Video yükleniyor...

Video Yüklenemedi

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...

rohanpaul_ai's profile picture

Rohan Paul

153,705 subscribers

11,253 görüntüleme • 3 ay önce •via X (Twitter)

LIVE

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
1:51

🚀 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

47,604 görüntüleme • 8 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
6:10

🦾 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 • 8 ay önce

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):
0:39

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,513 görüntüleme • 2 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 →
0:47

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

50,130 görüntüleme • 9 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 🤖🦾🦿 👋
6:01

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

26,391 görüntüleme • 7 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.
1:01

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

35,364 görüntüleme • 8 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.
1:14

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

The Humanoid Hub

11,575 görüntüleme • 7 ay önce

Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.⁠⁠ FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with NVIDIA, we also integrated FLUX 3 Action natively into Hugging Face's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).
1:10

Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.⁠⁠ FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with NVIDIA, we also integrated FLUX 3 Action natively into Hugging Face's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).

Black Forest Labs

180,847 görüntüleme • 21 gün önce

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with Black Forest Labs. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like Audi USA, on complex, multi-step manipulation long considered impossible for conventional automation.
3:49

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with Black Forest Labs. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like Audi USA, on complex, multi-step manipulation long considered impossible for conventional automation.

mimic

119,063 görüntüleme • 2 ay önce

New model: your robot can now pack your suitcase 🧳 Xiaomi has released a new robot foundation model. Called Xiaomi-Robotics-1, it is designed to have a robot pick things up and move them around. But first, DEFINITIONS: - Mixture-of-Transformers (MoT): An architecture where separate transformer "experts" (e.g., one for vision-language, one for actions) share a single attention stream, so each modality gets specialized parameters without losing joint reasoning. - Vision-language model (VLM): A model that jointly understands images and text. - Diffusion transformer: A transformer trained to turn noise into structured outputs by iterative denoising, here generating robot actions rather than images. - Action chunks: Short sequences of future actions (e.g., the next ~50 motor commands) predicted in one shot instead of one step at a time. - Flow matching: A faster version of diffusion. The model learns a straight-line velocity field from noise to the target action, so it needs only a few integration steps instead of many denoising ones. Its peculiarity comes from its two stage training: 1. 100,000 hours of video shot through a UMI rig: a handheld 3D-printed gripper with a camera, worn by humans doing ordinary tasks in homes, shops, factories and offices. 2. Adapt to actual robot bodies with ~10,000 hours of real-robot data. It replaces the standard approach of teleoperating a real robot for every hour of training data. Its architecture is a Mixture-of-Transformers pairing a pre-trained Qwen3-VL vision-language model with a diffusion transformer that emits action chunks via flow matching, released in 2.6B, 5.1B and 10.5B parameter variants. However, if you read the entire paper ("Scaling VLA Models with over 100K Hours"), you realize that all of the scaling experiments on 20k hours. Therefore the headline "out-of-the-box success climbing 26% → 75% as pre-training data grows" tops out at 100% of 20k hours! What the full corpus does to that curve is never shown -> and this where things would become interesting! Xiaomi's own conclusion is that model size has stopped mattering and data is the binding constraint. The performance gap among different model sizes are less pronounced than those observed across different data scales. This result suggests that model capacity at the billions-parameter scale may already be sufficient to capture the current dataset's distribution. Which further asks the same question: why not use the 100k video hours? Anyway, I would definitely love to have a couple robots at home that can cooperate to pack my suitcase with items relevant to my next destination:
0:58

New model: your robot can now pack your suitcase 🧳 Xiaomi has released a new robot foundation model. Called Xiaomi-Robotics-1, it is designed to have a robot pick things up and move them around. But first, DEFINITIONS: - Mixture-of-Transformers (MoT): An architecture where separate transformer "experts" (e.g., one for vision-language, one for actions) share a single attention stream, so each modality gets specialized parameters without losing joint reasoning. - Vision-language model (VLM): A model that jointly understands images and text. - Diffusion transformer: A transformer trained to turn noise into structured outputs by iterative denoising, here generating robot actions rather than images. - Action chunks: Short sequences of future actions (e.g., the next ~50 motor commands) predicted in one shot instead of one step at a time. - Flow matching: A faster version of diffusion. The model learns a straight-line velocity field from noise to the target action, so it needs only a few integration steps instead of many denoising ones. Its peculiarity comes from its two stage training: 1. 100,000 hours of video shot through a UMI rig: a handheld 3D-printed gripper with a camera, worn by humans doing ordinary tasks in homes, shops, factories and offices. 2. Adapt to actual robot bodies with ~10,000 hours of real-robot data. It replaces the standard approach of teleoperating a real robot for every hour of training data. Its architecture is a Mixture-of-Transformers pairing a pre-trained Qwen3-VL vision-language model with a diffusion transformer that emits action chunks via flow matching, released in 2.6B, 5.1B and 10.5B parameter variants. However, if you read the entire paper ("Scaling VLA Models with over 100K Hours"), you realize that all of the scaling experiments on 20k hours. Therefore the headline "out-of-the-box success climbing 26% → 75% as pre-training data grows" tops out at 100% of 20k hours! What the full corpus does to that curve is never shown -> and this where things would become interesting! Xiaomi's own conclusion is that model size has stopped mattering and data is the binding constraint. The performance gap among different model sizes are less pronounced than those observed across different data scales. This result suggests that model capacity at the billions-parameter scale may already be sufficient to capture the current dataset's distribution. Which further asks the same question: why not use the 100k video hours? Anyway, I would definitely love to have a couple robots at home that can cooperate to pack my suitcase with items relevant to my next destination:

Léo

15,777 görüntüleme • 2 ay önce

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.
0:28

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.

The Humanoid Hub

15,988 görüntüleme • 2 ay önce

This World Model 'LingBot-World-Infinity (LingBot-World 2.0)' just released from Ant Group looks realy promising. It is an open causal world model with an Agentic harness. Most interactive world models hold together for a few minutes. Then textures smear and geometry warps. That's a video model, not a world — and Robbyant just drew the line at the attention mask. They released LingBot-World-Infinity (LingBot-World 2.0) — a 14B open causal video world model built on Wan2.2, trained with a Mixture of Bidirectional and Autoregressive (MoBA) attention mask, then distilled into a few-step real-time generator with no post-hoc drift filtering anywhere in the stack. Here's what's actually interesting: → Pure teacher forcing overfits — as context grows, the model leans on context instead of predicting frames. MoBA appends a bidirectional full-attention block as a regularizer → Leak-free cross-attention: AR rows attend to background prompt a_B plus chunk prompts a_≤i, lower-triangular. Bidirectional rows see one global prompt a_G → DMD runs over long self-rollout trajectories, not teacher-forced states — the student is optimized on the distribution its own errors induce → Director-Pilot harness: a VLM proposes event cards, the DiT generator renders physical dynamics. Mode B adds a SAM tracking loop for object-centric interaction → One 60-minute uninterrupted session, 20 distinct scenarios, no perceptible decay Full analysis: Paper: Model weight: GitHub Repo: Project: Ant Group Robbyant
0:48

This World Model 'LingBot-World-Infinity (LingBot-World 2.0)' just released from Ant Group looks realy promising. It is an open causal world model with an Agentic harness. Most interactive world models hold together for a few minutes. Then textures smear and geometry warps. That's a video model, not a world — and Robbyant just drew the line at the attention mask. They released LingBot-World-Infinity (LingBot-World 2.0) — a 14B open causal video world model built on Wan2.2, trained with a Mixture of Bidirectional and Autoregressive (MoBA) attention mask, then distilled into a few-step real-time generator with no post-hoc drift filtering anywhere in the stack. Here's what's actually interesting: → Pure teacher forcing overfits — as context grows, the model leans on context instead of predicting frames. MoBA appends a bidirectional full-attention block as a regularizer → Leak-free cross-attention: AR rows attend to background prompt a_B plus chunk prompts a_≤i, lower-triangular. Bidirectional rows see one global prompt a_G → DMD runs over long self-rollout trajectories, not teacher-forced states — the student is optimized on the distribution its own errors induce → Director-Pilot harness: a VLM proposes event cards, the DiT generator renders physical dynamics. Mode B adds a SAM tracking loop for object-centric interaction → One 60-minute uninterrupted session, 20 distinct scenarios, no perceptible decay Full analysis: Paper: Model weight: GitHub Repo: Project: Ant Group Robbyant

Marktechpost AI

233,449 görüntüleme • 3 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.
3:12

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

179,812 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: 🧵
2:21

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

467,710 görüntüleme • 1 yıl önce

Introducing Praxis-1, an open-weight World Action Model that turns our video pre-training expertise into real world control for robots. Robot demonstration data is limited. But video data is infinite. Praxis-1 extends our bet that the best policy models will learn from video, and use that scale to bring embodied intelligence to every industry. Praxis-1 is built on our large-scale video pre-training and real-time infrastructure, and acts as a policy model for robotics developers and researchers that works across any embodiment or environment, no matter how complex. We are actively testing with early partners including Noble Machines, Standard Bots and Ultra, and will be releasing the weights publicly in the coming months. Learn more and request early access at
1:54

Introducing Praxis-1, an open-weight World Action Model that turns our video pre-training expertise into real world control for robots. Robot demonstration data is limited. But video data is infinite. Praxis-1 extends our bet that the best policy models will learn from video, and use that scale to bring embodied intelligence to every industry. Praxis-1 is built on our large-scale video pre-training and real-time infrastructure, and acts as a policy model for robotics developers and researchers that works across any embodiment or environment, no matter how complex. We are actively testing with early partners including Noble Machines, Standard Bots and Ultra, and will be releasing the weights publicly in the coming months. Learn more and request early access at

Runway

118,602 görüntüleme • 14 gün önce

Most AI world models can generate beautiful scenes. Keeping those scenes alive for an hour without falling apart is the real challenge. That's what caught my attention about LingBot-World 2.0 (LingBot-World-Infinity) from Robbyant Instead of chasing longer videos, it focuses on something much harder: persistent, interactive worlds that stay coherent while you explore. A few highlights: • Generates worlds from a single frame and continuously responds to live user actions through a causal world model. • Streams stable 720p at 60 FPS in real time. The team reports a continuous 60 minute stress test across 20 different scenarios with no noticeable visual degradation. • Uses a Brain-Cerebellum co-simulation framework where a VLM plans events while the video model turns them into consistent world evolution. • Pilot and Director Agents help drive character behavior and introduce new objects and events. • Open sourced with a 14B flagship model, while the paper also describes a lightweight 1.3B version for a single consumer GPU. There is also an online interactive demo. The biggest takeaway? We're moving beyond AI that generates clips. We're getting closer to AI that generates living, evolving worlds you can actually interact with. And that feels like a much bigger shift than another jump in video quality. Explore more: 💻 Github: 🤗 Weights: 🌐 Website-with videos you can use : 🎮 Try it online: #Robbyant #LingBot #WorldModel #EmbodiedAI #OpenSource #Robotics #ad
0:59

Most AI world models can generate beautiful scenes. Keeping those scenes alive for an hour without falling apart is the real challenge. That's what caught my attention about LingBot-World 2.0 (LingBot-World-Infinity) from Robbyant Instead of chasing longer videos, it focuses on something much harder: persistent, interactive worlds that stay coherent while you explore. A few highlights: • Generates worlds from a single frame and continuously responds to live user actions through a causal world model. • Streams stable 720p at 60 FPS in real time. The team reports a continuous 60 minute stress test across 20 different scenarios with no noticeable visual degradation. • Uses a Brain-Cerebellum co-simulation framework where a VLM plans events while the video model turns them into consistent world evolution. • Pilot and Director Agents help drive character behavior and introduce new objects and events. • Open sourced with a 14B flagship model, while the paper also describes a lightweight 1.3B version for a single consumer GPU. There is also an online interactive demo. The biggest takeaway? We're moving beyond AI that generates clips. We're getting closer to AI that generates living, evolving worlds you can actually interact with. And that feels like a much bigger shift than another jump in video quality. Explore more: 💻 Github: 🤗 Weights: 🌐 Website-with videos you can use : 🎮 Try it online: #Robbyant #LingBot #WorldModel #EmbodiedAI #OpenSource #Robotics #ad

Alif Khan

84,562 görüntüleme • 3 ay 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:
0:44

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

1,080,311 görüntüleme • 4 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.
0:27

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

3,378,362 görüntüleme • 2 yıl önce

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
1:35

JUST IN: Dyna Robotics just published one of the most important research papers in robotics this year. It could fundamentally change how robot foundation models are trained. A scaling law that transfers from human video to robot performance. Dyna-2 is out and it's 🔥 Here's what that means in plain terms. Dyna-2 was pre-trained on ONE MILLION hours of egocentric human video, 170 years of continuous human experience, cooking, folding, assembling, cleaning. And as that human data scaled, robot performance improved. Predictably. Monotonically. Across 39 tasks on two different robot embodiments the model had never seen. → 1,000 hours pre-training → 20% normalised task performance → 10,000 hours → 28% → 100,000 hours → 45% → 1,000,000 hours → 53% Human video exists at effectively unlimited scale. Every cook, every factory worker, every craftsperson wearing a camera is generating training data for future robots. But the finding that stunned even the researchers, world modeling is what makes the transfer work. A model trained to predict future video AND actions massively outperforms one trained on actions alone. Video is the new scaling axis for robotics. One more jaw-dropping data point. 13 minutes of teleoperation data was enough to fine-tune Dyna-2 to open a bottle cap using two five-fingered robot hands. The robots are coming, and they're learning from us directly :D Read more here: Congrats Jason Ma and team! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

23,681 görüntüleme • 2 ay önce