Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Trio-Lumen turns plain English into a live perception rule in under a minute: 1️⃣ Language compiles into a structured detection rule 2️⃣ Real-time tracking (~30ms) + VLM semantic judgment per subject 3️⃣ Every alert fires as a structured event — frame, zone, track ID Zero labeling. Zero training. Zero... show more

IoTeX

326,006 subscribers

10,638 просмотров • 2 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I built a real app today by describing what I wanted in plain English. That’s the promise of Replit ⠕. You start with an idea. You explain it in natural language. Replit turns it into a working app with hosting, auth, data, and AI already wired in. No setup. No tool switching. No fragile prototypes. What stood out is how far you can take it. From a rough concept to something you can actually ship, all in one place. Even on mobile. This is vibe coding as a complete workflow, not a shortcut. If you’ve ever wanted to turn an idea into a real product without friction, this is worth trying. Build here →

I built a real app today by describing what I wanted in plain English. That’s the promise of Replit ⠕. You start with an idea. You explain it in natural language. Replit turns it into a working app with hosting, auth, data, and AI already wired in. No setup. No tool switching. No fragile prototypes. What stood out is how far you can take it. From a rough concept to something you can actually ship, all in one place. Even on mobile. This is vibe coding as a complete workflow, not a shortcut. If you’ve ever wanted to turn an idea into a real product without friction, this is worth trying. Build here →

Parul Gautam

70,662 просмотров • 8 месяцев назад

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.

At Avalon we are building "Real-time creating" - the ability to generate gameplay ready persistent worlds prompted from text. While others are building real-time video world models, Avalon is building real-time world generation inside a fully playable, persistent multiplayer engine. Internally running at 3840×2180 at 60 FPS. Built on Unreal Engine. Multiplayer by default. Persistent by default. Gameplay-ready by default. This is not a video latent replay. Not a simulation of interaction. It is a real 3D world with physics, logic, and authoritative multiplayer state. Avalon is trained on proprietary Avalon interaction data and powered by a hybrid system that combines language understanding, 3D model generation, procedural systems, and structured gameplay logic synthesis. Players can walk through a live world and generate environments, assets, mechanics, and entirely new gameplay modes using natural language. We accomplish this through a combination of 3D model generation, game logic generation based on our proprietary systems, and AI driven world creation. While other players are inside it. Changes persist instantly. State is synchronized in real time. Creation happens inside the world, not outside of it. Describe a biome. Spawn a civilization. Create a survival mode. Build a dungeon crawler. Launch a new game inside the world. Avalon interprets intent and integrates it directly into the live multiplayer environment. This is not a world model predicting video. This is a gameplay engine that understands language. If you can describe it, you can build it. And others can walk into it instantly.

AVALON

64,992 просмотров • 7 месяцев назад

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

zostaff

230,988 просмотров • 4 месяцев назад

Sukhendu Das, IIT Madras professor: "Jump Trading pays a 23 year old $500,000 a year for one skill: given the odds, pick the one move that makes the most money on average. that rule is the first thing this professor proves on a free chalkboard, and it costs nothing" this free lecture is the decision rule sitting under every trading bot and every hedge fund model on the planet. strip away the AI and the neural nets and one question is left. given everything you know right now, what is the single best bet. there is a mathematically correct answer. it is called the Bayes decision rule, and it turns a probability into the one action that maximizes your payoff. every profitable bot is just this rule running fast. Das builds it from zero, on a blackboard, in notation a beginner can follow. the odds go in, the optimal bet comes out. Wall Street rents this out as a $500,000 edge. an IIT professor hands you the rule itself for nothing.

Sukhendu Das, IIT Madras professor: "Jump Trading pays a 23 year old $500,000 a year for one skill: given the odds, pick the one move that makes the most money on average. that rule is the first thing this professor proves on a free chalkboard, and it costs nothing" this free lecture is the decision rule sitting under every trading bot and every hedge fund model on the planet. strip away the AI and the neural nets and one question is left. given everything you know right now, what is the single best bet. there is a mathematically correct answer. it is called the Bayes decision rule, and it turns a probability into the one action that maximizes your payoff. every profitable bot is just this rule running fast. Das builds it from zero, on a blackboard, in notation a beginner can follow. the odds go in, the optimal bet comes out. Wall Street rents this out as a $500,000 edge. an IIT professor hands you the rule itself for nothing.

Rossst.03

69,755 просмотров • 16 дней назад

Runway has unveiled a massive breakthrough in AI video generation at NVIDIA's GTC event, showcasing a new model capable of generating high-definition video in genuine real-time. The new model boasts a "time-to-first-frame" of under 100 milliseconds. This means HD video begins generating and playing almost the instant a command is given. This research preview was co-developed with NVIDIA and runs on their newly announced Vera Rubin architecture. This real-time capability is a foundational step for Runway's General World Model (GWM-1). It pushes the technology beyond simple video generation and into the realm of live, interactive environments.

Runway has unveiled a massive breakthrough in AI video generation at NVIDIA's GTC event, showcasing a new model capable of generating high-definition video in genuine real-time. The new model boasts a "time-to-first-frame" of under 100 milliseconds. This means HD video begins generating and playing almost the instant a command is given. This research preview was co-developed with NVIDIA and runs on their newly announced Vera Rubin architecture. This real-time capability is a foundational step for Runway's General World Model (GWM-1). It pushes the technology beyond simple video generation and into the realm of live, interactive environments.

Wes Roth

82,506 просмотров • 5 месяцев назад

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):

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

32,331 просмотров • 1 месяц назад

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 просмотров • 6 месяцев назад

This is so cool. Tesla can take footage from its massive vehicle fleet and synthetically create new driving scenarios to test edge cases and improve safety for its self-driving software. Tesla can also stitch footage from all 8 cameras into a fully drivable 3D environment—letting engineers steer, brake, and navigate as if they were on real roads, all powered by neural network–generated video streams. • Can simulate 8 Tesla camera feeds simultaneously — fully synthetic. • Used for testing, training, and reinforcement learning. • Allows adversarial event injection (e.g., adding a pedestrian or vehicle cutting in). • Enables replaying past failures to verify new model improvements. • Can run in near real-time, letting testers “drive” inside a simulated world.

This is so cool. Tesla can take footage from its massive vehicle fleet and synthetically create new driving scenarios to test edge cases and improve safety for its self-driving software. Tesla can also stitch footage from all 8 cameras into a fully drivable 3D environment—letting engineers steer, brake, and navigate as if they were on real roads, all powered by neural network–generated video streams. • Can simulate 8 Tesla camera feeds simultaneously — fully synthetic. • Used for testing, training, and reinforcement learning. • Allows adversarial event injection (e.g., adding a pedestrian or vehicle cutting in). • Enables replaying past failures to verify new model improvements. • Can run in near real-time, letting testers “drive” inside a simulated world.

Sawyer Merritt

591,824 просмотров • 10 месяцев назад

How do you know your robot actually succeeded? In v0.6.0, you ask a VLM 🤖 LeRobot ships a new unified reward models API with two zero-shot additions. Robometer is a general-purpose reward model trained on 1M+ trajectories across 21 robot embodiments: point it at any LeRobot dataset and it scores task progress and success straight from video and a language instruction, no task-specific training needed. TOPReward goes even further: no reward weights at all. It wraps an off-the-shelf VLM and reads the log-probability of the token "True" given the video and the instruction. Both come with labeling scripts that write per-frame progress curves into your dataset, ready for reward-aware behavior cloning. More on how they work:

How do you know your robot actually succeeded? In v0.6.0, you ask a VLM 🤖 LeRobot ships a new unified reward models API with two zero-shot additions. Robometer is a general-purpose reward model trained on 1M+ trajectories across 21 robot embodiments: point it at any LeRobot dataset and it scores task progress and success straight from video and a language instruction, no task-specific training needed. TOPReward goes even further: no reward weights at all. It wraps an off-the-shelf VLM and reads the log-probability of the token "True" given the video and the instruction. Both come with labeling scripts that write per-frame progress curves into your dataset, ready for reward-aware behavior cloning. More on how they work:

LeRobot

22,358 просмотров • 2 месяцев назад

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.

Robotics has a massive, silent bottleneck. It isn’t just data collection—it’s the brutal 1x speed of the physical world. Genesis AI Genesis AI just unveiled Genesis World 1.0, and they are attempting to turn the notorious Sim2Real gap into a pure compute problem. Evaluating a robotics foundation model across edge cases usually means hundreds of hours of physical lab testing. With Genesis World 1.0, what traditionally takes nearly a week of continuous, real-world operation is being compressed into 30 minutes in simulation. What makes this different from just dropping a robot model into an off-the-shelf game engine? 1️⃣ Nyx Renderer: A custom, real-time path-traced engine rendering noise-free 1080p frames in under 4ms. Game engines use rasterization tricks that confuse AI; Nyx uses physically accurate multi-bounce lighting so the model's "eyes" see exactly what real sensors see. 2️⃣ Quadrants Compiler: A custom Python-to-GPU compiler to run heavily parallelized multi-physics simulations (rigid bodies, fluids, deformables) natively across architectures. 3️⃣ Evaluation First: They aren't rushing to train on synthetic data. They are using this purely for closed-loop evaluation to perfect the physics first, currently claiming an impressive 89% correlation with real-world hardware tests. If the industry can accurately evaluate models in simulation without the physical world bottleneck, humanoid development stops moving at wall-clock time and starts scaling with compute.

Humanoids daily

17,302 просмотров • 3 месяцев назад

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

Andrew Ng

89,792 просмотров • 1 год назад

AI TENNIS ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, PYTORCH, AND KEYPOINT EXTRACTION. Take any tennis match broadcast, any camera angle, any resolution. Feed it into the pipeline. YOLO detects both players and the tennis ball frame by frame. No manual labeling, no pre-annotated dataset. A fine-tuned YOLOv5 model trained on a Roboflow tennis ball dataset handles the ball - the hardest object to track in any sport. Tiny, fast, constantly occluded. The model finds it anyway. Trackers maintain identity across frames so Player 1 stays Player 1 from the first serve to match point. But detection is just the start. A ResNet50 CNN trained in PyTorch predicts court keypoints from every frame - the corners, service lines, baselines, net posts. Fourteen points that define the entire playing surface geometry. From those keypoints the system builds a homography matrix and warps the broadcast perspective into a top-down mini court with real coordinates. Now every player has a position in real space, not pixel space. Every frame becomes a measurement. Every rally becomes a dataset. Player movement speed - calculated from position deltas between frames, converted to meters per second through the homography. Ball shot speed - measured from the ball trajectory across consecutive detections. Number of shots per rally - counted automatically through ball direction changes. All of this rendered live on the video as an overlay. A mini court in the corner showing both players as dots moving in real time. Stats updating after every point. OpenCV handles the rendering. Pandas handles the math. PyTorch handles the intelligence. YOLO handles the eyes. No Hawkeye subscription, no court-embedded sensors, no tracking chips in the ball. A Python script, a trained model, and a GPU. The full code is on GitHub. The tutorial walks through every module - from ball detector training to court keypoint extraction to the final statistical overlay. Professional teams used to need broadcast deals and proprietary hardware for this kind of analysis. Now you build it in an afternoon with open-source tools. Trading here: Computer vision didn't just enter tennis. It made the expensive stuff free.

AI TENNIS ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, PYTORCH, AND KEYPOINT EXTRACTION. Take any tennis match broadcast, any camera angle, any resolution. Feed it into the pipeline. YOLO detects both players and the tennis ball frame by frame. No manual labeling, no pre-annotated dataset. A fine-tuned YOLOv5 model trained on a Roboflow tennis ball dataset handles the ball - the hardest object to track in any sport. Tiny, fast, constantly occluded. The model finds it anyway. Trackers maintain identity across frames so Player 1 stays Player 1 from the first serve to match point. But detection is just the start. A ResNet50 CNN trained in PyTorch predicts court keypoints from every frame - the corners, service lines, baselines, net posts. Fourteen points that define the entire playing surface geometry. From those keypoints the system builds a homography matrix and warps the broadcast perspective into a top-down mini court with real coordinates. Now every player has a position in real space, not pixel space. Every frame becomes a measurement. Every rally becomes a dataset. Player movement speed - calculated from position deltas between frames, converted to meters per second through the homography. Ball shot speed - measured from the ball trajectory across consecutive detections. Number of shots per rally - counted automatically through ball direction changes. All of this rendered live on the video as an overlay. A mini court in the corner showing both players as dots moving in real time. Stats updating after every point. OpenCV handles the rendering. Pandas handles the math. PyTorch handles the intelligence. YOLO handles the eyes. No Hawkeye subscription, no court-embedded sensors, no tracking chips in the ball. A Python script, a trained model, and a GPU. The full code is on GitHub. The tutorial walks through every module - from ball detector training to court keypoint extraction to the final statistical overlay. Professional teams used to need broadcast deals and proprietary hardware for this kind of analysis. Now you build it in an afternoon with open-source tools. Trading here: Computer vision didn't just enter tennis. It made the expensive stuff free.

zostaff

120,370 просмотров • 4 месяцев назад

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Over the Reality 🌐

400,269 просмотров • 4 месяцев назад

Sora 2 has changed the game, the world of video will never be the same. A model that doesn't just generate visuals, it simulates the physical world. It understands how the world moves, how light behaves, and how sound interacts within a scene. Every frame carries a physical truth that turns imagination into reality. Sora 2: → understands how the world moves, from physics to light to sound → makes imagination look real, indistinguishable from a camera-led shoot → gives creators precise control over shots, edits and every visual detail And now it’s inside invideo. invideo's agent acts like an AI production house, making 500 creative decisions autonomously to turn a single prompt into a complete video, researching the topic, writing the script, generating and evaluating storyboards, directing and editing autonomously. We’re featured today at OpenAI Dev Day OpenAI Developers, showing what’s now possible when creators and businesses can use the world’s most advanced video model. The line between imagination and reality just blurred. Examples of what you can now create with Sora 2 👇

Sora 2 has changed the game, the world of video will never be the same. A model that doesn't just generate visuals, it simulates the physical world. It understands how the world moves, how light behaves, and how sound interacts within a scene. Every frame carries a physical truth that turns imagination into reality. Sora 2: → understands how the world moves, from physics to light to sound → makes imagination look real, indistinguishable from a camera-led shoot → gives creators precise control over shots, edits and every visual detail And now it’s inside invideo. invideo's agent acts like an AI production house, making 500 creative decisions autonomously to turn a single prompt into a complete video, researching the topic, writing the script, generating and evaluating storyboards, directing and editing autonomously. We’re featured today at OpenAI Dev Day OpenAI Developers, showing what’s now possible when creators and businesses can use the world’s most advanced video model. The line between imagination and reality just blurred. Examples of what you can now create with Sora 2 👇

Sanket Shah

63,297 просмотров • 11 месяцев назад

$GME GameStop is going to unlock a new economy! 🚨🚨🚨 Listen to this segment from Ryan Cohen in today’s All-In podcast. Ryan Cohen announced he’ll use eBay to build a NEW digital marketplace for in-game items. This is something that has never been done before and it changes everything: Every skin, weapon, virtual item, or asset you earn in games suddenly has real-world tradable value. What you own in a game becomes a true asset you can buy, sell, or cash out (just like stocks or physical goods). This is a MASSIVE deal! It turns gaming from pure entertainment into a REAL EARNING ECONOMY. Players get actual ownership and liquidity for their time and skill, creators can build thriving secondary markets, and the entire industry shifts toward player-owned economies at scale. Ryan Cohen is going to finally unlock the gaming economy.

$GME GameStop is going to unlock a new economy! 🚨🚨🚨 Listen to this segment from Ryan Cohen in today’s All-In podcast. Ryan Cohen announced he’ll use eBay to build a NEW digital marketplace for in-game items. This is something that has never been done before and it changes everything: Every skin, weapon, virtual item, or asset you earn in games suddenly has real-world tradable value. What you own in a game becomes a true asset you can buy, sell, or cash out (just like stocks or physical goods). This is a MASSIVE deal! It turns gaming from pure entertainment into a REAL EARNING ECONOMY. Players get actual ownership and liquidity for their time and skill, creators can build thriving secondary markets, and the entire industry shifts toward player-owned economies at scale. Ryan Cohen is going to finally unlock the gaming economy.

GregisKitty

43,140 просмотров • 2 месяцев назад

Your ai agent is genuinely smart right up until it has to do something in the real world ask it to host a site, send an email, scrape a page, take a payment, and the magic stops. now you're the one doing the boring part: → hunting api keys → paying for subscriptions you'll use once → gluing integrations together → losing an afternoon to config files i gave my agent access to Zero instead and just described the job. it built and hosted a full ai tool marketplace, 120+ tools, live on a real url, and i configured nothing. no keys, no dashboards, no setup zero plugs agents into 14,000+ real services on demand. everything runs on pay-per-use microtransactions, so you pay for the one call you make, not a monthly plan you forget about what's the one task your agent still can't do on its own? that's exactly the gap this closes $5 free credit → #Ad

Your ai agent is genuinely smart right up until it has to do something in the real world ask it to host a site, send an email, scrape a page, take a payment, and the magic stops. now you're the one doing the boring part: → hunting api keys → paying for subscriptions you'll use once → gluing integrations together → losing an afternoon to config files i gave my agent access to Zero instead and just described the job. it built and hosted a full ai tool marketplace, 120+ tools, live on a real url, and i configured nothing. no keys, no dashboards, no setup zero plugs agents into 14,000+ real services on demand. everything runs on pay-per-use microtransactions, so you pay for the one call you make, not a monthly plan you forget about what's the one task your agent still can't do on its own? that's exactly the gap this closes $5 free credit → #Ad

Freya Lawson

80,316 просмотров • 2 месяцев назад

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

ComfyUI

13,174 просмотров • 1 месяц назад