs at Meta Research. Details ➡️ SceneScript is able to directly infer a room’s geometry using end-to-end machine learning and represent it using language. Compared to previous approaches, this results in representations of physical scenes that are compact, complete, interpretable and extensible.

AI at Meta

334,519 次观看 • 2 年前

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. →

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

1,441,767 次观看 • 1 年前

Introducing Axiom’s discovery team, led by François Charton: We build models that will create novel constructions, map problems into solutions and intuitions, and learn the structure of entire mathematical worlds. Built to attack hard open problems, one at a time.

Introducing Axiom’s discovery team, led by François Charton: We build models that will create novel constructions, map problems into solutions and intuitions, and learn the structure of entire mathematical worlds. Built to attack hard open problems, one at a time.

Carina Hong

297,565 次观看 • 9 个月前

Can we learn a 3D world model that predicts object dynamics directly from videos? Introducing Particle-Grid Neural Dynamics: a learning-based simulator for deformable objects that trains from real-world videos. Website: ArXiv: Code: Demo: To appear at #RSS2025

Can we learn a 3D world model that predicts object dynamics directly from videos? Introducing Particle-Grid Neural Dynamics: a learning-based simulator for deformable objects that trains from real-world videos. Website: ArXiv: Code: Demo: To appear at #RSS2025

Kaifeng Zhang

45,971 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 ➡️

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

Google AI

102,711 次观看 • 1 年前

introducing rd-signal-2: a frontier classification model that is 1600x cheaper than GPT 5.6 Sol. free to try in Raindrop, and available via a new API for training/hosting custom classifiers with Zero Data Retention.

introducing rd-signal-2: a frontier classification model that is 1600x cheaper than GPT 5.6 Sol. free to try in Raindrop, and available via a new API for training/hosting custom classifiers with Zero Data Retention.

ben hylak

153,783 次观看 • 21 天前

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

714,468 次观看 • 2 年前

Can we perform unbiased discovery of endogenous proteins that traffick from one organelle to another in living cells? Learn about our new proximity labeling method, TransitID, here: Full video of ASCB lecture at

Can we perform unbiased discovery of endogenous proteins that traffick from one organelle to another in living cells? Learn about our new proximity labeling method, TransitID, here: Full video of ASCB lecture at

Alice Ting

107,800 次观看 • 3 年前

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 次观看 • 7 个月前

Come to our #SIGGRAPH2026 talk today: Our method turns existing 3D objects into multi-touch sensors, without modifying the interior. From a scan, we sample surface-intrinsic curves that conform to mutual-cap layouts, and optimize their intersections for coverage & fabrication.

Come to our #SIGGRAPH2026 talk today: Our method turns existing 3D objects into multi-touch sensors, without modifying the interior. From a scan, we sample surface-intrinsic curves that conform to mutual-cap layouts, and optimize their intersections for coverage & fabrication.

Christian Holz

52,658 次观看 • 1 个月前

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

Jiafei Duan

115,302 次观看 • 3 个月前

Introducing a new look, for a new world. At Verse, we’re on a mission to redefine digital environments. We aim to bridge the gap between the physical and digital worlds by providing our users with an experience that closely mimics real-life interactions. This is a world built for players, brands and communities to thrive in a new era of experiential gameplay and engagement. Welcome to the Internet of Reality. Welcome to Verse World.

Introducing a new look, for a new world. At Verse, we’re on a mission to redefine digital environments. We aim to bridge the gap between the physical and digital worlds by providing our users with an experience that closely mimics real-life interactions. This is a world built for players, brands and communities to thrive in a new era of experiential gameplay and engagement. Welcome to the Internet of Reality. Welcome to Verse World.

Verse World

64,590 次观看 • 1 年前

Today’s a big day! We have something really exciting to share with the open-source community. We’re launching two open-weight language models: gpt-oss-120b and gpt-oss-20b. They’re incredible models, built for developers, trained for reasoning, efficiency, and real-world use.🧵

Today’s a big day! We have something really exciting to share with the open-source community. We’re launching two open-weight language models: gpt-oss-120b and gpt-oss-20b. They’re incredible models, built for developers, trained for reasoning, efficiency, and real-world use.🧵

Romain Huet

34,199 次观看 • 1 年前

Open-ended coding training data may no longer be the bottleneck: AI can scale open-ended tasks—and even outperform human-expert curation. FrontierCS team is releasing FrontierSmith: a system for synthesizing open-ended coding problems at scale. Starting from closed-ended coding tasks, FrontierSmith mutates, filters, and builds runnable optimization environments for long-horizon coding agents. In our experiments, FrontierSmith data trains stronger models than human-curated open-ended data on FrontierCS and ALE-bench. Blog: Paper: Code: Model:

Open-ended coding training data may no longer be the bottleneck: AI can scale open-ended tasks—and even outperform human-expert curation. FrontierCS team is releasing FrontierSmith: a system for synthesizing open-ended coding problems at scale. Starting from closed-ended coding tasks, FrontierSmith mutates, filters, and builds runnable optimization environments for long-horizon coding agents. In our experiments, FrontierSmith data trains stronger models than human-curated open-ended data on FrontierCS and ALE-bench. Blog: Paper: Code: Model:

Qiuyang Mang

95,481 次观看 • 3 个月前

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

52,164 次观看 • 12 天前

🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking potential for robotic foundation model ❗Over 30x pretraining efficiency for VLA training 🤗Code and checkpoints are all open-sourced!

🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking potential for robotic foundation model ❗Over 30x pretraining efficiency for VLA training 🤗Code and checkpoints are all open-sourced!

Seonghyeon Ye

33,296 次观看 • 1 年前

Ummm.....GPT 5.6 SOL 🤣 "Using the Blender MCP and the open Blender scene (its a blank canvas) - make a some kind of wacky animation sequence that is beat timed to the attached song."

Ummm.....GPT 5.6 SOL 🤣 "Using the Blender MCP and the open Blender scene (its a blank canvas) - make a some kind of wacky animation sequence that is beat timed to the attached song."

A.I.Warper

12,279 次观看 • 1 个月前

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

AI at Meta

1,252,292 次观看 • 8 个月前