The Vision Encoder: Our Secret Weapon 🔥 An ultra-accurate... vision encoder plate, combined with 5μm-resolution optical feedback, calibrates the H2D’s motion system to achieve consistent 50μm accuracy across the entire build plate. #BambuH2Dshow more

Can a VLM see without a vision encoder? We... trained one for $100, inspired by Gemma 4 12B. Latency on an M3 Pro MacBook: 112 ms -> 1.1 ms for the image path 30% lower end-to-end image+LLM The architecture is just: patchify the image -> linear projection with pos embeddings -> LLM Writeup:show more

🚨 Only on 365Scores: Exclusive Live Match Tracking 🚨... We’ve officially levelled up. Experience football like never before with our Exclusive Live Match Tracker, now powered by industry-leading Computer Vision technology. What makes it a game-changer? 🤖 Computer Vision Precision: Our AI-driven tech tracks every play with pinpoint accuracy. 🏃‍♂️💨 Fluid Motion: See more accurate and realistic player movement across the pitch. ⚡️Enhanced Visuals: A premium, high-tech interpretation of every match moment. 📲 Download the app now to witness the tech in action! 😎 📺 Available currently in UEFA Competitions 🇪🇺, Bundesliga and Bundesliga 2 🇩🇪show more

appreciate the shoutout Nigel Eccles (founder of FanDuel) on... 11AM w/ Seed Club with Jess 🌱 re: our early gated beta an initial step in our vision to build an opinionated, gamified exchange providing liquidity to all onchain asset classesshow more

Excited to unveil the AIOZ Network Vision Paper V2!... Dive into our vision for a unified DePIN layer powering: → Decentralized storage (AIOZ Storage) → Content pinning/caching (AIOZ Pin) → Streaming & delivery (AIOZ Stream) → AI inference orchestration (AIOZ AI) An end-to-end DePIN stack with flexible monetization and stronger developer enablement. Read now & build the people-powered internet with us! Link:show more

Accidentally ran an accuracy test on our MicroFactory robotic... arm. I had to disassemble the base for some improvements. To keep testing consistent for our already-trained models, I quickly built an improvised setup to recreate the previous calibration. After removing and reinstalling the motors, I was able to restore their position within 0.002°. Positioning repeatability was at least 0.01 mm at 300 mm reach. This isn’t a full accuracy test — a proper one would require more planes and indicators with resolution at least an order of magnitude better than the measured values. But anyway, this accuracy is sufficient for all of our assembly tasks.show more

RoadScan-AI-Automated-Pothole-Detection-Tracking RoadScan AI is a computer vision system built... to automatically detect and track potholes in road footage — including dashcam, drone, and fixed-camera video. At its core, the system uses a YOLO11n model fine-tuned on a custom pothole dataset, paired with ByteTrack for multi-object tracking. This enables the system to maintain a consistent identity for each pothole across frames rather than treating every detection as a new, isolated event.show more

We always listen to and value the voice of... our community, treating every piece of feedback as an opportunity for progress. We remain committed to staying on track and delivering on our vision. Our goals are aligned with our users, and together, we’re moving forward toward even greater success! 🚀 While we understand that NFTs may still raise questions for some, rest assured that $XCOIN and NFTs are vital to the continued growth of NebX_Land. Whether you're ready to dive in or prefer to observe from the sidelines, we respect your choice. As the development team, our vision for NebX_Land remains strong, and with testing coming next month, exciting possibilities await. Join us in shaping the future! 🌟show more

(1/5) Maintain consistency as you execute your creative vision.... 🎥 With Ingredients to Video, you can create impactful stories, while maintaining consistent characters across multiple scenes. So, now we can follow the same main characters (a man, his balloon, and a snazzy green and pink car) on an expanding adventure in the Mojave Desert…show more

The Next 100 Days: Our Campaign Forward 🌐 LayerAI... is the most user-rich web3 AI ecosystem. 12 products with over 2 million combined users. We are now approaching the verge of releasing mainnet versions of products used by 6+ billion people globally: 1. laiOS The world’s first AI-enabled operating system. Pluggable by hardware manufacturers across the world. The equivalent of Google’s Android, but for the AI economy. An OS for trillions of devices. 2. aiSEARCH The world’s AI-native web3 browser system, a competitor of Open AI's Search. The vision: the only browser with a native wallet, payment system, and AI Search, powering the future of AI Agents in the workforce. Built for AI markets: AI2AI transactions are the future of global commerce. Our Campaign Forward starts tomorrow. 100 Day Journey to 1 Billion AI Agents on LayerAI.show more

Our latest safety innovation is scanning wheels to catch... potential defects, all while we keep rolling. Meet the Wheel Integrity System: 🚂 HOW IT WORKS ⚙️ Six synchronized cameras capture about 55 ultra-high-resolution images of every wheel at speeds up to 70 mph. AI algorithms analyze those images to detect subtle defects that are difficult for the human eye to identify consistently. Wheel defects are among the most serious mechanical defects in the industry. This technology helps our railroaders act faster, enhancing safety, reducing service disruptions, and protecting long-term asset performance. NS is proud to be the first railroad to deploy a vision‑based system that identifies cracks before they break — powered by our own technology and built through collaboration across multiple NS teams, with integration support from the Georgia Tech Research.show more

Seedance 2.0 has the most accurate character swap available... in my opinion. It's managed to maintain complete scene continuity. I can't see anything else that has changed in the entire scene. It's also maintained accurate camera motion and character movement and just swapped out the character as instructed. The best way to see accuracy is to showcase both clips. All you have to do is upload the video you want to replace the character in as an OMNI Reference and an image of the character to replace them with and type in the following prompt and adjust as needed: Keep the scene the same but just swap the women with the grey shirt with a completely different person, it's the black female in Image1 wearing a dark blue knitted sweater. #CapCutSeedance2 CapCutshow more

We’ve raised $2.3M in pre-seed funding to build Bleap—a... bank on the blockchain! 🚀 The round was led by Ethereal Ventures, with participation from Maven 11, Alliance DAO, Robot Ventures, Credibly Neutral , and other amazing investors who share our vision of a better financial system. Check out the coverage from @TheBlock__ : Bleap is now in beta for EEA users! 💳show more

The (Processing) Level Required to Be Super We’ve had... clients ask us whether our 3D/4DGS capture and processing pipeline holds up in high-end VFX cinematic shots. Last year we were fortunate to work on the Superman production with Framestore (capturing Superman’s parents for a hologram), with our work shown on IMAX screens ~30 m high—so we’re confident the quality delivers. For this R&D preview, we ran test captures using an affordable off-the-shelf temporal plugin to reduce flicker and improve stability over time. We recorded @ 48fps from our 196x machine vision cameras and trained the 4DGS using Postshot at Ultra quality ~20 million splat resolution. What you’re seeing are stop-motion 3DGS frames. Each frame is an individual Gaussian Splat—processed to ~20 million splats for the full scene, then cropped and cleaned to ~6 million splats per frame. Our system—and the 3DGS process—picks up fine details like stray fine hairs, skin pores and woven cloth threads. Thanks for watching & stay super! Learn more @ #3DGS #4DGS #VFX #GaussianSplatting #IMAX #VolumetricCapture #Superman 4K Version here -show more

Etihad Rail is preparing to launch the UAE’s first... fully integrated national passenger rail network, as part of a national vision to advance the transport sector and strengthen connectivity between the emirates. Designed to connect 11 cities and regions through an advanced transport system, the network will include stations in Abu Dhabi, Dubai, Sharjah, Fujairah, Sila, Al Dhannah, Mirfa, Madinat Zayed, Mezaira’a, Al Faya, and Al Dhaid, with services introduced in phases in line with future growth and expansion requirements. Together, we move towards a more integrated and efficient mobility system across the UAE.show more

Made a quick haptic feedback prototype for hand-tracking interactions... with a voxel. Felt fun and engaging. It's another level of immersiveness (unfortunately, the video is not able to convey this). Visual design alone can make an interactive experience great, but if you want to make it exceptional, DIFFERENT, this is where haptic design plays the key role. The device on my wrist is from the Hapticlabs.io Prototyping Kit (the thing on my index fingertip is called Linear Resonant Actuator). It's a beautiful, simple-to-use tool. Found a good case for it in my experiments :) To get hand-tracking data, I used the Leap Motion controller (Computer Vision Camera), which is excellent for quick prototypes like this. I saw people experimenting with gloves to build a solid haptic feedback system for XR. It's great for advanced immersive experiences (video games/simulators/interactive entertainment). But for many day-to-day use cases (productivity/OS/media entertainment), having just a "simple" thimble that provides the haptic feedback for the "touching" fingertip will already significantly improve the UX. Hope we will have something like this from our major XR vendors in the near future.show more

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR... is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!show more

The Bluefin Foundation is thrilled to announce that the... genesis of the BLUE token has been completed! Bluefin was founded with a vision to accelerate on-chain trading. To date, the exchange has processed $40 billion in trading volume across spot and derivatives on Sui. The launch of BLUE is an important step toward a decentralized governance model. Bluefin’s strategy is designed to align incentives across users, contributors, and stakeholders, ensuring long-term ecosystem growth and platform integrity. With the support of our core contributors, partners, and investors, we’re excited to put a product into the hands of the community that powers the next generation of on-chain trading. For more information about BLUE, please visit here:show more