<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Henry Navarro on Medium]]></title>
        <description><![CDATA[Stories by Henry Navarro on Medium]]></description>
        <link>https://medium.com/@hdnh2006?source=rss-a39e3cc02d8c------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*Of5d_ZbBm7xyJgEwuFR7Tw.jpeg</url>
            <title>Stories by Henry Navarro on Medium</title>
            <link>https://medium.com/@hdnh2006?source=rss-a39e3cc02d8c------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 15:13:08 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@hdnh2006/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Agentic Mode in Open WebUI: turn your LLM into a worker for you]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/agentic-mode-in-open-webui-turn-your-llm-into-a-worker-for-you-64eb84f4e929?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1024/0*O4KLvCcN7Dy3kQrN.jpg" width="1024"></a></p><p class="medium-feed-snippet">Open WebUI agents can autonomously run tools and sequences for tasks</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/agentic-mode-in-open-webui-turn-your-llm-into-a-worker-for-you-64eb84f4e929?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/agentic-mode-in-open-webui-turn-your-llm-into-a-worker-for-you-64eb84f4e929?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/64eb84f4e929</guid>
            <category><![CDATA[self-hosted]]></category>
            <category><![CDATA[secure-and-private-ai]]></category>
            <category><![CDATA[agentic-mode]]></category>
            <category><![CDATA[open-webui]]></category>
            <category><![CDATA[agentic-ai]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Thu, 01 Oct 2026 13:50:20 GMT</pubDate>
            <atom:updated>2026-10-01T14:11:06.642Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Uncensored AI Models: a Single Line of Code to Avoid Refusals]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/uncensored-ai-models-a-single-line-of-code-to-avoid-refusals-22f2d842d8f5?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1920/1*XNHAsrELdRnF1MOi8jscog.jpeg" width="1920"></a></p><p class="medium-feed-snippet">UncensoredGPT that replies to any question, no matter what you ask</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/uncensored-ai-models-a-single-line-of-code-to-avoid-refusals-22f2d842d8f5?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/uncensored-ai-models-a-single-line-of-code-to-avoid-refusals-22f2d842d8f5?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/22f2d842d8f5</guid>
            <category><![CDATA[uncensored-gpt]]></category>
            <category><![CDATA[uncensored-ai]]></category>
            <category><![CDATA[abliteration]]></category>
            <category><![CDATA[venice-ai]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Mon, 20 Apr 2026 15:02:48 GMT</pubDate>
            <atom:updated>2026-04-21T09:07:21.320Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Ultralytics Platform: Annotate, Train and Deploy]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/ultralytics-platform-annotate-train-and-deploy-1b8028c2a825?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1920/1*Fe05CCyD1uyBhcB8UjoPdA.jpeg" width="1920"></a></p><p class="medium-feed-snippet">Annotate, Train and Deploy YOLO Models Without Writing a Single Line of Code Using Ultralytics Platform</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/ultralytics-platform-annotate-train-and-deploy-1b8028c2a825?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/ultralytics-platform-annotate-train-and-deploy-1b8028c2a825?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/1b8028c2a825</guid>
            <category><![CDATA[yolo26]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[ultralytics]]></category>
            <category><![CDATA[object-detection]]></category>
            <category><![CDATA[computer-vision]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Mon, 30 Mar 2026 10:16:48 GMT</pubDate>
            <atom:updated>2026-04-06T08:28:32.091Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Qwen3.5 from Alibaba: Deploy This Giant Model With Privacy]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/qwen3-5-from-alibaba-deploy-this-giant-model-with-privacy-43c9aa80c4cf?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1536/1*4f7-3p6emS54-k1Nxp8GPQ.png" width="1536"></a></p><p class="medium-feed-snippet">A Complete Step-by-Step Guide to Self-Hosting The Qwen3.5&#x2013;397B-A17B, Still Controlled by the Chinese Dictatorship and the Communist Party&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/qwen3-5-from-alibaba-deploy-this-giant-model-with-privacy-43c9aa80c4cf?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/qwen3-5-from-alibaba-deploy-this-giant-model-with-privacy-43c9aa80c4cf?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/43c9aa80c4cf</guid>
            <category><![CDATA[llama-cpp]]></category>
            <category><![CDATA[gpu-computing]]></category>
            <category><![CDATA[self-hosted]]></category>
            <category><![CDATA[qwen]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Mon, 23 Feb 2026 12:13:01 GMT</pubDate>
            <atom:updated>2026-02-26T09:09:02.984Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[AI Governance: This is How You Must Run Your AI Agents]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/ai-governance-this-is-how-you-must-run-your-ai-agents-3d6029f08935?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1280/1*rk2brpiUGbABNG4UXZHvdg.png" width="1280"></a></p><p class="medium-feed-snippet">Running OpenClaw, Claude Code, Cline, and OpenCode Safely with Self-Hosted Models, Docker, and Access Control</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/ai-governance-this-is-how-you-must-run-your-ai-agents-3d6029f08935?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/ai-governance-this-is-how-you-must-run-your-ai-agents-3d6029f08935?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/3d6029f08935</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[openclaw]]></category>
            <category><![CDATA[ai-governance]]></category>
            <category><![CDATA[ai-agent]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Mon, 16 Feb 2026 13:52:27 GMT</pubDate>
            <atom:updated>2026-02-17T10:01:26.826Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[YOLO26 on Edge Devices: A Complete Guide]]></title>
            <link>https://ai.plainenglish.io/yolo26-on-edge-devices-a-complete-guide-9047db79e83b?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/9047db79e83b</guid>
            <category><![CDATA[yolo26]]></category>
            <category><![CDATA[nvidia-jetson]]></category>
            <category><![CDATA[edge-ai]]></category>
            <category><![CDATA[edge-computing]]></category>
            <category><![CDATA[ultralytics]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Mon, 02 Feb 2026 16:13:28 GMT</pubDate>
            <atom:updated>2026-02-04T16:52:21.911Z</atom:updated>
            <content:encoded><![CDATA[<h4>Mobile phone, NVIDIA Jetson &amp; CPU: A Comprehensive Deployment Tutorial</h4><figure><a href="https://www.buymeacoffee.com/hdnh2006"><img alt="" src="https://cdn-images-1.medium.com/max/170/1*XtNqB9hQZ085lM-wnlSXbQ.png" /></a></figure><p><strong>Full and unrestricted article here: </strong><a href="https://henrynavarro.org/yolo26-on-edge-devices-a-complete-guide-9047db79e83b?sk=dc8d9a6f08a12c8f40182cf11d31509f">https://henrynavarro.org/yolo26-on-edge-devices-a-complete-guide-9047db79e83b?sk=dc8d9a6f08a12c8f40182cf11d31509f</a></p><p><strong>YouTube video here: </strong><a href="https://youtu.be/DEL6TRfyTe0?si=c9GToMSwKO5REHje">https://youtu.be/DEL6TRfyTe0?si=c9GToMSwKO5REHje</a></p><h3>Introduction 🎯</h3><p><a href="https://docs.ultralytics.com/models/yolo26/"><strong>YOLO26</strong></a><strong> on edge</strong> represents a major leap forward in bringing advanced AI inference to local devices. In this comprehensive guide, we’ll demonstrate how to deploy <a href="https://docs.ultralytics.com/models/yolo26/?utm_source=infl&amp;utm_medium=general&amp;utm_campaign=yolo26&amp;utm_term=hn">Ultralytics</a> YOLO26 models on three distinct platforms: mobile phones, <a href="https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/">NVIDIA Jetson devices</a>, and Intel CPUs.</p><figure><img alt="Results YOLO26 on Edge running on NVIDIA Jetson Xavier NX" src="https://cdn-images-1.medium.com/max/720/1*37wKEszoiie-oEythyNiOA.gif" /><figcaption><em>Results </em><a href="https://docs.ultralytics.com/models/yolo26/"><em>YOLO26</em></a><em> on Edge running on NVIDIA Jetson Xavier NX</em></figcaption></figure><h3>Why Deploy on Edge? 🏠</h3><p><a href="https://docs.ultralytics.com/models/yolo26/"><strong>YOLO26</strong></a><strong> on edge</strong> offers several critical advantages over cloud-based AI. Privacy is paramount as sensitive data never leaves the device. Low latency enables real-time inference without network delays. Cost-effectiveness eliminates recurring cloud computing expenses. Reliability ensures functionality offline, perfect for remote locations. Scalability allows deploying thousands of devices independently.</p><p>Common enterprise use cases include mobile applications with object detection, NVIDIA Jetson devices for industrial automation, Intel CPUs for cost-sensitive deployments, and edge accelerators for IoT devices.</p><figure><img alt="YOLO26 on Edge: Real-time inference on multiple platforms. Image taken from [here](https://www.youtube.com/watch?v=pZWL9r7wotU)" src="https://cdn-images-1.medium.com/max/1024/1*sk6Ku7WmaYCbStPyCrZMfQ.jpeg" /><figcaption><a href="https://docs.ultralytics.com/models/yolo26/"><em>YOLO26</em></a><em> on Edge: Real-time inference on multiple platforms. Image taken from </em><a href="https://www.youtube.com/watch?v=pZWL9r7wotU"><em>this</em></a><em> video.</em></figcaption></figure><p>The official <a href="https://docs.ultralytics.com/models/yolo26/?utm_source=infl&amp;utm_medium=general&amp;utm_campaign=yolo26&amp;utm_term=hn">Ultralytics documentation</a> provides comprehensive guides for every platform, including mobile, NVIDIA Jetson, and Intel CPU deployment.</p><h3>Mobile Deployment with TensorFlow Lite 📱</h3><p><a href="https://docs.ultralytics.com/models/yolo26/"><strong>YOLO26</strong></a><strong> on edge</strong> can run on mobile devices using Google’s TensorFlow Lite framework. This allows inference on Android and iOS devices with GPU acceleration.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/480/1*ORC5jHgVGTBKNCyvy-VN_g.gif" /><figcaption>Ultralytics YOLO on Mobile Android Device.</figcaption></figure><h3>Building the Mobile Application</h3><p>We’ve created a Docker-based solution to simplify the build process. The complete repository is available at <a href="https://github.com/NeuralNet-Hub/yolo-flutter-app">https://github.com/NeuralNet-Hub/yolo-flutter-app</a>.</p><p><strong>Build the Docker container:</strong></p><pre>git clone https://github.com/NeuralNet-Hub/yolo-flutter-app.git<br>cd yolo-flutter-app<br>docker build -t yolo-flutter-app-flutter-builder .<br>docker run -it -v $(pwd):/app/ yolo-flutter-app-flutter-builder:latest /bin/bash</pre><p><strong>Create the APK:</strong></p><pre>cd example<br>flutter build apk --release</pre><p>Once built, transfer the APK to your mobile phone and install it. The application will automatically download the YOLO26 model and start inference.</p><h3>Features and Performance</h3><p>The mobile application supports:</p><ul><li>✅ <strong>Object detection</strong> with bounding boxes</li><li>✅ <strong>Instance segmentation</strong> (pixel-level precision)</li><li>✅ <strong>Pose estimation</strong> (human keypoints)</li><li>✅ <strong>Automatic model download</strong></li><li>✅ <strong>Camera integration</strong></li><li>✅ <strong>Real-time inference</strong> on mobile GPU</li></ul><p>The TensorFlow Lite framework leverages the mobile device’s GPU for accelerated inference, enabling smooth real-time performance even on mobile hardware.</p><h3>NVIDIA Jetson Deployment with TensorRT ⚡</h3><p><a href="https://docs.ultralytics.com/models/yolo26/"><strong>YOLO26</strong></a><strong> on Jetson</strong> devices offers exceptional performance for edge AI applications. NVIDIA Jetson devices are powerful embedded computers with integrated GPUs, making them ideal for computer vision workloads.</p><p>TensorRT is NVIDIA’s software development kit designed for high-speed deep learning inference. It optimizes deep learning models for NVIDIA GPUs through techniques like layer fusion, precision calibration (INT8 and FP16), dynamic tensor memory management, and automatic kernel tuning. By converting YOLO26 models to TensorRT format, you can significantly enhance inference speed and efficiency on NVIDIA hardware. Learn more about <a href="https://developer.nvidia.com/tensorrt">TensorRT</a> and <a href="https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/">NVIDIA embedded systems</a>.</p><figure><img alt="NVIDIA Jetson Xavier: Edge AI powerhouse" src="https://cdn-images-1.medium.com/max/1024/1*bHww3SlQGURLCachcZUDXQ.jpeg" /><figcaption><em>NVIDIA Jetson Xavier: Edge AI powerhouse</em></figcaption></figure><h3>Hardware Overview</h3><p>We tested on an NVIDIA Jetson Xavier, which we consider an older but capable device. Think of it as a Raspberry Pi with a powerful GPU. While not state-of-the-art, it demonstrates that <strong>YOLO26 on edge</strong> can run on modest hardware.</p><h3>Docker Setup</h3><p><strong>Connect through SSH to your Jetson device:</strong></p><pre>ssh &lt;your-username&gt;@&lt;your-jetson-ip-address&gt;</pre><p><strong>Pull the Docker container:</strong></p><pre>docker pull ultralytics/ultralytics:latest-jetson-jetpack5<br>docker run -it --network=host --ipc=host --runtime=nvidia -v &quot;$(pwd):/workspace&quot; ultralytics/ultralytics:latest-jetson-jetpack5 /bin/bash<br>cd /workspace</pre><h3>Exporting Models for TensorRT</h3><p><strong>Export YOLO26s for TensorRT:</strong></p><pre>yolo export format=engine imgsz=384,640 half=True simplify=True device=0 batch=1 model=yolo26s.pt</pre><p><strong>Export YOLO26x for TensorRT:</strong></p><pre>yolo export format=engine imgsz=384,640 half=True simplify=True device=0 batch=1 model=yolo26x.pt</pre><h3>Performance Comparisons</h3><p>We tested <strong>YOLO26 on Jetson</strong> with and without TensorRT optimization.</p><p><strong>YOLO26s Performance:</strong></p><ul><li>Without optimization: ~50ms per frame (25 FPS)</li><li>With TensorRT optimization: ~14ms per frame (52 FPS)</li><li><strong>Improvement: 2.08x faster</strong></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*CsMpruRMHzliVSzWpKC9Lw.jpeg" /><figcaption><em>YOLO26 on Jetson: Performance without optimization (PyTorch)</em></figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*rivsDC7HiNHclWkgkotYVQ.jpeg" /><figcaption><em>YOLO26 on Jetson: Performance with TensorRT optimization</em></figcaption></figure><p>Key considerations:</p><ul><li>Use batch size 1 for single-source inference</li><li>Adjust image size based on your requirements</li><li>TensorRT optimization requires NVIDIA GPU</li><li>Jetpack version selection depends on your Jetson device</li></ul><h3>Running Predictions</h3><p><strong>With optimization:</strong></p><pre>yolo predict detect device=0 source=video_example/ model=yolo26s_1x384x640_half.engine half=True imgsz=384,640</pre><p><strong>Without optimization:</strong></p><pre>yolo predict detect device=0 source=video_example/ model=yolo26s.pt</pre><h3>Intel CPU Deployment with OpenVINO 🖥️</h3><p><a href="https://docs.ultralytics.com/models/yolo26/"><strong>YOLO26</strong></a><strong> on Intel CPU</strong> demonstrates how to deploy models on standard servers without NVIDIA GPUs. Intel’s OpenVINO toolkit provides excellent optimization for Intel processors.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*QWrysg92V6Gd9Fziz9uhtA.jpeg" /><figcaption>Image taken from <a href="https://docs.ultralytics.com/models/yolo26/">Ultralytics documentation</a>.</figcaption></figure><h3>Cloud Server Setup</h3><p>We tested on a <a href="https://hetzner.cloud/?ref=Dpjmw8zJflXY">Hetzner</a> cloud server (€3/month) with:</p><p><strong>Connect to server:</strong> <strong>Pull the Docker container:</strong></p><pre>docker pull ultralytics/ultralytics:latest-cpu docker run -it --network=host --ipc=host -v &quot;$(pwd):/workspace&quot; ultralytics/ultralytics:latest-cpu /bin/bash cd /workspace</pre><h3>Exporting Models for OpenVINO</h3><p><strong>Export YOLO26s for OpenVINO:</strong></p><pre>yolo export format=openvino imgsz=384,640 half=True simplify=True batch=1 model=yolo26s.pt</pre><h3>Performance Comparisons</h3><p><strong>YOLO26s Performance (2 CPU cores, 4GB RAM):</strong></p><ul><li>Without optimization: ~350ms per frame (2.8 FPS)</li><li>With OpenVINO: ~150ms per frame (6.7 FPS)</li><li><strong>Improvement: 2.3x faster</strong></li></ul><h3>Advanced Optimization: INT8 Quantization</h3><p>For further performance improvements, Intel OpenVINO supports INT8 quantization, which reduces model size and improves inference speed at the cost of minimal accuracy degradation.</p><p><strong>Run benchmarks:</strong></p><pre>yolo benchmark model=yolo26s.pt data=&#39;coco128.yaml&#39; imgsz=640 yolo benchmark model=yolo26s.pt data=&#39;coco128.yaml&#39; imgsz=640 format=openvino half=True yolo benchmark model=yolo26s.pt data=&#39;coco128.yaml&#39; imgsz=640 format=openvino int8=True</pre><h3>Best Practices for YOLO26 on Edge 🔧</h3><h3>Comparison Methodology</h3><p>When comparing performance, it’s essential to use the same image size and source for fair comparisons. Unfortunately, <strong>YOLO26 on edge</strong> cannot run without optimization on non-square images, so we standardized on 640×640 pixel images.</p><h3>Docker Benefits</h3><p>We highly recommend using Docker for <strong>YOLO26 on edge</strong> deployment because it provides an isolated environment with all dependencies, eliminates complex installations, and ensures consistent performance. <a href="https://docs.ultralytics.com/models/yolo26/?utm_source=infl&amp;utm_medium=general&amp;utm_campaign=yolo26&amp;utm_term=hn">Ultralytics</a> provides pre-built Docker containers for every platform:</p><ul><li>Mobile: TensorFlow Lite</li><li>NVIDIA Jetson: Jetpack 4, 5, 6</li><li>Intel CPU: OpenVINO</li></ul><h3>Conclusion 🎯</h3><p><strong>YOLO26 on edge</strong> marks a significant milestone in accessible, production-ready computer vision. By consolidating object detection, instance segmentation, pose estimation, and other vision tasks into a single framework, YOLO26 eliminates the complexity of managing multiple tools and models. If you’re running inference on a mobile device, an NVIDIA Jetson, or an Intel CPU, YOLO26 delivers state-of-the-art performance with remarkable flexibility.</p><p>However, moving from experimentation to production requires more than just a powerful model. It demands <strong>careful dataset preparation, domain-specific fine-tuning, optimization for your target hardware, and robust deployment infrastructure</strong>. That’s where expert guidance becomes invaluable.</p><h3>Professional Computer Vision for Enterprise 💼</h3><p>At <strong>NeuralNet Solutions</strong>, we specialize in <strong>enterprise-grade YOLO26 on edge</strong> solutions:</p><p>✅ Custom YOLO26 model training<br> ✅ Advanced segmentation and pose pipelines<br> ✅ Edge deployment (NVIDIA Jetson, embedded devices, mobile)<br> ✅ Cloud and on-premise scaling<br> ✅ TensorRT and OpenVINO optimization<br> ✅ End-to-end production systems</p><p>You can build a proof of concept or scale to millions of inferences per day, <strong>we help you deploy YOLO26 correctly and efficiently</strong>.</p><p>If you want to <strong>train, deploy, or scale YOLO26 on dge</strong> for your business, let’s talk.</p><p>👉 <strong>Schedule a free 30-minute consultation</strong><br><a href="https://cal.com/henry-neuralnet/30min">https://cal.com/henry-neuralnet/30min</a></p><p>🌐 Website: <a href="https://neuralnet.solutions/">https://neuralnet.solutions</a><br> 💼 LinkedIn: <a href="https://www.linkedin.com/in/henrymlearning/">https://www.linkedin.com/in/henrymlearning/</a></p><p><em>The companies adopting advanced computer vision today will lead their industries tomorrow.</em></p><p><strong>#YOLO26onEdge #EdgeAI #ComputerVision #YOLO26 #NVIDIAJetson #IntelOpenVINO #TensorRT #NeuralNetSolutions</strong></p><p><em>Originally published at </em><a href="https://neuralnet.solutions/yolo26-on-edge-devices-a-complete-guide"><em>https://neuralnet.solutions</em></a><em> on February 2, 2026.</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9047db79e83b" width="1" height="1" alt=""><hr><p><a href="https://ai.plainenglish.io/yolo26-on-edge-devices-a-complete-guide-9047db79e83b">YOLO26 on Edge Devices: A Complete Guide</a> was originally published in <a href="https://ai.plainenglish.io/">Artificial Intelligence in Plain English</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Ultralytics YOLO26: The Most Power Complete AI Vision Model]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://ai.plainenglish.io/ultralytics-yolo26-the-most-power-complete-ai-vision-model-7a890351a1d5?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/720/1*Bht24lUJE-4zkaqd3hNvyQ.gif" width="720"></a></p><p class="medium-feed-snippet">The new State-Of-The-Art models by Ultralytics, a complete review</p><p class="medium-feed-link"><a href="https://ai.plainenglish.io/ultralytics-yolo26-the-most-power-complete-ai-vision-model-7a890351a1d5?source=rss-a39e3cc02d8c------2">Continue reading on Artificial Intelligence in Plain English »</a></p></div>]]></description>
            <link>https://ai.plainenglish.io/ultralytics-yolo26-the-most-power-complete-ai-vision-model-7a890351a1d5?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/7a890351a1d5</guid>
            <category><![CDATA[computer-vision]]></category>
            <category><![CDATA[yolo26]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[ultralytics]]></category>
            <category><![CDATA[ultralyticsyolo26]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Tue, 20 Jan 2026 11:09:18 GMT</pubDate>
            <atom:updated>2026-01-29T19:38:30.562Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[What is the AI Engineer Salary in 2026? ]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/what-is-the-ai-engineer-salary-in-2026-8c2c1373cd7a?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1280/0*HUqd2NTWVUkyNS3G.png" width="1280"></a></p><p class="medium-feed-snippet">AI Engineer Q&amp;A: Career Paths, Salaries, and the Future of AI in 2026</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/what-is-the-ai-engineer-salary-in-2026-8c2c1373cd7a?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/what-is-the-ai-engineer-salary-in-2026-8c2c1373cd7a?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/8c2c1373cd7a</guid>
            <category><![CDATA[online-courses]]></category>
            <category><![CDATA[coursera]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[salary]]></category>
            <category><![CDATA[salary-negotiations]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Mon, 22 Dec 2025 12:05:24 GMT</pubDate>
            <atom:updated>2025-12-22T12:20:02.083Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Private AI Image Generator: Connect ComfyUI and Open WebUI]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/private-ai-image-generator-connect-comfyui-and-open-webui-7b25f7137207?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/1272/1*62XRnBOl3WyjAAlt8_fiaA.jpeg" width="1272"></a></p><p class="medium-feed-snippet">Build your private AI image generator for enterprise&#x2011;grade creativity, control, and privacy.</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/private-ai-image-generator-connect-comfyui-and-open-webui-7b25f7137207?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/private-ai-image-generator-connect-comfyui-and-open-webui-7b25f7137207?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/7b25f7137207</guid>
            <category><![CDATA[ai-image-generator]]></category>
            <category><![CDATA[comfy-ui]]></category>
            <category><![CDATA[text-to-image-generation]]></category>
            <category><![CDATA[open-webui]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Tue, 02 Dec 2025 12:52:28 GMT</pubDate>
            <atom:updated>2025-12-02T13:15:26.064Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Turn Images into Videos AI: Complete Tutorial with ComfyUI]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@hdnh2006/turn-images-into-videos-ai-complete-tutorial-with-comfyui-27d36a46ecb6?source=rss-a39e3cc02d8c------2"><img src="https://cdn-images-1.medium.com/max/720/1*jTMIfQqCFT2hX1EXwQqeXA.gif" width="720"></a></p><p class="medium-feed-snippet">How to turn images into videos using AI with open-source models, ComfyUI workflows, and private GPU infrastructure</p><p class="medium-feed-link"><a href="https://medium.com/@hdnh2006/turn-images-into-videos-ai-complete-tutorial-with-comfyui-27d36a46ecb6?source=rss-a39e3cc02d8c------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@hdnh2006/turn-images-into-videos-ai-complete-tutorial-with-comfyui-27d36a46ecb6?source=rss-a39e3cc02d8c------2</link>
            <guid isPermaLink="false">https://medium.com/p/27d36a46ecb6</guid>
            <category><![CDATA[image-to-video]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[neuralnet-solutions]]></category>
            <category><![CDATA[comfy-ui]]></category>
            <category><![CDATA[comfyui-workflow]]></category>
            <dc:creator><![CDATA[Henry Navarro]]></dc:creator>
            <pubDate>Wed, 29 Oct 2025 12:29:50 GMT</pubDate>
            <atom:updated>2025-11-03T10:39:25.329Z</atom:updated>
        </item>
    </channel>
</rss>