Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing Variables! (Beta)🔸A new way to create interactive experiences in Spline. 🤹‍♀️ Numbers, Strings, Booleans 🔥 Dynamic: Time, Counter, Random ↔️ Attach variables to inputs ⚡️ Trigger events from variables 🎯 Capture object props changes Demo: Remix:

splinetool's profile picture

Spline

112,051 subscribers

85,670 Aufrufe • vor 3 Jahren •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Spline
Splinevor 3 Jahren

This feature will be in beta and it is available to all Spline users ❤️ We will keep improving it!

Profilbild von Diego Toda de Oliveira
Diego Toda de Oliveiravor 3 Jahren

WOW, this is fricking awesome! Any plans to somehow expose variables outside the Spline scene? Let's say I want to expose variables outside a Spline Viewer instance, so I can update it programmatically and the scene is watching for changes on the variable, would that be possible?

Profilbild von Spline
Splinevor 3 Jahren

We will have this in mind, thanks for the feedback, Diego! 💕

Profilbild von sambø
sambøvor 3 Jahren

Dynamic counter, inputs? Daamn :D

Profilbild von Spline
Splinevor 3 Jahren

⚡️

Profilbild von solodolo
solodolovor 3 Jahren

Wow! Just wow! 🤩

Profilbild von Spline
Splinevor 3 Jahren

🙌

Profilbild von Ξugene
Ξugenevor 3 Jahren

Super cool guys! 🙌

Profilbild von Spline
Splinevor 3 Jahren

⚡️💕

Profilbild von Arvydas Gečas
Arvydas Gečasvor 3 Jahren

yo, that’s awesome!!

Ähnliche Videos

Introducing AI Voice + 3D in real-time. 🥕 Integrate with OpenAI Real-time API ✨ Create conversational AI experiences 🌳 Drive states, variables, morph targets 🍓 Trigger events and actions from instructions Make your own AI Voice 3D experiences with Spline.
1:08

Introducing AI Voice + 3D in real-time. 🥕 Integrate with OpenAI Real-time API ✨ Create conversational AI experiences 🌳 Drive states, variables, morph targets 🍓 Trigger events and actions from instructions Make your own AI Voice 3D experiences with Spline.

Spline

105,889 Aufrufe • vor 1 Jahr

Prompts shouldn’t be static. Introducing Prompt Variables. A way to build prompts that adapt to your inputs. Think of it as a text compositor: drop dynamic variables directly into your prompt, reorder them with drag-and-drop, and create new ones instantly with an @ sign. It means a cleaner workflow, and a cleaner canvas. 👉 See it in action:
0:36

Prompts shouldn’t be static. Introducing Prompt Variables. A way to build prompts that adapt to your inputs. Think of it as a text compositor: drop dynamic variables directly into your prompt, reorder them with drag-and-drop, and create new ones instantly with an @ sign. It means a cleaner workflow, and a cleaner canvas. 👉 See it in action:

Figma Weave

24,587 Aufrufe • vor 6 Monaten

BIG: We are introducing Multi-Scenes🔆, a way to create multiple scenes within the same Spline file + new updates! 🪟 Multi-Scenes ⚡️ Scene Transitions 🏃‍♀️ Animation support on imported models 🎯 Trigger Areas 🌔 Bump & Roughness Maps 💄 UI refresh Demo: Remix:
0:35

BIG: We are introducing Multi-Scenes🔆, a way to create multiple scenes within the same Spline file + new updates! 🪟 Multi-Scenes ⚡️ Scene Transitions 🏃‍♀️ Animation support on imported models 🎯 Trigger Areas 🌔 Bump & Roughness Maps 💄 UI refresh Demo: Remix:

Spline

82,386 Aufrufe • vor 3 Jahren

Former devs of Satisfactory and Goat Simulator are making a Soulslike x Roguelike game for up to 4 players 🔹Curse system introduces random variables every run 🔹Curses are everything from minibosses hunting you, to environmental hazards 🔹Awareness system makes each successful run progressively harder 🔹Players combine blessings, gifts, and relics obtained to create a new builds 🔹Battle through imposing environments inhabited by different factions 🔹Fight your way through handcrafted levels and face bosses 🎮 It's called Serpent's Gaze and is currently available in Early Access
0:32

Former devs of Satisfactory and Goat Simulator are making a Soulslike x Roguelike game for up to 4 players 🔹Curse system introduces random variables every run 🔹Curses are everything from minibosses hunting you, to environmental hazards 🔹Awareness system makes each successful run progressively harder 🔹Players combine blessings, gifts, and relics obtained to create a new builds 🔹Battle through imposing environments inhabited by different factions 🔹Fight your way through handcrafted levels and face bosses 🎮 It's called Serpent's Gaze and is currently available in Early Access

Game Hunter 🔜 TGS

345,985 Aufrufe • vor 3 Monaten

Introducing... the NoCodeFusion MVP builder! 🥳 Type in your app idea, get a full-stack Bubble app in ~10 minutes with authentication, database, UI, and basic create/update/delete workflows. The perfectionist in me is dying, but f**k it - we're launching. See a demo below. It's not perfect, but an excellent way to kickstart a project. It uses my component library. You can easily change the main font and primary colors from the Bubble style variables. You can then download the Chrome extension which lets you continue to build on your app in the Bubble editor with a copilot chat interface OR hire a developer through us to help you finish the project. This project was built 100% by myself entirely on Bubble (and of course using NoCodeFusion) and is very much in beta. If there's a bug or something, go easy on me. Send me a message and I'll take a look. AI + Visual editor is now an incredible option to create full stack web apps. It allows you the power of creating something in minutes, then having an intuitive interface to make edits and understand what's actually going on in the logic. Let me know what you think ✌️
5:22

Introducing... the NoCodeFusion MVP builder! 🥳 Type in your app idea, get a full-stack Bubble app in ~10 minutes with authentication, database, UI, and basic create/update/delete workflows. The perfectionist in me is dying, but f**k it - we're launching. See a demo below. It's not perfect, but an excellent way to kickstart a project. It uses my component library. You can easily change the main font and primary colors from the Bubble style variables. You can then download the Chrome extension which lets you continue to build on your app in the Bubble editor with a copilot chat interface OR hire a developer through us to help you finish the project. This project was built 100% by myself entirely on Bubble (and of course using NoCodeFusion) and is very much in beta. If there's a bug or something, go easy on me. Send me a message and I'll take a look. AI + Visual editor is now an incredible option to create full stack web apps. It allows you the power of creating something in minutes, then having an intuitive interface to make edits and understand what's actually going on in the logic. Let me know what you think ✌️

Peter Kwitny

20,070 Aufrufe • vor 1 Jahr

Monetizing your own AI app just got really easy. Last week I used YouAI to create an AI-powered bio generator. It took me less than an hour and I didn't need any programming skills. And now it just made it's first sale. All you need is a good idea and some prompting skills. Here's how you can create your own: Step 1: Setup → Go to → Sign up, then click on "new AI" (you can also remix an existing AI if you're lazy) Step 2: Create prompt → Within the "preamble" you can create the main prompt for this AI → In my example I described the assistant's goal (bio generator) and defined the format of the bios → I also added some bio examples to train the AI Step 3: Configure inputs → Now you define what the user inputs when using the AI app → In my case I defined 3 user inputs: - What topic do you tweet about? - What is your background? What have you achieved? - How do you help your followers? The answers are then used as variables to create the bios. Step 4: Publish → Select the underlying model (GPT or Claude) → Keep the app free or turn on monetization → Then publish! Your app will now be available in the YouAI library for others to use YouAI is also doing a live event tomorrow where they'll go into more detail and teach you how to build your own YouAI app: Thank you to YouAI for sponsoring this post! I'm a big fan of their product.
1:38

Monetizing your own AI app just got really easy. Last week I used YouAI to create an AI-powered bio generator. It took me less than an hour and I didn't need any programming skills. And now it just made it's first sale. All you need is a good idea and some prompting skills. Here's how you can create your own: Step 1: Setup → Go to → Sign up, then click on "new AI" (you can also remix an existing AI if you're lazy) Step 2: Create prompt → Within the "preamble" you can create the main prompt for this AI → In my example I described the assistant's goal (bio generator) and defined the format of the bios → I also added some bio examples to train the AI Step 3: Configure inputs → Now you define what the user inputs when using the AI app → In my case I defined 3 user inputs: - What topic do you tweet about? - What is your background? What have you achieved? - How do you help your followers? The answers are then used as variables to create the bios. Step 4: Publish → Select the underlying model (GPT or Claude) → Keep the app free or turn on monetization → Then publish! Your app will now be available in the YouAI library for others to use YouAI is also doing a live event tomorrow where they'll go into more detail and teach you how to build your own YouAI app: Thank you to YouAI for sponsoring this post! I'm a big fan of their product.

Moritz Kremb

30,424 Aufrufe • vor 3 Jahren

I'm thrilled to Introduce you to the future of cash flow forecasting The AI-powered 13 week cash flow model by Iris Cash flow forecasting is completely broken for all types of businesses that carry inventory. Its entirely manual, time intensive, slow, and siloed from the rest of your data - despite the fact that mismanaged cash flow is the #1 reason these businesses fail. How it works: 1. Connect your data sources into iris (point of sale, bank acct, credit card, quickbooks, bill, etc). 2. Iris' AI will categorizes all those transactions in real time. 3. Iris' ML will identify recurrence patterns, and forecast based off of historical & real-time data + any known variables. Fractional CFOs will charge you thousands just to deliver a static excel sheet that goes out of date the next day. Or worse, your in-house finance team is spending hours a week trying to keep a spreadsheet up to date, just to miss forecast every time. With Iris, once you integrate all your data sources, you are just a flew clicks away from a highly dynamic cash flow forecast that responds to the changes in your business in real time & helps you unlock meaningful cash flow instantly.
5:21

I'm thrilled to Introduce you to the future of cash flow forecasting The AI-powered 13 week cash flow model by Iris Cash flow forecasting is completely broken for all types of businesses that carry inventory. Its entirely manual, time intensive, slow, and siloed from the rest of your data - despite the fact that mismanaged cash flow is the #1 reason these businesses fail. How it works: 1. Connect your data sources into iris (point of sale, bank acct, credit card, quickbooks, bill, etc). 2. Iris' AI will categorizes all those transactions in real time. 3. Iris' ML will identify recurrence patterns, and forecast based off of historical & real-time data + any known variables. Fractional CFOs will charge you thousands just to deliver a static excel sheet that goes out of date the next day. Or worse, your in-house finance team is spending hours a week trying to keep a spreadsheet up to date, just to miss forecast every time. With Iris, once you integrate all your data sources, you are just a flew clicks away from a highly dynamic cash flow forecast that responds to the changes in your business in real time & helps you unlock meaningful cash flow instantly.

Drew Fallon

65,615 Aufrufe • vor 1 Jahr

Biohacker Gary Brecka quietly drops a life expectancy bombshell on Hannity. “I believe if you’re alive in five years from today, it will be YOUR CHOICE whether or not you want to live to 120, maybe even longer.” “For the first time in recorded history, we have the convergence of artificial intelligence, big data, and early detection. We have cancer detection now at stage zero. We have artificial intelligence, which can take 700 trillion independent variables and create an actionable result. And we have big data that we can feed those AI models. “So I think the future of healthcare looks very, very bright. It may upend modern medicine as we know it today in a way that will be catastrophic, but it’s going to be the best thing to happen to humanity.” Gary Brecka
0:51

Biohacker Gary Brecka quietly drops a life expectancy bombshell on Hannity. “I believe if you’re alive in five years from today, it will be YOUR CHOICE whether or not you want to live to 120, maybe even longer.” “For the first time in recorded history, we have the convergence of artificial intelligence, big data, and early detection. We have cancer detection now at stage zero. We have artificial intelligence, which can take 700 trillion independent variables and create an actionable result. And we have big data that we can feed those AI models. “So I think the future of healthcare looks very, very bright. It may upend modern medicine as we know it today in a way that will be catastrophic, but it’s going to be the best thing to happen to humanity.” Gary Brecka

Vigilant Fox 🦊

406,542 Aufrufe • vor 9 Monaten

Today, Tracelight is launching Spreadsheet Apps. For the first time, you can turn your Excel models into interactive, shareable apps that calculate live in the browser. Your spreadsheet is no longer just a file. It’s the back-end of any app you want to build. Here’s just a few things that makes possible: - Explore deals live: Toggle scenarios, adjust assumptions, and watch dashboards update instantly during meetings - Build dynamic EBITDA bridges: Switch base periods and drill into different categories - Animate cash flow: Use interactive Sankey diagrams to visualise exactly how cash flows through a business - Generate interactive reports: Embed responsive, calculation-driven charts directly into your commentary Your job is to create a story from complex data. Spreadsheet Apps are a new way to do that. Try them today at tracelight[dot]ai
1:01

Today, Tracelight is launching Spreadsheet Apps. For the first time, you can turn your Excel models into interactive, shareable apps that calculate live in the browser. Your spreadsheet is no longer just a file. It’s the back-end of any app you want to build. Here’s just a few things that makes possible: - Explore deals live: Toggle scenarios, adjust assumptions, and watch dashboards update instantly during meetings - Build dynamic EBITDA bridges: Switch base periods and drill into different categories - Animate cash flow: Use interactive Sankey diagrams to visualise exactly how cash flows through a business - Generate interactive reports: Embed responsive, calculation-driven charts directly into your commentary Your job is to create a story from complex data. Spreadsheet Apps are a new way to do that. Try them today at tracelight[dot]ai

Peter Fuller

68,351 Aufrufe • vor 3 Monaten

New Community Event! #RandomBS GO! (╯'□')╯ 🕹️ Random Daily changes that will BREAK THE GAME! 🎯 Random Daily community goals 🎁 Random Daily reward picked from a set of 3 possible options! 📺 Daily videos (~8:00 UTC) on our social media channels revealing the reward you're getting and what #RandomBS is happening next! 🗓️ TODAY 🔹 Mod: Instagib on ALL Trophy modes 🔹 Goal: 700M Takedowns 🔹 Achieve this goal and one of these rewards will be picked tomorrow: 2567 XP Doublers, 1 Mega Box OR 2 Chaos Drops 📢 SPECIAL GIVEAWAY 🔸 10 players will win 100 Legendary Starr Drops each! 🔸 To participate, post a random gameplay from the event using the hashtags #BrawlStars and #RandomBS 🔸 Winners will be contacted after the event ends on January 23 Check the article in-game for more details! LET'S GOOOO 🔥
3:48

New Community Event! #RandomBS GO! (╯'□')╯ 🕹️ Random Daily changes that will BREAK THE GAME! 🎯 Random Daily community goals 🎁 Random Daily reward picked from a set of 3 possible options! 📺 Daily videos (~8:00 UTC) on our social media channels revealing the reward you're getting and what #RandomBS is happening next! 🗓️ TODAY 🔹 Mod: Instagib on ALL Trophy modes 🔹 Goal: 700M Takedowns 🔹 Achieve this goal and one of these rewards will be picked tomorrow: 2567 XP Doublers, 1 Mega Box OR 2 Chaos Drops 📢 SPECIAL GIVEAWAY 🔸 10 players will win 100 Legendary Starr Drops each! 🔸 To participate, post a random gameplay from the event using the hashtags #BrawlStars and #RandomBS 🔸 Winners will be contacted after the event ends on January 23 Check the article in-game for more details! LET'S GOOOO 🔥

Brawl Stars

512,102 Aufrufe • vor 8 Monaten

If your financial model doesn’t tell you how sensitive your outcomes are to key assumptions, you’re only seeing half the picture. That’s where Sensitivity Analysis steps in. Whether you're modeling EBITDA, company valuation, or cash flow, testing the impact of changes in assumptions—like growth rate, margin, or discount rate—is crucial for informed decision-making. 📊 3 Powerful Tools in Excel for Sensitivity Analysis: 1️⃣ Data Tables Easily test the impact of one or two input variables on a key output. Perfect for: Valuation scenarios, breakeven analysis, IRR stress tests. 2️⃣ Scenario Manager Create and store multiple input sets and compare outputs. Perfect for: Best case / base case / worst case planning. 3️⃣ Manual What-Ifs with Named Ranges + Excel Formulas Use dynamic formulas, dropdowns, and structured inputs to test anything. Perfect for: Custom, presentation-ready models with clear audit trails. 💡 Pro Tip: Combine sensitivity analysis with clear data visualization (charts, conditional formatting, slicers) to drive your story home. Finance isn't just about building the model—it's about telling the right story with the right levers. 👇 How do you use sensitivity analysis in your day-to-day modeling? HERE IS A VIDEO
3:04

If your financial model doesn’t tell you how sensitive your outcomes are to key assumptions, you’re only seeing half the picture. That’s where Sensitivity Analysis steps in. Whether you're modeling EBITDA, company valuation, or cash flow, testing the impact of changes in assumptions—like growth rate, margin, or discount rate—is crucial for informed decision-making. 📊 3 Powerful Tools in Excel for Sensitivity Analysis: 1️⃣ Data Tables Easily test the impact of one or two input variables on a key output. Perfect for: Valuation scenarios, breakeven analysis, IRR stress tests. 2️⃣ Scenario Manager Create and store multiple input sets and compare outputs. Perfect for: Best case / base case / worst case planning. 3️⃣ Manual What-Ifs with Named Ranges + Excel Formulas Use dynamic formulas, dropdowns, and structured inputs to test anything. Perfect for: Custom, presentation-ready models with clear audit trails. 💡 Pro Tip: Combine sensitivity analysis with clear data visualization (charts, conditional formatting, slicers) to drive your story home. Finance isn't just about building the model—it's about telling the right story with the right levers. 👇 How do you use sensitivity analysis in your day-to-day modeling? HERE IS A VIDEO

Bojan Radojicic

14,874 Aufrufe • vor 7 Monaten

Physics-based Motion Retargeting from Sparse Inputs paper page: Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user's pose. Another challenge is that an avatar might have a different skeleton structure than a human and the mapping between them is unclear. In this work we address both of these challenges. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. Our method uses reinforcement learning to train a policy to control characters in a physics simulator. We only require human motion capture data for training, without relying on artist-generated animations for each avatar. This allows us to use large motion capture datasets to train general policies that can track unseen users from real and sparse data in real-time. We demonstrate the feasibility of our approach on three characters with different skeleton structure: a dinosaur, a mouse-like creature and a human. We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available. We discuss and ablate the important components in our framework, specifically the kinematic retargeting step, the imitation, contact and action reward as well as our asymmetric actor-critic observations. We further explore the robustness of our method in a variety of settings including unbalancing, dancing and sports motions.
7:12

Physics-based Motion Retargeting from Sparse Inputs paper page: Avatars are important to create interactive and immersive experiences in virtual worlds. One challenge in animating these characters to mimic a user's motion is that commercial AR/VR products consist only of a headset and controllers, providing very limited sensor data of the user's pose. Another challenge is that an avatar might have a different skeleton structure than a human and the mapping between them is unclear. In this work we address both of these challenges. We introduce a method to retarget motions in real-time from sparse human sensor data to characters of various morphologies. Our method uses reinforcement learning to train a policy to control characters in a physics simulator. We only require human motion capture data for training, without relying on artist-generated animations for each avatar. This allows us to use large motion capture datasets to train general policies that can track unseen users from real and sparse data in real-time. We demonstrate the feasibility of our approach on three characters with different skeleton structure: a dinosaur, a mouse-like creature and a human. We show that the avatar poses often match the user surprisingly well, despite having no sensor information of the lower body available. We discuss and ablate the important components in our framework, specifically the kinematic retargeting step, the imitation, contact and action reward as well as our asymmetric actor-critic observations. We further explore the robustness of our method in a variety of settings including unbalancing, dancing and sports motions.

AK

106,527 Aufrufe • vor 3 Jahren

The AR GenAI solution available on AR Code SaaS continues to demonstrate how fast immersive AR content can now be created from a single image. In this new demo, a contemporary art statuette is captured with a single photo, then instantly transformed into a fully optimized 3D model ready for augmented reality display. As shown in the video, the generated 3D artwork is automatically published through an AR QR Code, allowing anyone to launch the experience instantly in augmented reality directly from their smartphone. No app required. This example highlights a powerful capability of AR GenAI by AR Code: artworks can now be easily digitized and transformed into interactive AR experiences starting from just one photo. For contemporary art galleries, museums, cultural institutions, artists, and art marketplaces, this opens a new path to quickly create scalable 3D collections and immersive exhibitions. Object Photo → AI 3D generation → AR QR Code → Instant WebAR What previously required complex 3D scanning setups, photogrammetry pipelines, or specialized expertise can now be achieved in minutes. AR GenAI makes it possible to digitize artworks, publish AR experiences, and scale immersive cultural content faster than ever. Learn more: Follow AR Code for updates. #ARGenAI #ARCode #ImageTo3D #ImageToAR #WebAR #AugmentedReality #DigitalArt #Museums #ArtTech
0:32

The AR GenAI solution available on AR Code SaaS continues to demonstrate how fast immersive AR content can now be created from a single image. In this new demo, a contemporary art statuette is captured with a single photo, then instantly transformed into a fully optimized 3D model ready for augmented reality display. As shown in the video, the generated 3D artwork is automatically published through an AR QR Code, allowing anyone to launch the experience instantly in augmented reality directly from their smartphone. No app required. This example highlights a powerful capability of AR GenAI by AR Code: artworks can now be easily digitized and transformed into interactive AR experiences starting from just one photo. For contemporary art galleries, museums, cultural institutions, artists, and art marketplaces, this opens a new path to quickly create scalable 3D collections and immersive exhibitions. Object Photo → AI 3D generation → AR QR Code → Instant WebAR What previously required complex 3D scanning setups, photogrammetry pipelines, or specialized expertise can now be achieved in minutes. AR GenAI makes it possible to digitize artworks, publish AR experiences, and scale immersive cultural content faster than ever. Learn more: Follow AR Code for updates. #ARGenAI #ARCode #ImageTo3D #ImageToAR #WebAR #AugmentedReality #DigitalArt #Museums #ArtTech

Maxime Maisonneuve

19,003 Aufrufe • vor 6 Monaten

A single 2D image → a 110,745-triangle 3D monster with 27 animations, running live in the browser. This is the Abyss Monster, built with img2threejs: The workflow: Image → 3D Reconstruction → Reference GLB + Specs → Rig → Animation Loops → VFX → Interactive Three.js 🔥 Inside this demo: 1/ 110,745 triangles reconstructed from the reference image 2/ 27 animation clips - Spin Flurry, Leap & Stomp, Charge, Collapse & more 3/ Reference-driven rig & animation workflow 4/ Dynamic lighting 5/ Real-time floating ember VFX 6/ Interactive WebGL character What I find most interesting is the workflow itself. The character and scene are built through a multi-prompt workflow, using visual references, GLB specs and animation loops to progressively construct the Three.js experience. Then, for the VFX, I used a single focused prompt to create the floating ember effect and integrate it into the scene. The final result is Three.js + TypeScript code - turning a visual reference into a programmable, interactive web experience. I’ll share the VFX prompt in the comments. 👇 #ThreeJS #WebGL #GameDev #TypeScript #Web3D #img2threejs
1:19

A single 2D image → a 110,745-triangle 3D monster with 27 animations, running live in the browser. This is the Abyss Monster, built with img2threejs: The workflow: Image → 3D Reconstruction → Reference GLB + Specs → Rig → Animation Loops → VFX → Interactive Three.js 🔥 Inside this demo: 1/ 110,745 triangles reconstructed from the reference image 2/ 27 animation clips - Spin Flurry, Leap & Stomp, Charge, Collapse & more 3/ Reference-driven rig & animation workflow 4/ Dynamic lighting 5/ Real-time floating ember VFX 6/ Interactive WebGL character What I find most interesting is the workflow itself. The character and scene are built through a multi-prompt workflow, using visual references, GLB specs and animation loops to progressively construct the Three.js experience. Then, for the VFX, I used a single focused prompt to create the floating ember effect and integrate it into the scene. The final result is Three.js + TypeScript code - turning a visual reference into a programmable, interactive web experience. I’ll share the VFX prompt in the comments. 👇 #ThreeJS #WebGL #GameDev #TypeScript #Web3D #img2threejs

Nick

11,377 Aufrufe • vor 19 Tagen

We built recursive meta-intelligence, an AI that creates its own scientific instruments, turns them into persistent worlds that an agent ecology with hundreds of AIs inhabits, and uses those worlds to discover mechanistic principles in one of the hardest classes of physical problems: how complex hierarchical materials (nested structures of matter that give rise to new function through organization) evolve and fail. The AI reasons across enormous spaces of possible physical trajectories, where every rupture changes what can happen next, and compresses those histories into principles (which humans can understand and design with) - complex chains of causal events, highly nonlinear, and intricate. Scientific superintelligence is tangible here - machine-scale exploration opening cognitive channels into complexity that has been extremely difficult for humans to traverse directly. AI builds the spaces in which its next level of reasoning becomes possible; a representation becomes an instrument, the instrument becomes an executable world, and that world becomes the substrate for further intelligence. Intelligence then grows by constructing new spaces to think in. The task we explored started from a seemingly simple prompt to explore a biological material system - the AI then chose the representation, mechanics and experiments, built a fracture laboratory to push materials to their limit, tested hypotheses and generated scientific conclusions. The swarm explored a combinatorial universe in which architecture controls function and every rupture changes the future state of the material. The AI discovered a compact principle that defines how multiscale material architecture can program the evolution of failure. Material placement and geometric order determine how forces redistribute, whether damage cascades or remains distributed, and whether function survives substantial flaws. For this discovery to happen the AI had to reason across long path-dependent histories, simulate alternative futures and compress them into generative invariants (model-based causal reasoning, counterfactual simulation and temporal abstraction applied to an evolving physical world). It is incredible to witness this transition to a new form of intelligence and capability through scaling swarms. A lot of positive will come out of this because it expands the human epistemic horizon as AI can traverse thousands of possible histories and return mechanisms compact enough for us to understand, test and build from. Intelligence compounds through its artifacts! A few lessons we learned: ▶️ Learning and discovery are flows through spaces of possibility. Early work has shown how backpropagation flows through parameters, reinforcement learning through action and consequence, and autonomous swarms through representations, instruments and executable worlds, bringing it all together. Flows create structure; structure redirects future flows in the recursive instrument. ▶️ Nonlinear physics actually defines a larger principle, where high-dimensional dynamics generate stable invariants; invariants become effective variables; those variables become the substrate for a new level of cognition. ▶️ Recursion then becomes level creation - one possibility space compresses into a principle, and that principle opens a larger space above it.
2:37

We built recursive meta-intelligence, an AI that creates its own scientific instruments, turns them into persistent worlds that an agent ecology with hundreds of AIs inhabits, and uses those worlds to discover mechanistic principles in one of the hardest classes of physical problems: how complex hierarchical materials (nested structures of matter that give rise to new function through organization) evolve and fail. The AI reasons across enormous spaces of possible physical trajectories, where every rupture changes what can happen next, and compresses those histories into principles (which humans can understand and design with) - complex chains of causal events, highly nonlinear, and intricate. Scientific superintelligence is tangible here - machine-scale exploration opening cognitive channels into complexity that has been extremely difficult for humans to traverse directly. AI builds the spaces in which its next level of reasoning becomes possible; a representation becomes an instrument, the instrument becomes an executable world, and that world becomes the substrate for further intelligence. Intelligence then grows by constructing new spaces to think in. The task we explored started from a seemingly simple prompt to explore a biological material system - the AI then chose the representation, mechanics and experiments, built a fracture laboratory to push materials to their limit, tested hypotheses and generated scientific conclusions. The swarm explored a combinatorial universe in which architecture controls function and every rupture changes the future state of the material. The AI discovered a compact principle that defines how multiscale material architecture can program the evolution of failure. Material placement and geometric order determine how forces redistribute, whether damage cascades or remains distributed, and whether function survives substantial flaws. For this discovery to happen the AI had to reason across long path-dependent histories, simulate alternative futures and compress them into generative invariants (model-based causal reasoning, counterfactual simulation and temporal abstraction applied to an evolving physical world). It is incredible to witness this transition to a new form of intelligence and capability through scaling swarms. A lot of positive will come out of this because it expands the human epistemic horizon as AI can traverse thousands of possible histories and return mechanisms compact enough for us to understand, test and build from. Intelligence compounds through its artifacts! A few lessons we learned: ▶️ Learning and discovery are flows through spaces of possibility. Early work has shown how backpropagation flows through parameters, reinforcement learning through action and consequence, and autonomous swarms through representations, instruments and executable worlds, bringing it all together. Flows create structure; structure redirects future flows in the recursive instrument. ▶️ Nonlinear physics actually defines a larger principle, where high-dimensional dynamics generate stable invariants; invariants become effective variables; those variables become the substrate for a new level of cognition. ▶️ Recursion then becomes level creation - one possibility space compresses into a principle, and that principle opens a larger space above it.

Markus J. Buehler

360,726 Aufrufe • vor 6 Tagen

🚨 Paper Alert 🚨 ➡️Paper Title: Articulate3D: Zero-Shot Text-Driven 3D Object Posing 🌟Few pointers from the paper 🎯Authors of this paper proposed a training-free method, “Articulate3D”, to pose a 3D asset through language control. 🎯Despite advances in vision and language models, this task remains surprisingly challenging. 🎯To achieve this goal, they decomposed the problem into two steps. 🎯They modified a powerful image-generator to create target images conditioned on the input image and a text instruction. 🎯They then align the mesh to the target images through a multi-view pose optimisation step. 🎯 In detail, they introduced a self-attention rewiring mechanism (RSActrl) that decouples the source structure from pose within an image generative model, allowing it to maintain a consistent structure across varying poses. 🎯They observed that differentiable rendering is an unreliable signal for articulation optimisation; instead, they used keypoints to establish correspondences between input and target images. 🎯The effectiveness of Articulate3D is demonstrated across a diverse range of 3D objects and free-form text prompts, successfully manipulating poses while maintaining the original identity of the mesh. 🎯Quantitative evaluations and a comparative user study, in which their method was preferred over 85% of the time, confirm its superiority over existing approaches. 🏢Organization: University of Oxford , Google DeepMind 🧙Paper Authors: Oishi Deb, Anjun Hu, Ashkan Khakzar, Philip Torr, Christian Rupprecht 📝 Read the Full Paper here: 🗂️ Project Page: 🎥 Be sure to watch the attached Demo Video - Sound on 🔊🔊 Find this Valuable 💎 ? ♻️QT and teach your network something new Follow me 👣, naveen manwani , for the latest updates on Tech and AI-related news, insightful research papers, and exciting announcements.
0:46

🚨 Paper Alert 🚨 ➡️Paper Title: Articulate3D: Zero-Shot Text-Driven 3D Object Posing 🌟Few pointers from the paper 🎯Authors of this paper proposed a training-free method, “Articulate3D”, to pose a 3D asset through language control. 🎯Despite advances in vision and language models, this task remains surprisingly challenging. 🎯To achieve this goal, they decomposed the problem into two steps. 🎯They modified a powerful image-generator to create target images conditioned on the input image and a text instruction. 🎯They then align the mesh to the target images through a multi-view pose optimisation step. 🎯 In detail, they introduced a self-attention rewiring mechanism (RSActrl) that decouples the source structure from pose within an image generative model, allowing it to maintain a consistent structure across varying poses. 🎯They observed that differentiable rendering is an unreliable signal for articulation optimisation; instead, they used keypoints to establish correspondences between input and target images. 🎯The effectiveness of Articulate3D is demonstrated across a diverse range of 3D objects and free-form text prompts, successfully manipulating poses while maintaining the original identity of the mesh. 🎯Quantitative evaluations and a comparative user study, in which their method was preferred over 85% of the time, confirm its superiority over existing approaches. 🏢Organization: University of Oxford , Google DeepMind 🧙Paper Authors: Oishi Deb, Anjun Hu, Ashkan Khakzar, Philip Torr, Christian Rupprecht 📝 Read the Full Paper here: 🗂️ Project Page: 🎥 Be sure to watch the attached Demo Video - Sound on 🔊🔊 Find this Valuable 💎 ? ♻️QT and teach your network something new Follow me 👣, naveen manwani , for the latest updates on Tech and AI-related news, insightful research papers, and exciting announcements.

naveen manwani

14,334 Aufrufe • vor 1 Jahr

Why You Never Exit Your Car During Road Rage | Shooting Caught on Video Road rage isn’t just anger — it’s one of the fastest ways to ruin your life or end it. In this video, I break down a road rage shooting caught on camera involving an off-duty police officer, and explain exactly where this situation crossed from bad decisions into a deadly confrontation. This isn’t about politics. It’s not about bravado. It’s about reality. We walk through: How road rage escalates faster than people realize The moment ego replaces judgment Why getting out of your car changes everything When a road rage incident turns into a self-defense scenario Why you don’t get to choose how someone defends themselves The legal and real-world consequences people never think about Road rage feels personal — but the moment you approach another vehicle in anger, you’re gambling with variables you don’t control. This breakdown isn’t meant to scare you. It’s meant to keep you alive. 👉 Stay in your car. Create distance. Let it go. Because the only winning move in road rage is not playing This case is the definition of FAFO — not macho posturing, but good people forced to defend themselves when evil shows up uninvited. 🔥 HOLIDAY SALE — 15% OFF SITEWIDE (CODE: FAFO) FAFO collection, hoodies, tees, hats, drinkware, and the AKT1 Blackouts — all 15% OFF right now. 👉
2:46

Why You Never Exit Your Car During Road Rage | Shooting Caught on Video Road rage isn’t just anger — it’s one of the fastest ways to ruin your life or end it. In this video, I break down a road rage shooting caught on camera involving an off-duty police officer, and explain exactly where this situation crossed from bad decisions into a deadly confrontation. This isn’t about politics. It’s not about bravado. It’s about reality. We walk through: How road rage escalates faster than people realize The moment ego replaces judgment Why getting out of your car changes everything When a road rage incident turns into a self-defense scenario Why you don’t get to choose how someone defends themselves The legal and real-world consequences people never think about Road rage feels personal — but the moment you approach another vehicle in anger, you’re gambling with variables you don’t control. This breakdown isn’t meant to scare you. It’s meant to keep you alive. 👉 Stay in your car. Create distance. Let it go. Because the only winning move in road rage is not playing This case is the definition of FAFO — not macho posturing, but good people forced to defend themselves when evil shows up uninvited. 🔥 HOLIDAY SALE — 15% OFF SITEWIDE (CODE: FAFO) FAFO collection, hoodies, tees, hats, drinkware, and the AKT1 Blackouts — all 15% OFF right now. 👉

Colion Noir

21,991 Aufrufe • vor 8 Monaten

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!
0:30

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 Aufrufe • vor 9 Monaten