Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Driver — a transformer-based, real-time, vision-only path prediction model for highway and urban driving. It predicts the vehicle’s future path using only camera-based perception—no Lidar, HD maps, or additional sensors required. We deployed it in closed-loop simulation with CARLA Simulator + GenSim-2, our generative AI model that re-renders... show more

Helm.ai

1,484 subscribers

4,040,913 views • 1 year ago •via X (Twitter)

News & Politics Science & Technology Autos & Vehicles

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NEWS: Waymo has introduced the Waymo World Model, "a frontier generative model built on Google DeepMind’s Genie 3 that sets a new bar for large-scale, hyper-realistic autonomous driving simulation." "By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and complex scenarios—from tornadoes to planes landing on freeways—long before it encounters them in the real world. The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity, multi-sensor outputs that include both camera and lidar data. This combination of broad world knowledge, fine-grained controllability, and multi-modal realism enhances Waymo’s ability to safely scale our service across more places and new driving environments. In the following sections we showcase the Waymo World Model in action, featuring simulations of the Waymo Driver navigating diverse rare edge-case scenarios." More info below.

NEWS: Waymo has introduced the Waymo World Model, "a frontier generative model built on Google DeepMind’s Genie 3 that sets a new bar for large-scale, hyper-realistic autonomous driving simulation." "By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and complex scenarios—from tornadoes to planes landing on freeways—long before it encounters them in the real world. The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity, multi-sensor outputs that include both camera and lidar data. This combination of broad world knowledge, fine-grained controllability, and multi-modal realism enhances Waymo’s ability to safely scale our service across more places and new driving environments. In the following sections we showcase the Waymo World Model in action, featuring simulations of the Waymo Driver navigating diverse rare edge-case scenarios." More info below.

Sawyer Merritt

133,325 views • 7 months ago

Excited to share this demo from Over the Reality! Watch our Unitree Go2 robodog navigating our office while reconstructing the 3D space in real-time using the VGGT-based foundation vision model. This is a prime example of machine perception in action, turning raw RGB camera feeds into rich, detailed 3D maps! The robodog's RGB cam generates a dense, textured 3D reconstruction via VGGT from a few photograms, capturing nuances like object shapes and surfaces with impressive fidelity (main view). Compare that to the standard LiDAR system (top right), it's sparser, more point-cloud focused, lacking the visual richness. Vision models are closing the gap fast! What's powering this? VGGT, a cutting-edge foundation model for 3D perception, trained on datasets orders of magnitude smaller than our massive OVER 3D maps dataset. Imagine the leap when we apply OVER's scale to VGGT-like transformer based architectures, denser reconstructions, better generalization, revolutionary for robotics, machine perception & AR! Stay tuned for more breakthroughs at the intersection of AI, robotics, and DePIN. We're building the future of Physical AI and Spatial Computing at Over the Reality 🌐 What do you think, ready for robodogs in your world? Drop your thoughts! 🤖🌐

Excited to share this demo from Over the Reality! Watch our Unitree Go2 robodog navigating our office while reconstructing the 3D space in real-time using the VGGT-based foundation vision model. This is a prime example of machine perception in action, turning raw RGB camera feeds into rich, detailed 3D maps! The robodog's RGB cam generates a dense, textured 3D reconstruction via VGGT from a few photograms, capturing nuances like object shapes and surfaces with impressive fidelity (main view). Compare that to the standard LiDAR system (top right), it's sparser, more point-cloud focused, lacking the visual richness. Vision models are closing the gap fast! What's powering this? VGGT, a cutting-edge foundation model for 3D perception, trained on datasets orders of magnitude smaller than our massive OVER 3D maps dataset. Imagine the leap when we apply OVER's scale to VGGT-like transformer based architectures, denser reconstructions, better generalization, revolutionary for robotics, machine perception & AR! Stay tuned for more breakthroughs at the intersection of AI, robotics, and DePIN. We're building the future of Physical AI and Spatial Computing at Over the Reality 🌐 What do you think, ready for robodogs in your world? Drop your thoughts! 🤖🌐

Over the Reality 🌐

359,717 views • 1 year ago

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,831 views • 11 months ago

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

The Humanoid Hub

17,065 views • 7 months ago

Transformer Explainer Interactive Learning of Text-Generative Models discuss: Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques.

Transformer Explainer Interactive Learning of Text-Generative Models discuss: Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques.

AK

90,862 views • 2 years ago

Why Elon rejected LiDAR for cars while personally spearheading LiDAR development at SpaceX “LiDAR is lame. They’re all going to dump LiDAR. Mark my words” And years later, the industry is starting to realize just how massive that mistake that was Automakers spent years piling expensive sensors onto cars while Elon took the opposite path: Solve vision People acted like Elon hated LiDAR He literally spearheaded the development of SpaceX’s own LiDAR system from scratch Dragon uses LiDAR to navigate and dock with the International Space Station Because in space, LiDAR actually solves a real problem But for cars, once vision is solved, LiDAR becomes expensive, redundant hardware That became Tesla’s entire autonomy architecture: Cameras, Neural networks, Massive real-world training data........AI doing the driving And Cybercab is the purest version of that philosophy. It comes with no LiDAR or giant rooftop sensor array or a hardware circus Just cameras, onboard AI and FSD Elon chose this path more than a decade ago while almost everyone else was throwing more sensors at the problem Now Cybercab is being built with pure vision from day one Solve vision well enough...and autonomy becomes dramatically simpler, cheaper and infinitely easier to scale The industry kept building autonomy around more hardware. Elon built Tesla around better intelligence

Why Elon rejected LiDAR for cars while personally spearheading LiDAR development at SpaceX “LiDAR is lame. They’re all going to dump LiDAR. Mark my words” And years later, the industry is starting to realize just how massive that mistake that was Automakers spent years piling expensive sensors onto cars while Elon took the opposite path: Solve vision People acted like Elon hated LiDAR He literally spearheaded the development of SpaceX’s own LiDAR system from scratch Dragon uses LiDAR to navigate and dock with the International Space Station Because in space, LiDAR actually solves a real problem But for cars, once vision is solved, LiDAR becomes expensive, redundant hardware That became Tesla’s entire autonomy architecture: Cameras, Neural networks, Massive real-world training data........AI doing the driving And Cybercab is the purest version of that philosophy. It comes with no LiDAR or giant rooftop sensor array or a hardware circus Just cameras, onboard AI and FSD Elon chose this path more than a decade ago while almost everyone else was throwing more sensors at the problem Now Cybercab is being built with pure vision from day one Solve vision well enough...and autonomy becomes dramatically simpler, cheaper and infinitely easier to scale The industry kept building autonomy around more hardware. Elon built Tesla around better intelligence

X Freeze

146,559 views • 5 days ago

Excited to share that our paper 🌊🤺 “CFC: Simulating Character–Fluid Coupling using a Two-Level World Model” has been accepted to #SIGGRAPHASIA2025! In this work, we build a two-level world model (neural physics) for rigid-body–fluid interaction and use it to train physics-based character controllers efficiently. We study: (1) learning to model highly dynamic fluid environments, (2) representing character–fluid interaction via joint-level forces as an interface, and (3) enabling supervised policy learning on the learned world model—avoiding expensive fluid simulation in the training loop. Our talk is on Monday afternoon(Dec 15)—hope to see you there! Time: Monday, 15 December 2025 5:02pm - 5:13pm GMT+8 Location: Meeting Room S221, Level 2. #SIGGRAPHASIA #SIGGRAPH

Excited to share that our paper 🌊🤺 “CFC: Simulating Character–Fluid Coupling using a Two-Level World Model” has been accepted to #SIGGRAPHASIA2025! In this work, we build a two-level world model (neural physics) for rigid-body–fluid interaction and use it to train physics-based character controllers efficiently. We study: (1) learning to model highly dynamic fluid environments, (2) representing character–fluid interaction via joint-level forces as an interface, and (3) enabling supervised policy learning on the learned world model—avoiding expensive fluid simulation in the training loop. Our talk is on Monday afternoon(Dec 15)—hope to see you there! Time: Monday, 15 December 2025 5:02pm - 5:13pm GMT+8 Location: Meeting Room S221, Level 2. #SIGGRAPHASIA #SIGGRAPH

Zhiyang (Frank) Dou

20,247 views • 9 months ago

Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Hitting 76.6% on R2R-CE With One RGB Camera. No LiDAR. No depth sensor. No multi-camera rig. Here's how it works. 👇 1. Pointing, not metric commands The model predicts the pixel coordinates of the next target in the camera view, plus the arrival orientation. Working in pixel space keeps it robust to camera intrinsics and world scale. When the target leaves the frame, it falls back to local displacements ("2m forward, 1.5m left, turn 25°"). 2. Grounding-first No open-source VLM base. It starts from Mistral's grounding model (pointing, counting, localization). Navigation emerges once the model knows where things are. → ~400,000 trajectories across 6,000 simulated scenes 3. Prefix-caching for training A tree-based attention mask packs a full episode into one sequence — all time steps in a single forward pass. → 22× fewer training tokens; months of training done in days 4. Online RL on top After supervised training, CISPO adds trial-and-error learning to fight distribution shift from behavior cloning. → +3.2% success rate from RL alone 5. The numbers (R2R-CE, Matterport3D) → 76.6% success on validation unseen → +9.7 pts over best single-camera approach → +4.5 pts over best depth/multi-camera system The key takeaway: state-of-the-art continuous VLN without a sensor stack — grounding-init, pixel-space actions, prefix-cached SFT, and online RL, on one RGB camera. Full analysis: Technical details: Mistral AI Mistral AI for Developers

Mistral AI Releases Robostral Navigate: An 8B Model Enabling Robots to Navigate Complex Environments Hitting 76.6% on R2R-CE With One RGB Camera. No LiDAR. No depth sensor. No multi-camera rig. Here's how it works. 👇 1. Pointing, not metric commands The model predicts the pixel coordinates of the next target in the camera view, plus the arrival orientation. Working in pixel space keeps it robust to camera intrinsics and world scale. When the target leaves the frame, it falls back to local displacements ("2m forward, 1.5m left, turn 25°"). 2. Grounding-first No open-source VLM base. It starts from Mistral's grounding model (pointing, counting, localization). Navigation emerges once the model knows where things are. → ~400,000 trajectories across 6,000 simulated scenes 3. Prefix-caching for training A tree-based attention mask packs a full episode into one sequence — all time steps in a single forward pass. → 22× fewer training tokens; months of training done in days 4. Online RL on top After supervised training, CISPO adds trial-and-error learning to fight distribution shift from behavior cloning. → +3.2% success rate from RL alone 5. The numbers (R2R-CE, Matterport3D) → 76.6% success on validation unseen → +9.7 pts over best single-camera approach → +4.5 pts over best depth/multi-camera system The key takeaway: state-of-the-art continuous VLN without a sensor stack — grounding-init, pixel-space actions, prefix-cached SFT, and online RL, on one RGB camera. Full analysis: Technical details: Mistral AI Mistral AI for Developers

Marktechpost AI

39,955 views • 2 months ago

If you can text, you can now edit videos. Introducing our new chat-based editor. Just type the edits you want to see and our AI does it for you. No learning curve or special skills required. This editor doesn’t only follow your direction, but has taste and opinions. Every graphic, zoom, or transition is applied in a way that quietly boosts engagement. To show you what this means, we pitted an editor against the prompt-box. Try it for yourself in Captions by Mirage

If you can text, you can now edit videos. Introducing our new chat-based editor. Just type the edits you want to see and our AI does it for you. No learning curve or special skills required. This editor doesn’t only follow your direction, but has taste and opinions. Every graphic, zoom, or transition is applied in a way that quietly boosts engagement. To show you what this means, we pitted an editor against the prompt-box. Try it for yourself in Captions by Mirage

Gaurav Misra

60,054 views • 11 months ago

NEWS: Waymo has released a new blog post detailing their AI strategy and how it’s allowing them to bring service to more riders faster. "Achieving demonstrably safe AI — where safety is proven, not just promised — requires a holistic approach. Beyond a smart and capable Driver, you also need a closed-loop, realistic Simulator to train and rigorously test the Driver in a myriad of challenging situations, and a sharp Critic to evaluate the Driver's performance and identify areas for improvement." Waymo says that autonomous driving isn’t just a matter of building a “smart driver,” but rather creating a full AI ecosystem centered on safety from the ground up. At the core is the Waymo Foundation Model, a unified world-model that powers all major components of Waymo’s autonomous stack (Driver, Simulator, Critic). "By using a “Think Fast/Think Slow” architecture (combining rapid sensor-fusion with deep semantic reasoning), this system enables the car to detect complex and rare road scenarios (e.g. a burning vehicle ahead), reason about them, and choose safe behavior. Waymo trains large “Teacher” AI-models for driving, simulation, and evaluation, then distills them into smaller, efficient “Student” models suitable for real-world deployment, while keeping safety validation tightly integrated. The result is a continuous “flywheel” of learning: driving data (real and simulated) generate feedback, which leads to refinements, more simulation, more data, and only when safety checks pass is new code deployed. Having already exceeded 100 million fully autonomous miles, Waymo reports a more than ten-fold reduction in severe-injury crashes compared to human drivers." Full blog post:

NEWS: Waymo has released a new blog post detailing their AI strategy and how it’s allowing them to bring service to more riders faster. "Achieving demonstrably safe AI — where safety is proven, not just promised — requires a holistic approach. Beyond a smart and capable Driver, you also need a closed-loop, realistic Simulator to train and rigorously test the Driver in a myriad of challenging situations, and a sharp Critic to evaluate the Driver's performance and identify areas for improvement." Waymo says that autonomous driving isn’t just a matter of building a “smart driver,” but rather creating a full AI ecosystem centered on safety from the ground up. At the core is the Waymo Foundation Model, a unified world-model that powers all major components of Waymo’s autonomous stack (Driver, Simulator, Critic). "By using a “Think Fast/Think Slow” architecture (combining rapid sensor-fusion with deep semantic reasoning), this system enables the car to detect complex and rare road scenarios (e.g. a burning vehicle ahead), reason about them, and choose safe behavior. Waymo trains large “Teacher” AI-models for driving, simulation, and evaluation, then distills them into smaller, efficient “Student” models suitable for real-world deployment, while keeping safety validation tightly integrated. The result is a continuous “flywheel” of learning: driving data (real and simulated) generate feedback, which leads to refinements, more simulation, more data, and only when safety checks pass is new code deployed. Having already exceeded 100 million fully autonomous miles, Waymo reports a more than ten-fold reduction in severe-injury crashes compared to human drivers." Full blog post:

Sawyer Merritt

83,635 views • 9 months ago

Project Astra: Google's AI agent that can 'see the world' using your phone camera Use cases that stood out to me: > Summarizing a book page in seconds and chatting with it for follow-ups on complex topics (professor-in-your-pocket) > Identifying a rash: just seasonal hives or something more serious? > Real-time translation of languages, sign language, and books (worked great for Japanese writing → English summary). > Locating landscapes in photos and estimating their distance using the Google Maps integration. > Remembering cookbook recipes and recommending wine pairings based on the recipe and budget. > Summarizing thousands of Amazon/Airbnb reviews in seconds using mobile screen sharing, with highlights of any negative feedback.

Project Astra: Google's AI agent that can 'see the world' using your phone camera Use cases that stood out to me: > Summarizing a book page in seconds and chatting with it for follow-ups on complex topics (professor-in-your-pocket) > Identifying a rash: just seasonal hives or something more serious? > Real-time translation of languages, sign language, and books (worked great for Japanese writing → English summary). > Locating landscapes in photos and estimating their distance using the Google Maps integration. > Remembering cookbook recipes and recommending wine pairings based on the recipe and budget. > Summarizing thousands of Amazon/Airbnb reviews in seconds using mobile screen sharing, with highlights of any negative feedback.

Rowan Cheung

20,022 views • 1 year ago

Introducing Beni AI We’re building a hyper-personal AI companion that remembers you, talks with you, and adapts in real time. No more static chat-based chatbots. Beni isn’t just reactive, she’s alive. Talk to her, hear her voice, see her move, and watch her remember the smallest details about you through your camera. Powered by a high-intelligence memory layer and real-time live communication, Beni learns your world and adapts to you - anywhere, anytime. Our chain-agnostic architecture connects to new chains in a day, and with AA-based login, onboarding is frictionless across Web2 or Web3 aiming for true mass adoption. Start on web, continue on desktop OS or mobile. Beni is always with you. Beni AI is coming on early December. 🔗 Join beta waitlist :

Introducing Beni AI We’re building a hyper-personal AI companion that remembers you, talks with you, and adapts in real time. No more static chat-based chatbots. Beni isn’t just reactive, she’s alive. Talk to her, hear her voice, see her move, and watch her remember the smallest details about you through your camera. Powered by a high-intelligence memory layer and real-time live communication, Beni learns your world and adapts to you - anywhere, anytime. Our chain-agnostic architecture connects to new chains in a day, and with AA-based login, onboarding is frictionless across Web2 or Web3 aiming for true mass adoption. Start on web, continue on desktop OS or mobile. Beni is always with you. Beni AI is coming on early December. 🔗 Join beta waitlist :

Beni AI

36,556 views • 10 months ago

Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are incredible. These videos are entirely synthetically generated by Wayve's generative AI, GAIA-1. But there is more here than just generating videos, GAIA is an entire world model. A world model allows us to simulate the future, conditioned on video, text and action inputs, which can be leveraged for making informed decisions when driving. Why is this game-changing for autonomous driving? 1. Safety. One limitation with AI systems like today's Large Language Models is that they are autoregressive, next-word prediction algorithms, but aren't necessarily aware of the implications of their decisions. A world model allows us to give our AI the capability to be aware of its decisions, by simulating the future, which is important for self-driving safety. 2. Synthetic training data. I believe synthetic training data is the future for AI, because it is safer, cheaper, and infinitely scalable. GAIA-1 unlocks unprecedented realism and diversity of synthetic data for self-driving. 3. Long-tail robustness. One of the biggest challenges for self-driving is long-tail robustness: dealing with the enormous magnitude of edge cases we see on the road. An advantage of generative AI is its incredible ability to recombine experiences in new ways. This is exciting for self-driving as it means we can learn from two edge case scenarios, and combine them to become a corner case. For example, we can experience driving in fog, and experience of jay-walking pedestrians, and GAIA can learn from these experiences to understand how to generate a fog+jay walking scenario. Check out many more videos in our blog or further technical details in our paper: Or come chat with our team who are at the International Conference on Computer Vision (#ICCV2023) this week in Paris in Booth 32 Jamie Shotton

Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are incredible. These videos are entirely synthetically generated by Wayve's generative AI, GAIA-1. But there is more here than just generating videos, GAIA is an entire world model. A world model allows us to simulate the future, conditioned on video, text and action inputs, which can be leveraged for making informed decisions when driving. Why is this game-changing for autonomous driving? 1. Safety. One limitation with AI systems like today's Large Language Models is that they are autoregressive, next-word prediction algorithms, but aren't necessarily aware of the implications of their decisions. A world model allows us to give our AI the capability to be aware of its decisions, by simulating the future, which is important for self-driving safety. 2. Synthetic training data. I believe synthetic training data is the future for AI, because it is safer, cheaper, and infinitely scalable. GAIA-1 unlocks unprecedented realism and diversity of synthetic data for self-driving. 3. Long-tail robustness. One of the biggest challenges for self-driving is long-tail robustness: dealing with the enormous magnitude of edge cases we see on the road. An advantage of generative AI is its incredible ability to recombine experiences in new ways. This is exciting for self-driving as it means we can learn from two edge case scenarios, and combine them to become a corner case. For example, we can experience driving in fog, and experience of jay-walking pedestrians, and GAIA can learn from these experiences to understand how to generate a fog+jay walking scenario. Check out many more videos in our blog or further technical details in our paper: Or come chat with our team who are at the International Conference on Computer Vision (#ICCV2023) this week in Paris in Booth 32 Jamie Shotton

Alex Kendall

631,869 views • 2 years ago

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

179,519 views • 1 year ago

Today, we're sharing new research on GWM Worlds 2. Our latest General World Model that generates interactive real-time simulations in continuous 720p video at 24 fps with 48000 Hz audio. Built on top of our foundational audio-visual generation model, GWM Worlds 2 allows you to define the environment, subjects, visual style, physical rules and ambience of any world. Once inside, you steer it with text actions addressed to any subject or to the scene itself, alongside continuous camera motion. The world continues from each new input instead of following a fixed clip or script so sessions have no preset length. GWM Worlds 2 creates a new foundation for interactive entertainment, virtual characters, robotics and embodied-agent simulation. Learn more about GWM Worlds 2 at the link below.

Today, we're sharing new research on GWM Worlds 2. Our latest General World Model that generates interactive real-time simulations in continuous 720p video at 24 fps with 48000 Hz audio. Built on top of our foundational audio-visual generation model, GWM Worlds 2 allows you to define the environment, subjects, visual style, physical rules and ambience of any world. Once inside, you steer it with text actions addressed to any subject or to the scene itself, alongside continuous camera motion. The world continues from each new input instead of following a fixed clip or script so sessions have no preset length. GWM Worlds 2 creates a new foundation for interactive entertainment, virtual characters, robotics and embodied-agent simulation. Learn more about GWM Worlds 2 at the link below.

Runway

300,647 views • 8 days ago

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

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

ANI

163,060 views • 1 month ago

We are excited to share our #CORL2024 paper on learning quadrotor obstacle avoidance from the visual stream of a single #eventcamera! Trained entirely in simulation! We demonstrate obstacle avoidance both in the dark and in a forest up to 5m/s. PDF: Video: Project page: Event cameras are sensors that output per-pixel-level intensity changes at microsecond latency resolution; they feature nearly zero motion blur and high dynamic range but produce a very large volume of events under significant ego-motion and further lack a high-fidelity continuous-time sensor model in simulation, making direct #sim2real transfer not possible. By leveraging depth prediction as a pretext task, we pre-train a reactive obstacle avoidance policy with “approximated” simulated events and then fine-tune the perception component with limited events-and-depth real-world data. This technique bridges the sim2real gap for #eventcameras! As at the current state, there is no continuous-time sensor model for event cameras, we hope that this work can finally spur future research leveraging simulation for training event-vision-based policies to create faster, agile robots! Kudos to Anish Bhattacharya, @marcocannic, Vijay Kumar Nikolai Matni UZH Science University of Zurich UZH Space Hub UZH IfI European Research Council (ERC) GRASP Laboratory Penn Engineering

We are excited to share our #CORL2024 paper on learning quadrotor obstacle avoidance from the visual stream of a single #eventcamera! Trained entirely in simulation! We demonstrate obstacle avoidance both in the dark and in a forest up to 5m/s. PDF: Video: Project page: Event cameras are sensors that output per-pixel-level intensity changes at microsecond latency resolution; they feature nearly zero motion blur and high dynamic range but produce a very large volume of events under significant ego-motion and further lack a high-fidelity continuous-time sensor model in simulation, making direct #sim2real transfer not possible. By leveraging depth prediction as a pretext task, we pre-train a reactive obstacle avoidance policy with “approximated” simulated events and then fine-tune the perception component with limited events-and-depth real-world data. This technique bridges the sim2real gap for #eventcameras! As at the current state, there is no continuous-time sensor model for event cameras, we hope that this work can finally spur future research leveraging simulation for training event-vision-based policies to create faster, agile robots! Kudos to Anish Bhattacharya, @marcocannic, Vijay Kumar Nikolai Matni UZH Science University of Zurich UZH Space Hub UZH IfI European Research Council (ERC) GRASP Laboratory Penn Engineering

Davide Scaramuzza

17,219 views • 1 year ago