Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Most video-action robot models are a content-creation video generator with an action module attached. LingBot-VA 2.0 from Robbyant, a video-action foundation model, throws that starting point out and trains the whole stack natively for control. And it runs closed-loop at a peak 225 Hz. It's so important because A... robot cannot move responsively when its controller pauses to imagine the next few frames. LingBot-VA 2.0 predicts during execution, then corrects using each real observation. And it carries only about 13B video parameters while activating roughly 1.9B per token. Bigger robot models usually mean slower reactions, creating a direct conflict between intelligence and control. LingBot-VA 2.0 is trained from scratch for robot control rather than adapted from a video generator built for content creation. Robbyant, an embodied AI company under Ant Group, built it to learn how scenes change under actions, predict what should happen next, and turn those predictions into real-time robot movements. Most video-action systems inherit a tokenizer and video backbone trained mainly to reproduce visual appearance. LingBot-VA 2.0 rebuilds both parts around physical control. Its semantic visual-action tokenizer maps observations toward features from a frozen vision foundation model and learns compact latent actions from frame-to-frame changes using self-supervised inverse and forward dynamics. Unlabeled web video can therefore carry action-relevant training signals without robot action labels. The policy is causal from the start, so every prediction can use only past observations. Its sparse Mixture-of-Experts video backbone has about 13B total parameters, while about 1.9B are active per token, keeping the compute lower during each step. A high-level vision-language planner breaks long tasks into smaller instructions, while the low-level video-action policy handles continuous movement. Foresight Reasoning predicts future visual states while the robot is already acting, then replaces imagined states with every new real observation. Combined with few-step distillation and systems acceleration, the paper reports a peak asynchronous execution frequency of 225 Hz. The model adapts from 10–15 demonstrations, transfers across robot embodiments, and handles some new tasks zero-shot. In the paper’s own evaluations, it reaches 93.6 average on RoboTwin 2.0 and reports stronger real-world results than LingBot-VA and π0.5 across the tested tasks. 🧵 1.show more

Rohan Paul

152,898 subscribers

10,926 görüntüleme • 2 gün önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

46,962 görüntüleme • 5 ay önce

🦾 From seeing to doing. We're closing the loop between video prediction and real-world action. On the final day of Robbyant Open Source Week, we bring you LingBot-VA—the world's first causal video-action world model for generalist robot control. 🔥 Key Highlights: 🤖 Predicts & Acts: A single model generates both future video and the actions to make it real. 🧠 Remembers the Past: True long-term memory for complex, sequential tasks. ⚡ Learns in a Snap: Masters new skills with just 30-50 real-world demos. The result? 📈 SOTA on RoboTwin (92.9%) and LIBERO (98.5%), +20% over π0.5 on challenging real-world long-horizon & high-precision tasks. More below 👇 #AI #Robotics #EmbodiedAI #WorldModel #OpenSource

🦾 From seeing to doing. We're closing the loop between video prediction and real-world action. On the final day of Robbyant Open Source Week, we bring you LingBot-VA—the world's first causal video-action world model for generalist robot control. 🔥 Key Highlights: 🤖 Predicts & Acts: A single model generates both future video and the actions to make it real. 🧠 Remembers the Past: True long-term memory for complex, sequential tasks. ⚡ Learns in a Snap: Masters new skills with just 30-50 real-world demos. The result? 📈 SOTA on RoboTwin (92.9%) and LIBERO (98.5%), +20% over π0.5 on challenging real-world long-horizon & high-precision tasks. More below 👇 #AI #Robotics #EmbodiedAI #WorldModel #OpenSource

Robbyant

704,157 görüntüleme • 5 ay önce

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robots might learn better from video than from language! 📼 Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle “what will happen next,” and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10× less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can “imagine” motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

49,920 görüntüleme • 6 ay önce

Learning from robot data? Standard. Direct Video-Action Models (DVA) is different: treat robot control as video generation, then translate the generated video into actions. Built by , the system pre-trains causal video models from scratch and can run complex production tasks for hours using only ~10 hours of robot data. • hundreds of frames of visual context • real-time control via causal video prediction More: The team behind it just exited 18 months of stealth with a $450M Series A at a $1.7B valuation. Founded by Jagdeep Singh (ex-QuantumScape) with a Stanford-heavy science team: CSO Eric Ryan Chan (ex-WorldLabs) and Prof. Gordon Wetzstein. Already running in large-scale automotive production environments. Backed by Vinod Khosla Ventures, Temasek, Premji Invest, and John Doerr. Thanks for sharing, Tongzhou Mu 🤖🦾🦿 👋

Learning from robot data? Standard. Direct Video-Action Models (DVA) is different: treat robot control as video generation, then translate the generated video into actions. Built by , the system pre-trains causal video models from scratch and can run complex production tasks for hours using only ~10 hours of robot data. • hundreds of frames of visual context • real-time control via causal video prediction More: The team behind it just exited 18 months of stealth with a $450M Series A at a $1.7B valuation. Founded by Jagdeep Singh (ex-QuantumScape) with a Stanford-heavy science team: CSO Eric Ryan Chan (ex-WorldLabs) and Prof. Gordon Wetzstein. Already running in large-scale automotive production environments. Backed by Vinod Khosla Ventures, Temasek, Premji Invest, and John Doerr. Thanks for sharing, Tongzhou Mu 🤖🦾🦿 👋

Ilir Aliu

26,209 görüntüleme • 4 ay önce

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

The Humanoid Hub

35,204 görüntüleme • 5 ay önce

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.

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 görüntüleme • 4 ay önce

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to be annoyingly complex—in both the action and vision space—to even get close to real life. We did an initial attempt: Whole-Body Conditioned Egocentric Video Prediction. In collaboration with @dans_t123 , Amir Bar, Yann LeCun , trevordarrell and Jitendra MALIK. (For more details, check: What we did is very simple: Predict Egocentric Video from human Actions (PEVA) - Given the past video and a future action represented by relative 3D body pose, PEVA predicts how the world looks next—from the first-person view. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, it learns how physical actions shape perception.

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to be annoyingly complex—in both the action and vision space—to even get close to real life. We did an initial attempt: Whole-Body Conditioned Egocentric Video Prediction. In collaboration with @dans_t123 , Amir Bar, Yann LeCun , trevordarrell and Jitendra MALIK. (For more details, check: What we did is very simple: Predict Egocentric Video from human Actions (PEVA) - Given the past video and a future action represented by relative 3D body pose, PEVA predicts how the world looks next—from the first-person view. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, it learns how physical actions shape perception.

Yutong Bai

176,940 görüntüleme • 1 yıl önce

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

465,968 görüntüleme • 1 yıl önce

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 ✈️ RSS

1,077,927 görüntüleme • 1 ay önce

Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained on action or text annotations, the foundation model can determine who the main character is and enable a user to control that character in the generated world. It does this through its Latent Action Model, Video Tokenizer, and Dynamics Model (will go more in-depth on this in tomorrow's newsletter for those interested). And for those asking, yes, it's research-only and not publicly available (here come the Google memes), and it does come with some limitations, like only currently creating games at 1FPS. But this is the worst AI will ever be. Anyone will be able to create their own entirely imagined virtual worlds soon, and that's a wild sentence to say out loud.

Google DeepMind just dropped 'Genie', an AI that can generate interactive video games. This is a huge deal. Genie is trained on 200,000 hours of unsupervised public internet gaming videos and can generate video games from a single prompt or image. But here's what's insane: Despite not being trained on action or text annotations, the foundation model can determine who the main character is and enable a user to control that character in the generated world. It does this through its Latent Action Model, Video Tokenizer, and Dynamics Model (will go more in-depth on this in tomorrow's newsletter for those interested). And for those asking, yes, it's research-only and not publicly available (here come the Google memes), and it does come with some limitations, like only currently creating games at 1FPS. But this is the worst AI will ever be. Anyone will be able to create their own entirely imagined virtual worlds soon, and that's a wild sentence to say out loud.

Rowan Cheung

3,376,834 görüntüleme • 2 yıl önce

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Turing Post

13,755 görüntüleme • 1 ay önce

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

Ilir Aliu - eu/acc

17,353 görüntüleme • 10 ay önce

Introducing PAN — MBZUAI’s New World Model for Interactive Intelligence Developed by MBZUAI’s Institute of Foundation Models, PAN is built for simulation, prediction, and agentic reasoning. Unlike traditional video generators that only output frames, PAN maintains a persistent internal state that evolves when guided with natural language. Its Generative Latent Prediction architecture combines: • A latent encoder to capture the world state • A dynamics module that evolves that state step-by-step • A video diffusion decoder that visualizes outcomes By decoding at every step using a causal sliding-window diffusion process, PAN stays grounded in real-world physics and maintains long-horizon continuity, a leap beyond single-shot models. Evaluated on action fidelity, long-horizon stability, and simulative planning, PAN delivers state-of-the-art performance compared to open models and rivals leading commercial systems. For robotics, autonomy, and decision support, PAN is a foundation for the next wave of intelligent, foresight-driven AI.

Introducing PAN — MBZUAI’s New World Model for Interactive Intelligence Developed by MBZUAI’s Institute of Foundation Models, PAN is built for simulation, prediction, and agentic reasoning. Unlike traditional video generators that only output frames, PAN maintains a persistent internal state that evolves when guided with natural language. Its Generative Latent Prediction architecture combines: • A latent encoder to capture the world state • A dynamics module that evolves that state step-by-step • A video diffusion decoder that visualizes outcomes By decoding at every step using a causal sliding-window diffusion process, PAN stays grounded in real-world physics and maintains long-horizon continuity, a leap beyond single-shot models. Evaluated on action fidelity, long-horizon stability, and simulative planning, PAN delivers state-of-the-art performance compared to open models and rivals leading commercial systems. For robotics, autonomy, and decision support, PAN is a foundation for the next wave of intelligent, foresight-driven AI.

MBZUAI

98,715 görüntüleme • 8 ay önce

X Square Robot just closed its Series C at a valuation above RMB 20 billion, about $2.8 billion 🤖 IDG came into this round. The bigger signal is the cap table. HongShan and Xiaomi were already in across earlier rounds, while Meituan, Alibaba, ByteDance, and Xiaomi have each led rounds at different stages. That puts X Square in a rare position for an embodied AI company: top-tier financial capital on one side, and four of China’s biggest tech platforms on the other. This is not just a money story. Meituan, Alibaba, ByteDance, and Xiaomi bring very different strategic assets: real-world scenarios, cloud infrastructure, consumer traffic, supply chains, and hardware ecosystems. The deployment side is already moving: robot home-cleaning services first, then a “Robots Into Homes” program with the first batch entering real households. The model stack is worth watching too. X Square has open-sourced WALL-OSS-0.5 for robot manipulation and WALL-WM for world modeling. WALL-OSS-0.5 showed strong real-robot performance without post-training, while WALL-WM uses event-level prediction to align language, vision, and action around meaningful physical-world events. They are also building a model-driven data pipeline for large-scale collection, cleaning, annotation, quality control, and augmentation. That matters because home robotics dies in the long tail: weird rooms, messy objects, bad lighting, and tasks that never look the same twice. Founded in 2023, X Square is building general-purpose embodied AI robots and foundation models for real-world environments, tying models, robot hardware, high-precision manipulation, data, and deployment into one system.

X Square Robot just closed its Series C at a valuation above RMB 20 billion, about $2.8 billion 🤖 IDG came into this round. The bigger signal is the cap table. HongShan and Xiaomi were already in across earlier rounds, while Meituan, Alibaba, ByteDance, and Xiaomi have each led rounds at different stages. That puts X Square in a rare position for an embodied AI company: top-tier financial capital on one side, and four of China’s biggest tech platforms on the other. This is not just a money story. Meituan, Alibaba, ByteDance, and Xiaomi bring very different strategic assets: real-world scenarios, cloud infrastructure, consumer traffic, supply chains, and hardware ecosystems. The deployment side is already moving: robot home-cleaning services first, then a “Robots Into Homes” program with the first batch entering real households. The model stack is worth watching too. X Square has open-sourced WALL-OSS-0.5 for robot manipulation and WALL-WM for world modeling. WALL-OSS-0.5 showed strong real-robot performance without post-training, while WALL-WM uses event-level prediction to align language, vision, and action around meaningful physical-world events. They are also building a model-driven data pipeline for large-scale collection, cleaning, annotation, quality control, and augmentation. That matters because home robotics dies in the long tail: weird rooms, messy objects, bad lighting, and tasks that never look the same twice. Founded in 2023, X Square is building general-purpose embodied AI robots and foundation models for real-world environments, tying models, robot hardware, high-precision manipulation, data, and deployment into one system.

RoboHub🤖

12,810 görüntüleme • 17 gün önce

Today I realized something absolutely with BitRobot Network You dont need to own a robot… to actually control one I was just sitting at my laptop and somehow I was moving a real robotic arm in real time At first I thought it would feel like a video game It didnt Theres a completely different feeling when you know this is happening in the real world not just on a screen Every movement matters. Every action generates data And then it hit me… This is how AI is learning to interact with the real world Not from code alone but from people like us Platforms like BitRobot are opening this to everyone No setup No cost No experience Just curiosity and the internet Someone sitting at home can now help train the next generation of robotics. The future isnt coming its happening right now. If you could control a robot right now what would you try first? 🤖👇

Today I realized something absolutely with BitRobot Network You dont need to own a robot… to actually control one I was just sitting at my laptop and somehow I was moving a real robotic arm in real time At first I thought it would feel like a video game It didnt Theres a completely different feeling when you know this is happening in the real world not just on a screen Every movement matters. Every action generates data And then it hit me… This is how AI is learning to interact with the real world Not from code alone but from people like us Platforms like BitRobot are opening this to everyone No setup No cost No experience Just curiosity and the internet Someone sitting at home can now help train the next generation of robotics. The future isnt coming its happening right now. If you could control a robot right now what would you try first? 🤖👇

RAJU

40,141 görüntüleme • 3 ay önce

Video: World’s first humanoid robot labor that swaps its own batteries to work endlessly | Jijo Malayil, Interesting Engineering Walker S2 uses dual-battery balancing and standardized modules to boost efficiency and ensure uninterrupted, optimized performance. In a leap for robotics, China’s UBTech has unveiled the Walker S2, the world’s first humanoid robot capable of fully autonomous battery swapping. Designed for non-stop industrial operations, the Walker S2 can replace its own power pack in just three minutes—no human intervention required. Equipped with advanced anthropomorphic bipedal locomotion and a hot-swappable battery system, Walker S2 is built to operate 24/7 across dynamic industrial environments. According to UBTech, the next-generation humanoid robot marks a major milestone in automation, bringing continuous, hands-free performance to the factory floor. In May 2025, UBTech Robotics and Huawei Technologies inked a significant partnership to accelerate the adoption of humanoid robots across China’s factories and households. Uninterrupted robot operations A video posted by the robotics firm opens with the sleek UBTech Walker S2 humanoid robot working in an industrial setting. The highlight, however, is its autonomous battery swap. Walker S2 approaches the charging station, carefully detaches its depleted power pack, and seamlessly installs a fresh one—all within about three minutes—without any human assistance, according to CGTN. The camera captures close-ups of the robot’s articulated limbs and the intelligent battery-handling mechanism, conveying precision and reliability. As the swap completes, Walker S2 resumes its duties, reinforcing the promise of uninterrupted, 24/7 operations in dynamic factory environments. UBTech’s Walker S2 humanoid robot is equipped with advanced dual-battery power balancing technology and uses standardized battery modules to optimize performance, reports CNEVPOST. This dual-battery system allows the robot to automatically switch to a backup battery in case of a main battery failure, ensuring that critical tasks are carried out without interruption. In addition to battery swapping, the robot can intelligently choose between charging and swapping based on task urgency, allowing it to manage energy dynamically and adapt to real-time operational demands. UBTech highlights these features as a step forward in deploying humanoid robots for industrial and domestic applications, combining flexibility, reliability, and autonomy in one intelligent platform. Factory intelligence upgrade Earlier in the year, UBTech unveiled a major advancement in humanoid robot collaboration, claiming the world’s first deployment of multiple humanoids working together across varied industrial tasks. Demonstrated at Zeekr’s 5G-enabled smart factory, the breakthrough centers on UBTech’s “BrainNet” framework, which orchestrates cooperative behavior through a cloud-device intelligence system. BrainNet integrates a “super brain” for high-level decision-making with an “intelligent sub-brain” for distributed multi-robot control. The super brain, powered by a proprietary large-scale multimodal reasoning model, handles complex production-line scheduling and decision-making. Meanwhile, the sub-brain coordinates real-time tasks using cross-field perception and Transformer-based control for dynamic adaptability. Together, they enable the Walker S1 humanoid robots to move beyond isolated operations and perform coordinated tasks with high precision and speed. The system is built on DeepSeek-R1 reasoning technology and trained on real-world data from automotive factory settings. Leveraging Retrieval-Augmented Generation (RAG), the model adapts to specific job functions and improves scalability across workstations. At Zeekr’s facility, dozens of Walker S1s now collaborate on tasks like assembly, inspection, and part handling. Using semantic VSLAM and shared mapping, they coordinate seamlessly via vision-based navigation and agile manipulation. UBTech says this marks a transition to “Practical Training 2.0,” where humanoid robots operate as a swarm, maximizing efficiency and setting the stage for next-generation intelligent manufacturing.

Video: World’s first humanoid robot labor that swaps its own batteries to work endlessly | Jijo Malayil, Interesting Engineering Walker S2 uses dual-battery balancing and standardized modules to boost efficiency and ensure uninterrupted, optimized performance. In a leap for robotics, China’s UBTech has unveiled the Walker S2, the world’s first humanoid robot capable of fully autonomous battery swapping. Designed for non-stop industrial operations, the Walker S2 can replace its own power pack in just three minutes—no human intervention required. Equipped with advanced anthropomorphic bipedal locomotion and a hot-swappable battery system, Walker S2 is built to operate 24/7 across dynamic industrial environments. According to UBTech, the next-generation humanoid robot marks a major milestone in automation, bringing continuous, hands-free performance to the factory floor. In May 2025, UBTech Robotics and Huawei Technologies inked a significant partnership to accelerate the adoption of humanoid robots across China’s factories and households. Uninterrupted robot operations A video posted by the robotics firm opens with the sleek UBTech Walker S2 humanoid robot working in an industrial setting. The highlight, however, is its autonomous battery swap. Walker S2 approaches the charging station, carefully detaches its depleted power pack, and seamlessly installs a fresh one—all within about three minutes—without any human assistance, according to CGTN. The camera captures close-ups of the robot’s articulated limbs and the intelligent battery-handling mechanism, conveying precision and reliability. As the swap completes, Walker S2 resumes its duties, reinforcing the promise of uninterrupted, 24/7 operations in dynamic factory environments. UBTech’s Walker S2 humanoid robot is equipped with advanced dual-battery power balancing technology and uses standardized battery modules to optimize performance, reports CNEVPOST. This dual-battery system allows the robot to automatically switch to a backup battery in case of a main battery failure, ensuring that critical tasks are carried out without interruption. In addition to battery swapping, the robot can intelligently choose between charging and swapping based on task urgency, allowing it to manage energy dynamically and adapt to real-time operational demands. UBTech highlights these features as a step forward in deploying humanoid robots for industrial and domestic applications, combining flexibility, reliability, and autonomy in one intelligent platform. Factory intelligence upgrade Earlier in the year, UBTech unveiled a major advancement in humanoid robot collaboration, claiming the world’s first deployment of multiple humanoids working together across varied industrial tasks. Demonstrated at Zeekr’s 5G-enabled smart factory, the breakthrough centers on UBTech’s “BrainNet” framework, which orchestrates cooperative behavior through a cloud-device intelligence system. BrainNet integrates a “super brain” for high-level decision-making with an “intelligent sub-brain” for distributed multi-robot control. The super brain, powered by a proprietary large-scale multimodal reasoning model, handles complex production-line scheduling and decision-making. Meanwhile, the sub-brain coordinates real-time tasks using cross-field perception and Transformer-based control for dynamic adaptability. Together, they enable the Walker S1 humanoid robots to move beyond isolated operations and perform coordinated tasks with high precision and speed. The system is built on DeepSeek-R1 reasoning technology and trained on real-world data from automotive factory settings. Leveraging Retrieval-Augmented Generation (RAG), the model adapts to specific job functions and improves scalability across workstations. At Zeekr’s facility, dozens of Walker S1s now collaborate on tasks like assembly, inspection, and part handling. Using semantic VSLAM and shared mapping, they coordinate seamlessly via vision-based navigation and agile manipulation. UBTech says this marks a transition to “Practical Training 2.0,” where humanoid robots operate as a swarm, maximizing efficiency and setting the stage for next-generation intelligent manufacturing.

Owen Gregorian

35,637 görüntüleme • 1 yıl önce

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library. ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent. "Trained model" is a repo of sensorimotor skills instead of floating weights. “Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches. Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of *training* compute ;) Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours! Deep dive in thread:

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library. ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent. "Trained model" is a repo of sensorimotor skills instead of floating weights. “Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches. Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of training compute ;) Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours! Deep dive in thread:

Jim Fan

198,213 görüntüleme • 15 gün önce

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. “We believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,” said the company in a statement. Reports revealed that to avoid the “uncanny valley” effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their users’ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims it’s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. It’s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robots’ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. “We believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,” said the company in a statement. Reports revealed that to avoid the “uncanny valley” effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their users’ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims it’s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. It’s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robots’ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.

Owen Gregorian

179,005 görüntüleme • 9 ay önce

BBREAKING: A German robotics startup from Stuttgart just gave robots imagination: Production robotics system where robots evaluate the long-term consequences of their actions before executing them in live industrial environments. Until now, every production robot optimised actions locally; reacting to what it sees right now. The problem? Small errors early in a sequence compound over time. A slightly off pick leads to a jam three steps later. A marginal placement leads to a collision five steps after that. Cortex 2.0 from Sereact introduces decision-grounded world models directly into live operations. The system evaluates alternative action sequences, predicts how risk accumulates, and estimates the likelihood of entering unrecoverable states, before the robot commits. The world model is trained exclusively on real-world execution data. No synthetic simulation. No approximate environment models. Learned from how robots actually fail, recover, and succeed in production. Works across form factors, pick-and-place arms, dual-arm systems, and humanoids. One intelligence layer, any robot body. The Stuttgart-based company Sereact raised a €25M Series A led by Creandum last year, backed by Air Street Capital Capital, Point Nine 🇺🇦 and angels including Nico Rosberg. They already run some of the most productive AI-driven robotic systems in live warehouse environments, with customers including Daimler Truck AG and Bol. ... Stuttgart, not San Francisco. 🇩🇪 Kudos to Ralf Gulde and team! Credit:

BBREAKING: A German robotics startup from Stuttgart just gave robots imagination: Production robotics system where robots evaluate the long-term consequences of their actions before executing them in live industrial environments. Until now, every production robot optimised actions locally; reacting to what it sees right now. The problem? Small errors early in a sequence compound over time. A slightly off pick leads to a jam three steps later. A marginal placement leads to a collision five steps after that. Cortex 2.0 from Sereact introduces decision-grounded world models directly into live operations. The system evaluates alternative action sequences, predicts how risk accumulates, and estimates the likelihood of entering unrecoverable states, before the robot commits. The world model is trained exclusively on real-world execution data. No synthetic simulation. No approximate environment models. Learned from how robots actually fail, recover, and succeed in production. Works across form factors, pick-and-place arms, dual-arm systems, and humanoids. One intelligence layer, any robot body. The Stuttgart-based company Sereact raised a €25M Series A led by Creandum last year, backed by Air Street Capital Capital, Point Nine 🇺🇦 and angels including Nico Rosberg. They already run some of the most productive AI-driven robotic systems in live warehouse environments, with customers including Daimler Truck AG and Bol. ... Stuttgart, not San Francisco. 🇩🇪 Kudos to Ralf Gulde and team! Credit:

Ilir Aliu

72,419 görüntüleme • 4 ay önce