Loading video...

Video Failed to Load

Go Home

RTX Spark laptops are great for creator workflows. Watch how DLSS 4.5 Ray Reconstruction delivers real-time viewport previews directly within Blender, replacing traditional denoising with instant visual feedback.

NVIDIARTXSpark's profile picture

NVIDIA RTX Spark

52,475 subscribers

317,496 views • 1 month ago •via X (Twitter)

ArtsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

.Blender 🔶, accelerated for the moment the idea changes. DLSS 4.5 Ray Reconstruction helps 3D artists adjust lighting, texture maps and camera moves with real-time feedback. Coming this fall alongside RTX Spark.
0:24

.Blender 🔶, accelerated for the moment the idea changes. DLSS 4.5 Ray Reconstruction helps 3D artists adjust lighting, texture maps and camera moves with real-time feedback. Coming this fall alongside RTX Spark.

NVIDIA Studio

91,913 views • 2 months ago

RTX Spark laptops are great for running advanced local AI agents. Watch how an @OpenClaw agent handles complex ComfyUI workflows, transforming a simple sketch into a fully animated concept video while keeping your data private and secure.
1:22

RTX Spark laptops are great for running advanced local AI agents. Watch how an @OpenClaw agent handles complex ComfyUI workflows, transforming a simple sketch into a fully animated concept video while keeping your data private and secure.

NVIDIA RTX Spark

12,892 views • 1 month ago

New Feature 📣 Many users have asked for insights and help as they are solving challenges. So today we’re launching our first AI-powered feature; Instant Feedback! ✨ You can now submit your challenges and receive real-time, AI-driven feedback directly within the scrim.
0:42

New Feature 📣 Many users have asked for insights and help as they are solving challenges. So today we’re launching our first AI-powered feature; Instant Feedback! ✨ You can now submit your challenges and receive real-time, AI-driven feedback directly within the scrim.

Scrimba

38,354 views • 1 year ago

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth
0:40

Unsloth AI and NVIDIA are Revolutionizing Local LLM Fine-Tuning: From RTX Desktops to DGX Spark Fine-tune popular AI models faster with Unsloth on NVIDIA RTX AI PCs such as GeForce RTX desktops and laptops to RTX PRO workstations and the new DGX Spark to build personalized assistants for coding, creative work, and complex agentic workflows. The landscape of modern AI is shifting. We are moving away from a total reliance on massive, generalized cloud models and entering the era of local, agentic AI. Whether it is tuning a chatbot to handle hyper-specific product support or building a personal assistant that manages intricate schedules, the potential for generative AI on local hardware is boundless. However, developers face a persistent bottleneck: How do you get a Small Language Model (SLM) to punch above its weight class and respond with high accuracy for specialized tasks? The answer is Fine-Tuning, and the tool of choice is Unsloth. Unsloth provides an easy and high-speed method to customize models. Optimized for efficient, low-memory training on NVIDIA GPUs, Unsloth scales effortlessly from GeForce RTX desktops and laptop all the way to the DGX Spark, the world’s smallest AI supercomputer...... Full analysis: NVIDIA NVIDIA AI NVIDIA AIDev NVIDIAnewsroom Unsloth AI Unsloth

Marktechpost AI Dev News ⚡

31,551 views • 7 months ago

Auto regressive LLMs are officially on notice. run Gemma 4 26B diffusion gguf with llama.cpp Google just dropped DiffusionGemma-26B, and it completely flips how we generate text. instead of predicting words one by one, it generates 256 tokens in parallel using bi-directional attention. its like stable diffusion, but for language. the model starts with random text "noise" and iteratively refines and self-corrects the entire block in real-time to fix formatting and reasoning errors on the fly. since it’s a Mixture of Experts (MoE) that only activates 3.8B parameters during inference, it fits perfectly on consumer hardware. You can run the Q4_K_M quant with an 18GB VRAM budget on a single RTX 3090 or RTX 4090 with exceptional throughput. Tested on Ubuntu 22 with CUDA 13.1 using the cutting edge experimental llama.cpp branch. Here is how to compile and run it with the live terminal denoising visualizer: # 1. Clone & check out the experimental PR (#24423) - 1) git clone && cd llama.cpp -git fetch origin 2) pull/24423/head:diffusiongemma && --git checkout diffusiongemma # 2. Build with CUDA support 1) cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native 2) cmake --build build -j $(nproc) --config Release --target llama-diffusion-cli # 3. Run with live visual denoising (llama.cpp flags) ./build/bin/llama-diffusion-cli \ -m /path/to/diffusiongemma-26B-A4B-it-Q4_K_M.gguf \ -ngl 99 -cnv -n 2048 --diffusion-visual Watch the video below to see the live --diffusion-visual canvas iteratively de noising the prompt output in real time. guide and unsloth's hugging face GGUF model links are in the comments below! Is auto regressive generation officially legacy tech? Let me know what you think.
0:31

Auto regressive LLMs are officially on notice. run Gemma 4 26B diffusion gguf with llama.cpp Google just dropped DiffusionGemma-26B, and it completely flips how we generate text. instead of predicting words one by one, it generates 256 tokens in parallel using bi-directional attention. its like stable diffusion, but for language. the model starts with random text "noise" and iteratively refines and self-corrects the entire block in real-time to fix formatting and reasoning errors on the fly. since it’s a Mixture of Experts (MoE) that only activates 3.8B parameters during inference, it fits perfectly on consumer hardware. You can run the Q4_K_M quant with an 18GB VRAM budget on a single RTX 3090 or RTX 4090 with exceptional throughput. Tested on Ubuntu 22 with CUDA 13.1 using the cutting edge experimental llama.cpp branch. Here is how to compile and run it with the live terminal denoising visualizer: # 1. Clone & check out the experimental PR (#24423) - 1) git clone && cd llama.cpp -git fetch origin 2) pull/24423/head:diffusiongemma && --git checkout diffusiongemma # 2. Build with CUDA support 1) cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native 2) cmake --build build -j $(nproc) --config Release --target llama-diffusion-cli # 3. Run with live visual denoising (llama.cpp flags) ./build/bin/llama-diffusion-cli \ -m /path/to/diffusiongemma-26B-A4B-it-Q4_K_M.gguf \ -ngl 99 -cnv -n 2048 --diffusion-visual Watch the video below to see the live --diffusion-visual canvas iteratively de noising the prompt output in real time. guide and unsloth's hugging face GGUF model links are in the comments below! Is auto regressive generation officially legacy tech? Let me know what you think.

Alok

52,656 views • 1 month ago

Agents Are Replacing SaaS 🟢 And We’re Living It At Assisterr, we don’t just build AI agents - we use them Our own infrastructure has already replaced most traditional SaaS tools with custom-built AI agents that handle everything from analytics and reporting to workflow automation Need deep product insights? Our Analytics Assistant tracks real-time data, generates reports, and delivers actionable insights—automatically 🚀 Need a new tool? We don’t waste time looking for SaaS alternatives - we just build a custom agent. No code, no hassle, just instant automation We’re committed to making this accessible to everyone—so anyone can create, customize, and deploy AI agents tailored to their needs The future isn’t SaaS. The future is agents. And with Assisterr, it’s already here
3:43

Agents Are Replacing SaaS 🟢 And We’re Living It At Assisterr, we don’t just build AI agents - we use them Our own infrastructure has already replaced most traditional SaaS tools with custom-built AI agents that handle everything from analytics and reporting to workflow automation Need deep product insights? Our Analytics Assistant tracks real-time data, generates reports, and delivers actionable insights—automatically 🚀 Need a new tool? We don’t waste time looking for SaaS alternatives - we just build a custom agent. No code, no hassle, just instant automation We’re committed to making this accessible to everyone—so anyone can create, customize, and deploy AI agents tailored to their needs The future isn’t SaaS. The future is agents. And with Assisterr, it’s already here

assisterr

28,813 views • 1 year ago

Anonymous feedback and honest feedback can both be true. We see that with ICE, Command Climate Surveys, and the recent Unaccompanied Housing Survey — all anonymous. If you dismiss anonymous feedback as dishonest, then you’d have to dismiss those mechanisms too. Yes, Hots&Cots is anonymous, but we’ve built ways for leaders to engage directly through our leadership dashboard. I’ve personally spoken with reviewers who are willing to engage with leadership when given the chance. Service members come to Hots&Cots because traditional means of getting issues addressed are broken. I get the feeling from SMA that Hots&Cots is being viewed as trying to make the Army look bad — that couldn’t be further from the truth. We’ve spent countless hours meeting with leaders across the force, on our own dime and time, to advocate for Soldiers living in the barracks. We all want the same thing — a great dining experience. Whether feedback comes with a name attached or not, it still reflects real experiences. The goal should be to listen, not to filter out voices based on how they’re shared. As I’ve always said I’m ready to give SMA’s team a verified account
2:21

Anonymous feedback and honest feedback can both be true. We see that with ICE, Command Climate Surveys, and the recent Unaccompanied Housing Survey — all anonymous. If you dismiss anonymous feedback as dishonest, then you’d have to dismiss those mechanisms too. Yes, Hots&Cots is anonymous, but we’ve built ways for leaders to engage directly through our leadership dashboard. I’ve personally spoken with reviewers who are willing to engage with leadership when given the chance. Service members come to Hots&Cots because traditional means of getting issues addressed are broken. I get the feeling from SMA that Hots&Cots is being viewed as trying to make the Army look bad — that couldn’t be further from the truth. We’ve spent countless hours meeting with leaders across the force, on our own dime and time, to advocate for Soldiers living in the barracks. We all want the same thing — a great dining experience. Whether feedback comes with a name attached or not, it still reflects real experiences. The goal should be to listen, not to filter out voices based on how they’re shared. As I’ve always said I’m ready to give SMA’s team a verified account

hots&cots

18,702 views • 9 months ago

EPISODE 159: How AI Is About to Upend the $140B Customer Research Industry Joe Lonsdale sits down with Aaron Cannon, founder & CEO of Outset Learn how AI can outperform humans in customer surveys, the new possibilities with real-time customer feedback, how Outset grew revenue 8X this past year, and more! (00:00) Episode intro (01:10) Aaron's entrepreneurial journey (06:00) How does AI-moderated research work? (09:25) Why people will talk to AI more than humans (13:40) How Outset landed Microsoft, Google & Uber (14:55) Are you replacing human jobs? (20:56) New possibilities for real-time product improvements (23:30) The pros and cons of synthetic research (28:00) Insane growth / how Outset 8X'd revenue (35:00) How AI is upending a $140B industry
39:58

EPISODE 159: How AI Is About to Upend the $140B Customer Research Industry Joe Lonsdale sits down with Aaron Cannon, founder & CEO of Outset Learn how AI can outperform humans in customer surveys, the new possibilities with real-time customer feedback, how Outset grew revenue 8X this past year, and more! (00:00) Episode intro (01:10) Aaron's entrepreneurial journey (06:00) How does AI-moderated research work? (09:25) Why people will talk to AI more than humans (13:40) How Outset landed Microsoft, Google & Uber (14:55) Are you replacing human jobs? (20:56) New possibilities for real-time product improvements (23:30) The pros and cons of synthetic research (28:00) Insane growth / how Outset 8X'd revenue (35:00) How AI is upending a $140B industry

American Optimist

114,224 views • 1 month ago

Finally. Instead of jumping back and forth to several different tools and tabs, my entire creative process now lives in one visual system. This is Freepik (now Magnific)'s major new announcement, called SPACES. Imagine if Figma and N8N had a baby. That's essentially what this is – a collaborative art canvas that automates entire creative workflows. Here's how it works. I want to thank Freepik for sponsoring this video. It's a great feeling as a creator when you get to work with the brands that are a staple in your workflow.
1:32

Finally. Instead of jumping back and forth to several different tools and tabs, my entire creative process now lives in one visual system. This is Freepik (now Magnific)'s major new announcement, called SPACES. Imagine if Figma and N8N had a baby. That's essentially what this is – a collaborative art canvas that automates entire creative workflows. Here's how it works. I want to thank Freepik for sponsoring this video. It's a great feeling as a creator when you get to work with the brands that are a staple in your workflow.

Roberto Nickson

54,489 views • 9 months ago

NVIDIA just handed every solo creator and freelancer an unfair advantage. Jensen Huang walked on stage and announced RTX Spark. An ARM-based laptop chip that nobody saw coming. They called it the most power efficient PC chip ever built. 20 cores. Blackwell graphics. 6144 CUDA cores. Up to 128GB of LPDDR5X memory. But forget the spec sheet for a second. Here is what actually matters. RTX Spark is built to run AI models locally. No cloud subscription. No API costs. No waiting on a server somewhere. Everything runs directly on the laptop at full speed. That changes the math completely for anyone using AI to make money. The guy generating 3D assets in Blender with Claude his renders now take minutes instead of hours. More projects per day. More income per week. The girl producing AI kids content for YouTube local rendering means no upload wait times, no generation limits, no monthly fees eating into her margins. The freelancer building websites and automating outreach every AI tool in his stack now runs faster and cheaper than before. 30 laptops from Asus, Dell, Lenovo, MSI and others. Available this fall. For years the barrier was hardware. You needed an expensive setup to run serious AI workflows locally. NVIDIA just put that power inside a thin laptop anyone can carry anywhere. The people who already figured out how to monetize AI are about to move twice as fast. The people who haven’t started yet just ran out of excuses. Save this.
0:45

NVIDIA just handed every solo creator and freelancer an unfair advantage. Jensen Huang walked on stage and announced RTX Spark. An ARM-based laptop chip that nobody saw coming. They called it the most power efficient PC chip ever built. 20 cores. Blackwell graphics. 6144 CUDA cores. Up to 128GB of LPDDR5X memory. But forget the spec sheet for a second. Here is what actually matters. RTX Spark is built to run AI models locally. No cloud subscription. No API costs. No waiting on a server somewhere. Everything runs directly on the laptop at full speed. That changes the math completely for anyone using AI to make money. The guy generating 3D assets in Blender with Claude his renders now take minutes instead of hours. More projects per day. More income per week. The girl producing AI kids content for YouTube local rendering means no upload wait times, no generation limits, no monthly fees eating into her margins. The freelancer building websites and automating outreach every AI tool in his stack now runs faster and cheaper than before. 30 laptops from Asus, Dell, Lenovo, MSI and others. Available this fall. For years the barrier was hardware. You needed an expensive setup to run serious AI workflows locally. NVIDIA just put that power inside a thin laptop anyone can carry anywhere. The people who already figured out how to monetize AI are about to move twice as fast. The people who haven’t started yet just ran out of excuses. Save this.

Shelpid.WI3M

27,774 views • 2 months ago

"I have prompts to simulate every exec I meet with so I can anticipate their questions." Here's my new episode with Morgan Brown (VP AI at Dropbox) where he shared his: - Top 3 AI workflows for PM work - AI product to save workers 160 hours a year - Top lessons from Drew (Dropbox), Tobi (Shopify), and Zuck (Meta) Some quotes from Morgan: "The best PMs know how to orchestrate a council of LLMs so that they can free up time to think." "Shipping is what puts your ideas in contact with reality. Progress should be measured by how fast you're learning." "We run a robust evaluation process that includes golden datasets, LLM as a judge, and real-time feedback. Here's how it works..." 📌 Watch now:
1:04

"I have prompts to simulate every exec I meet with so I can anticipate their questions." Here's my new episode with Morgan Brown (VP AI at Dropbox) where he shared his: - Top 3 AI workflows for PM work - AI product to save workers 160 hours a year - Top lessons from Drew (Dropbox), Tobi (Shopify), and Zuck (Meta) Some quotes from Morgan: "The best PMs know how to orchestrate a council of LLMs so that they can free up time to think." "Shipping is what puts your ideas in contact with reality. Progress should be measured by how fast you're learning." "We run a robust evaluation process that includes golden datasets, LLM as a judge, and real-time feedback. Here's how it works..." 📌 Watch now:

Peter Yang

59,720 views • 1 year ago

We're excited to introduce Box + Perplexity Computer – where your AI assistant becomes a true operator, working directly within your content hub. Empower your agents with: → A Real Filesystem for AI: Seamlessly connect Perplexity with your Box files → Intelligent Insights: Point Perplexity across multiple files to surface insights, patterns, and answers that drive strategic decisions. → Automated Multi-Step Workflows: Perplexity Computer handles complex tasks efficiently in the background. → Secure & Governed Operations: Leverage Box's security and permissions, ensuring your AI operates with the right access and governance. Watch how Box + Perplexity Computer transforms raw data into actionable intelligence, like building a comprehensive competitive brief from multiple documents.
1:29

We're excited to introduce Box + Perplexity Computer – where your AI assistant becomes a true operator, working directly within your content hub. Empower your agents with: → A Real Filesystem for AI: Seamlessly connect Perplexity with your Box files → Intelligent Insights: Point Perplexity across multiple files to surface insights, patterns, and answers that drive strategic decisions. → Automated Multi-Step Workflows: Perplexity Computer handles complex tasks efficiently in the background. → Secure & Governed Operations: Leverage Box's security and permissions, ensuring your AI operates with the right access and governance. Watch how Box + Perplexity Computer transforms raw data into actionable intelligence, like building a comprehensive competitive brief from multiple documents.

Box

246,743 views • 5 months ago

"Maybe the right UI for AI is a generative UI." Here's my new interview with Stephen Chau featuring a live demo of Cove's ground-breaking visual AI interface that breaks free from chatbots. We had a great chat about: - Real world use cases for visual AI interfaces - Generative UI and just-in-time AI apps - How Stephen scaled Uber Eats to $25B ARR Some quotes from Stephen Chau: "In computing, we moved from the command line to graphic user interfaces. Chatbots are like the command line era of AI. What's next is this..." "Imagine the entire layout of the workspace and all its contents is something made just in time, based on what you're trying to do..." "Our goal with Uber Eats was to build a business that's the same size as the Rides business. Here's what mattered..." 📌 Watch now:
1:09

"Maybe the right UI for AI is a generative UI." Here's my new interview with Stephen Chau featuring a live demo of Cove's ground-breaking visual AI interface that breaks free from chatbots. We had a great chat about: - Real world use cases for visual AI interfaces - Generative UI and just-in-time AI apps - How Stephen scaled Uber Eats to $25B ARR Some quotes from Stephen Chau: "In computing, we moved from the command line to graphic user interfaces. Chatbots are like the command line era of AI. What's next is this..." "Imagine the entire layout of the workspace and all its contents is something made just in time, based on what you're trying to do..." "Our goal with Uber Eats was to build a business that's the same size as the Rides business. Here's what mattered..." 📌 Watch now:

Peter Yang

74,682 views • 1 year ago

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.
1:18

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.

nikshep

40,500 views • 4 months ago

GM builders 🟦 Big shift happening right now. Base is evolving… and Base App is leading the charge. From social-first → trading-first. This isn’t just a feature update, it’s a complete change in direction for the onchain economy. For months, social fueled attention. Creators earned. Communities grew. Narratives formed. Now? That attention is turning into liquidity. Every creator coin, every meme, every AI narrative is about to plug directly into a trading engine. What this means: • Faster discovery → instant trading • Attention → real market value • Creators → become liquidity drivers • Users → move from scrolling to trading The lines between content, culture, and capital are disappearing. This is how ecosystems mature. This is how onchain wins. Watch the video 👇 and see why this changes everything. Tagging the builders: Base Baseapp
1:29

GM builders 🟦 Big shift happening right now. Base is evolving… and Base App is leading the charge. From social-first → trading-first. This isn’t just a feature update, it’s a complete change in direction for the onchain economy. For months, social fueled attention. Creators earned. Communities grew. Narratives formed. Now? That attention is turning into liquidity. Every creator coin, every meme, every AI narrative is about to plug directly into a trading engine. What this means: • Faster discovery → instant trading • Attention → real market value • Creators → become liquidity drivers • Users → move from scrolling to trading The lines between content, culture, and capital are disappearing. This is how ecosystems mature. This is how onchain wins. Watch the video 👇 and see why this changes everything. Tagging the builders: Base Baseapp

𝙼𝙰𝚉𝙸 𝙴𝙼𝙾𝙽𝙸𝙴 ™LOFTE3 2026

11,589 views • 5 months ago

STEAL THE BRAINROT is expanding. We’re hiring a high-level UEFN Level Designer to lead our in-game events. We’re looking for someone very experienced and creative, who knows how to bring their talent and ideas into high-quality in-game events. There is an existing structure and visual style, and the role requires the ability to adapt and build new events based on what has already been done. Requirements: - Several years of experience in level / environment design - Strong portfolio - All assets must be custom made - Strong experience with Blender - Deep understanding of materials - Advanced UEFN experience (materials, VFX, optimization) - Full-time availability - Available to start immediately We’re looking for talented people with real experience, not beginners. Compensation is high and based on experience. A signing bonus is available for the right candidate. Below are examples of past events, this is the quality bar: 100% custom assets, modeled in Blender, with custom materials & VFX in UEFN, fully optimized. DM me with your portfolio.
0:41

STEAL THE BRAINROT is expanding. We’re hiring a high-level UEFN Level Designer to lead our in-game events. We’re looking for someone very experienced and creative, who knows how to bring their talent and ideas into high-quality in-game events. There is an existing structure and visual style, and the role requires the ability to adapt and build new events based on what has already been done. Requirements: - Several years of experience in level / environment design - Strong portfolio - All assets must be custom made - Strong experience with Blender - Deep understanding of materials - Advanced UEFN experience (materials, VFX, optimization) - Full-time availability - Available to start immediately We’re looking for talented people with real experience, not beginners. Compensation is high and based on experience. A signing bonus is available for the right candidate. Below are examples of past events, this is the quality bar: 100% custom assets, modeled in Blender, with custom materials & VFX in UEFN, fully optimized. DM me with your portfolio.

FeRinS

133,604 views • 7 months ago

We are excited to share our work “Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones” published in IEEE Transactions on Robotics IEEE Transactions on Robotics (T-RO), which tackles sharp radiance field reconstruction under agile drone motion, where RGB frames are heavily motion-blurred and pose priors become unreliable! 4 years in the making! Code & dataset released! PDF: Code & Dataset: Full Narrated Video: High-speed flight is essential for time- and battery-constrained missions (e.g., inspection, exploration, search & rescue). However, fast motion corrupts visual data with severe motion blur and introduces drift/noise in visual-inertial odometry, making NeRF-based 3D reconstruction particularly brittle. We propose a unified framework that leverages asynchronous #EventCamera streams together with motion-blurred frames to reconstruct high-fidelity radiance fields from agile drone flights. Our key idea is to embed event-image fusion directly into radiance field optimization while jointly refining a shared, continuous-time camera trajectory initialized from event-based VIO. This enables us to recover sharp radiance fields and accurate trajectories without ground-truth supervision during training. We validate our method on synthetic data and on real sequences captured by a drone flying up to 2 m/s. Despite severe blur and noisy pose priors, our method preserves fine scene details and achieves a performance gain of over 50% on real-world data compared to state-of-the-art methods. Kudos to Rong Zou and Marco Cannici! Marco Cannici Reference: Rong Zou*, Marco Cannici*, Davide Scaramuzza Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones IEEE Transactions on Robotics (T-RO), 2026 NCCR Robotics European Research Council (ERC) AUTOASSESS UZH IfI University of Zurich UZH Science Prophesee SynSense UZH Space Hub
1:02

We are excited to share our work “Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones” published in IEEE Transactions on Robotics IEEE Transactions on Robotics (T-RO), which tackles sharp radiance field reconstruction under agile drone motion, where RGB frames are heavily motion-blurred and pose priors become unreliable! 4 years in the making! Code & dataset released! PDF: Code & Dataset: Full Narrated Video: High-speed flight is essential for time- and battery-constrained missions (e.g., inspection, exploration, search & rescue). However, fast motion corrupts visual data with severe motion blur and introduces drift/noise in visual-inertial odometry, making NeRF-based 3D reconstruction particularly brittle. We propose a unified framework that leverages asynchronous #EventCamera streams together with motion-blurred frames to reconstruct high-fidelity radiance fields from agile drone flights. Our key idea is to embed event-image fusion directly into radiance field optimization while jointly refining a shared, continuous-time camera trajectory initialized from event-based VIO. This enables us to recover sharp radiance fields and accurate trajectories without ground-truth supervision during training. We validate our method on synthetic data and on real sequences captured by a drone flying up to 2 m/s. Despite severe blur and noisy pose priors, our method preserves fine scene details and achieves a performance gain of over 50% on real-world data compared to state-of-the-art methods. Kudos to Rong Zou and Marco Cannici! Marco Cannici Reference: Rong Zou*, Marco Cannici*, Davide Scaramuzza Event-Aided Sharp Radiance Field Reconstruction for Fast-Flying Drones IEEE Transactions on Robotics (T-RO), 2026 NCCR Robotics European Research Council (ERC) AUTOASSESS UZH IfI University of Zurich UZH Science Prophesee SynSense UZH Space Hub

Davide Scaramuzza

12,006 views • 5 months ago

🚀 Announcing our new loyalty program with Alkimi, the ad platform redefining how brands, publishers, and users interact with Web3. Leveraging the full Sui stack, Alkimi delivers the speed and scalability needed to run real-time ad auctions fully on-chain. Powered by their token, $ALKIMI, the platform brings transparency, efficiency, and trust back into a $750B industry plagued by hidden fees and inefficiencies. 💠 $ALKIMI holders can earn yield right now by staking their tokens on Alkimi Labs: With Alkimi, advertisers launch campaigns that are faster, cheaper, and more effective, while publishers and users benefit directly from a fairer value exchange. This isn’t just an ad platform; it’s the advertising infrastructure layer Web3 has been waiting for. Let’s GiveRep to Alkimi and spread the word about how we’re redefining digital advertising with our new loyalty program.
1:42

🚀 Announcing our new loyalty program with Alkimi, the ad platform redefining how brands, publishers, and users interact with Web3. Leveraging the full Sui stack, Alkimi delivers the speed and scalability needed to run real-time ad auctions fully on-chain. Powered by their token, $ALKIMI, the platform brings transparency, efficiency, and trust back into a $750B industry plagued by hidden fees and inefficiencies. 💠 $ALKIMI holders can earn yield right now by staking their tokens on Alkimi Labs: With Alkimi, advertisers launch campaigns that are faster, cheaper, and more effective, while publishers and users benefit directly from a fairer value exchange. This isn’t just an ad platform; it’s the advertising infrastructure layer Web3 has been waiting for. Let’s GiveRep to Alkimi and spread the word about how we’re redefining digital advertising with our new loyalty program.

GiveRep

40,572 views • 11 months ago

🇺🇸🌍🇺🇸 ZEBEC NETWORK IS NOW INSIDE THE U.S. PAYMENTS RAILS Most people will miss how big this is. Zebec Network is no longer operating around the financial system, it’s now operating inside it.🌍💳 🏦 What Just Happened Zebec Network has integrated directly with U.S. United States 🇺🇸 payment infrastructure, including: ✅ ACH (Automated Clearing House) ✅ Direct deposit rails ✅ Bank & payroll interoperability ✅ ISO 2️⃣0️⃣0️⃣2️⃣2️⃣ financial messaging 📡 This means Zebec can now move value where real money already flows, inside the same rails used by banks, employers, and payroll providers. 🔗 Why This Matters This isn’t a workaround. This isn’t an off~ramp. This is native alignment with U.S. payments infrastructure. 💼 Employers can run payroll 💰 Workers can receive wages 🔁 Funds can flow between bank accounts and programmable payments, all within a compliant, enterprise-ready framework. 🧠 Here the Bigger Picture Zebec is building a dual~rail system: 🏛️ Traditional finance rails (ACH, payroll, banks) Programmable, real~time payment rails Both operating together, not competing. That’s how infrastructure gets adopted. That’s how payments scale. That’s how Web3 becomes invisible, and useful. 🧱 Built for the Future 🔹🌐 ISO 20022 compliant 🔹 Interoperable with existing financial systems. Aligned with Nacha & ACH standards 🔹 Designed for payroll, treasury, and enterprise payments 🔹 Operating where regulation, compliance, and volume already exist This is infrastructure, not hype. 📌 In Simple Terms Zebec Network didn’t ask TradFi for permission. It plugged directly into the rails and started building. 🚆 Real rails 💵 Real money 🏗️ Real adoption Most people will scroll past this. Institutions won’t. Zebec Network
0:25

🇺🇸🌍🇺🇸 ZEBEC NETWORK IS NOW INSIDE THE U.S. PAYMENTS RAILS Most people will miss how big this is. Zebec Network is no longer operating around the financial system, it’s now operating inside it.🌍💳 🏦 What Just Happened Zebec Network has integrated directly with U.S. United States 🇺🇸 payment infrastructure, including: ✅ ACH (Automated Clearing House) ✅ Direct deposit rails ✅ Bank & payroll interoperability ✅ ISO 2️⃣0️⃣0️⃣2️⃣2️⃣ financial messaging 📡 This means Zebec can now move value where real money already flows, inside the same rails used by banks, employers, and payroll providers. 🔗 Why This Matters This isn’t a workaround. This isn’t an off~ramp. This is native alignment with U.S. payments infrastructure. 💼 Employers can run payroll 💰 Workers can receive wages 🔁 Funds can flow between bank accounts and programmable payments, all within a compliant, enterprise-ready framework. 🧠 Here the Bigger Picture Zebec is building a dual~rail system: 🏛️ Traditional finance rails (ACH, payroll, banks) Programmable, real~time payment rails Both operating together, not competing. That’s how infrastructure gets adopted. That’s how payments scale. That’s how Web3 becomes invisible, and useful. 🧱 Built for the Future 🔹🌐 ISO 20022 compliant 🔹 Interoperable with existing financial systems. Aligned with Nacha & ACH standards 🔹 Designed for payroll, treasury, and enterprise payments 🔹 Operating where regulation, compliance, and volume already exist This is infrastructure, not hype. 📌 In Simple Terms Zebec Network didn’t ask TradFi for permission. It plugged directly into the rails and started building. 🚆 Real rails 💵 Real money 🏗️ Real adoption Most people will scroll past this. Institutions won’t. Zebec Network

AlphaLion

12,178 views • 7 months ago