# vision Published articles for vision. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Hackers Stole Flock's Camera Software, Revealing How the Company Tracks Cars and People DevFeed: [Hackers Stole Flock's Camera Software, Revealing How the Company Tracks Cars and People]() Original publisher: [Read original article]() Author: EditorDavid Published: 2026-09-17T16:04:00Z Content type: news Language: en Sources: [Slashdot]() Topics: [Computer vision](), [Encryption](), [Software](), [data](), [Cryptography]() Tags: [camera](), [encryption](), [flock](), [image](), [logs](), [net-11](), [people](), [privacy](), [software](), [vision]() ### AI overview A joint investigation analyzed data copied from a Flock roadway camera after hackers breached the device. The recovered files showed that its on-device software detects people, vehicles, license plates, bicycles, and some graphics, while logs documented extensive image generation and vehicle activity. ### Source excerpt "Hackers ripped down a Flock camera above a roadway, made a near-complete copy of the data stored inside it, and shared the files with 404 Media and WIRED," according to an article published on both sites. Though Flock has described its system as protected by on-device encryption, "The hackers were able to copy the camera's storage and recover an encryption key stored on the device, which unlocked videos of thousands of vehicle detections." The hackers shared the material with 404 Media and the transparency nonprofit Distributed Denial of Secrets, which shared the data with WIRED. 404 Media and WIRED then analyzed those files as part of a joint investigation... [T]he joint analysis of the recovered data shows that software running on the device explicitly detects people as well as vehicles, license plates, and bicycles. The camera can produce dozens of images of a single passing vehicle and, according to several weeks of recovered logs, generated more than a million images. Its computer-vision software also sometimes isolated bumper stickers and other graphics, including, in one case, an American flag patch on a motorcyclist's saddlebag... According to our analysis, the camera's logs recorded about 21 days of activity across several periods. During those windows, the device photographed roughly 50,200 vehicles and generated about 1.6 million images. On a typical day, it logged around 3,300 vehicles, with a high of 4,454... The software running on the camera explicitly detects people, something which is typically overlooked in discussions around Flock cameras. When it spots a person, it records where they appear in the image and how confident it is in the detection. It was a collective calling itself stegan0gram that breached the cameras, according to the interview they did with Wired and 404 Media. "Why just destroy them when we can reverse engineer them and find the secrets of those spying on us?" Read more of this story at Slashdot. ## New AI technique could make minimally invasive surgeries safer and more precise DevFeed: [New AI technique could make minimally invasive surgeries safer and more precise]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-09-16T15:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [Artificial Intelligence](), [AI Research](), [3D](), [navigation]() Tags: [3d](), [ai](), [artificial-intelligence](), [computer-science-and-artificial-intelligence-laboratory-csail](), [computer-science-and-technology](), [computer-vision](), [electrical-engineering-and-computer-science-eecs](), [health-care](), [images](), [imaging](), [jameel-clinic](), [machine-learning](), [medical-devices](), [medical-imaging](), [minimally-invasive-surgery](), [mit-ibm-computing-research-lab](), [mit-schwarzman-college-of-computing](), [model](), [national-institutes-of-health-nih](), [navigation](), [paper](), [polina-golland](), [precision](), [real-time](), [research](), [school-of-engineering](), [vision](), [vivek-gopalakrishnan]() ### AI overview MIT researchers and collaborators developed xvr, an AI method that adapts to individual patients and rapidly aligns intraoperative X-rays with preoperative 3D medical scans. The technique is intended to improve surgical navigation for minimally invasive procedures. ### Source excerpt This patient-specific method, called xvr, helps doctors use X-rays for surgical navigation in fields such as orthopedics and neurosurgery. ## Designing Claude for ears, not eyes: An accessibility skill for blind and low-vision users DevFeed: [Designing Claude for ears, not eyes: An accessibility skill for blind and low-vision users]() Original publisher: [Read original article]() Author: Nubank Editorial Published: 2026-09-16T14:09:16Z Content type: article Language: en Sources: [Nubank]() Topics: [Accessibility](), [Claude](), [User interface design](), [screen](), [Users](), [Development]() Tags: [accessibility](), [accessible](), [claude](), [culture-values](), [data-science-machine-learning](), [development-environment](), [engineering](), [inclusive](), [life-at-nu](), [people-with-disabilities](), [text](), [users](), [vision]() ### AI overview Nubank describes BLIND-CLAUDE.md, an instruction set that adapts Claude responses for people who primarily use screen readers or read-aloud functionality. The approach treats auditory comprehension as an engineering constraint and changes behavioral instructions without modifying Claude or adding a native accessibility feature. ### Source excerpt How a cognitively diverse IT team at Nubank, they coded screen reader-friendly rules into Claude's instructions, treating auditory comprehension as an engineering constraint The post Designing Claude for ears, not eyes: An accessibility skill for blind and low-vision users appeared first on Building Nubank. ## Designing Claude for ears, not eyes: An accessibility skill for blind and low-vision users DevFeed: [Designing Claude for ears, not eyes: An accessibility skill for blind and low-vision users]() Original publisher: [Read original article]() Author: Nubank Editorial Published: 2026-09-16T14:09:16Z Content type: opinion Language: en Sources: [Nubank]() Topics: [Accessibility](), [Claude](), [Users](), [screen]() Tags: [accessibility](), [claude](), [configuration](), [culture-values](), [data-science-machine-learning](), [development-environment](), [life-at-nu](), [people-with-disabilities](), [vision]() ### AI overview Nubank describes BLIND-CLAUDE.md, an instruction set that adapts Claude responses for developers who primarily use screen readers or read-aloud tools. The approach addresses conventions such as Markdown tables, diffs, diagrams, long logs, and spatial references by adding behavioral instructions without modifying Claude or introducing a native accessibility feature. ### Source excerpt How a cognitively diverse IT team at Nubank, they coded screen reader-friendly rules into Claude's instructions, treating auditory comprehension as an engineering constraint The post Designing Claude for ears, not eyes: An accessibility skill for blind and low-vision users appeared first on Building Nubank. ## CVITEK CV1842H-P-based edge AI camera module offers night vision and AI-ISP support (Crowdfunding) DevFeed: [CVITEK CV1842H-P-based edge AI camera module offers night vision and AI-ISP support (Crowdfunding)]() Original publisher: [Read original article]() Author: Debashis Das Published: 2026-09-16T00:00:55Z Content type: news Language: en Sources: [CNX Software - Embedded Systems News]() Topics: [Artificial Intelligence](), [Embedded Systems](), [AI Inference](), [V](), [Arm](), [cpu](), [Open Source](), [Ethernet](), [Linux](), [Toit]() Tags: [ai](), [arm](), [artificial-intelligence-ai](), [camera](), [computer-vision](), [cpu](), [debug](), [edge-ai](), [embedded](), [ethernet](), [hardware](), [inference](), [kickstarter](), [linux](), [module](), [open-source](), [real-time](), [risc-v](), [robotics](), [rt-thread](), [soc](), [sophgo](), [tinyml](), [usb](), [video](), [vision]() ### AI overview The AIMORELOGY Ovis is an open-source modular AI vision camera built around the CVITEK CV1842H-P SoC. It provides full-color 1080p night vision, 1.5 TOPS edge AI inference, USB and Ethernet connectivity, and a dual-OS environment using Linux and RT-Thread. ### Source excerpt The AIMORELOGY Ovis is an open-source AI vision camera module built around the CVITEK CV1842H-P SoC, with full-color 1080p night vision and 1.5 TOPS edge AI inference in a compact modular design. It is designed for drones, robotics, security systems, smart cameras, and custom embedded vision products. The camera features a compact stacked design, with a 20 x 20 mm Core board that includes the CVITEK CV1842H-P SoC, 2 Gbit NAND flash, USB, and UART debug pads. A Sensor board with the SC235HAI image sensor connects on top and also adds Ethernet and UART interfaces. An optional CVBS board goes between the Sensor board and the Ovis Core board. AIMORELOGY Ovis specifications: Ovis Core Board SoC - CVITEK CV1842H-P CPU - 1x Arm Cortex-A53 core @ 1.1 GHz, 1x RISC-V C906 core @ 800 MHz NPU - 1.5 TOPS @ INT8 with BF16 support ISP - AI-ISP with real-time 1080p [...] The post CVITEK CV1842H-P-based edge AI camera module offers night vision and AI-ISP support (Crowdfunding) appeared first on CNX Software - Embedded Systems News. ## Arcturus Vision Camera Adds Color Passthrough & 3D Video Capture To Steam Frame DevFeed: [Arcturus Vision Camera Adds Color Passthrough & 3D Video Capture To Steam Frame]() Original publisher: [Read original article]() Author: David Heaney Published: 2026-09-15T06:59:00Z Content type: news Language: en Sources: [UploadVR]() Topics: [3D]() Tags: [3d](), [camera](), [capture](), [experimental](), [headsets-tech](), [rgb](), [video](), [vision]() ### AI overview The $149 Arcturus Vision Camera adds color passthrough to Valve's Steam Frame headset through its PCI-E expansion port. It also captures tracked stereoscopic 3D video, with options for 6-megapixel-per-eye HDR recording at 60fps or lower-resolution recording at 120fps. ### Source excerpt The $149 Arcturus Vision Camera, weighing just 10 grams, adds 6 megapixel per eye color passthrough to Steam Frame and captures tracked 3D HDR video. ## Apple Laid Off Around 100 Staff Working On Vision Pro, But Don't Panic DevFeed: [Apple Laid Off Around 100 Staff Working On Vision Pro, But Don't Panic]() Original publisher: [Read original article]() Author: David Heaney Published: 2026-09-14T13:06:59Z Content type: news Language: en Sources: [UploadVR]() Topics: [visionOS](), [Security](), [Meta]() Tags: [apple](), [article](), [company](), [cost](), [ecosystem](), [gaming](), [immersive-video](), [industry-news](), [meta](), [open](), [report](), [security](), [series](), [third-party](), [video](), [vision]() ### AI overview Apple laid off around 100 Vision Pro staff, largely shutting down its spatial gaming team and reducing its immersive video team. The cuts also affected security, spatial audio, Siri integration, and visionOS personnel, but Apple is not leaving the VR/MR market. The changes reflect limited gaming use and the high cost of producing immersive video. Apple may launch a slimmer, lighter successor headset around late 2028, although its continuation could depend on the wider headset market. ### Source excerpt Apple laid off around 100 staff working on Vision Pro, including "largely shutting down" the spatial gaming team and downsizing the immersive video team, Bloomberg's Mark Gurman reported. ## NeoEyes NE302 - A tiny USB-C-powered WiFi 6 Edge AI Vision camera based on STM32N6 MCU DevFeed: [NeoEyes NE302 - A tiny USB-C-powered WiFi 6 Edge AI Vision camera based on STM32N6 MCU]() Original publisher: [Read original article]() Author: Jean-Luc Aufranc (CNXSoft) Published: 2026-09-12T02:19:36Z Content type: news Language: en Sources: [CNX Software - Embedded Systems News]() Topics: [Embedded Systems](), [Microcontroller](), [wifi 6](), [Hardware](), [object-detection]() Tags: [c-c-plus-plus](), [camera](), [computer-vision](), [edge-ai](), [embedded-systems](), [hardware](), [mcu](), [object-detection](), [open-source](), [stm32](), [stmicro-stm32](), [vision](), [wifi-6]() ### AI overview The article reports on CamThink's NeoEyes NE302, a compact USB-C-powered Wi-Fi 6 edge AI vision camera built around the STM32N6 MCU. It describes the device's reduced memory and feature set compared with the NE301, along with its camera, wireless, debugging, video-encoding, object-detection, networking, OTA, and security capabilities. ### Source excerpt CamThink NeoEyes NE302 is a tiny WiFi 6 Edge AI camera based on an STM32N6 Arm Cortex-M55 MCU with Neural-ART NPU which the company says is "especially suitable for developers and makers". I initially thought about it as a smaller version of the CamThink NeoEyes NE301 based on the same STM32N6 MCU and 4MP OS04C10 camera sensor. But it's quite a different device. First, it doesn't have a battery, and the USB-C is only used for power. Memory and storage capacities have been reduced to 32 MB PSRAM and 64 MP SPI flash, and a range of built-in and optional features have been removed, including 4G LTE module (global or US), audio wafers, PIR motion connector, and a 16-pin GPIO header, as well as support for PoE power. CamThink NeoEyes NE302 specifications: Vision MCU STMicro STM32N6 MCU Core - Arm 32-bit Cortex-M55 CPU @ up to 800MHz with Arm Helium [...] The post NeoEyes NE302 - A tiny USB-C-powered WiFi 6 Edge AI Vision camera based on STM32N6 MCU appeared first on CNX Software - Embedded Systems News. ## iPhone Duo Seemingly Can't Capture Spatial Photos Or Video DevFeed: [iPhone Duo Seemingly Can't Capture Spatial Photos Or Video]() Original publisher: [Read original article]() Author: Craig Storm Published: 2026-09-11T21:15:11Z Content type: news Language: en Sources: [UploadVR]() Topics: [iphone](), [Artificial Intelligence](), [Machine learning]() Tags: [3d-media](), [ai](), [cameras](), [iphone](), [iphone-duo](), [machine-learning](), [photos](), [video](), [vision]() ### AI overview Apple's $1,999 iPhone Duo appears not to support native spatial photo or spatial video capture, despite having cameras and processing hardware comparable to supported iPhone Pro models. Apple has not explained the omission, and the device was not independently tested. ### Source excerpt Apple's $2000 iPhone Duo has two rear cameras, but seemingly can't capture spatial photos or video for viewing on Apple Vision Pro. ## DeepSeek V4.1 Flash now available on AI Gateway DevFeed: [DeepSeek V4.1 Flash now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [deepseek](), [Artificial Intelligence](), [API](), [Language models](), [AI-assisted coding](), [Claude Code](), [codex](), [cursor]() Tags: [ai](), [ai-gateway](), [api](), [caching](), [codex](), [context-window](), [cursor](), [deepseek](), [responses](), [tool](), [vercel](), [vision]() ### AI overview DeepSeek V4.1 Flash is now available through Vercel's AI Gateway, offering native image understanding, a 1 million token context window, responses up to 384,000 tokens, reasoning, tool use, and prompt caching. Developers can use it in Claude Code, Codex, Cursor, and other coding agents with the model name deepseek/deepseek-v4.1-flash. ### Source excerpt DeepSeek V4.1 Flash is now available on AI Gateway with native image understanding. V4.1 Flash has vision support and accepts text and images in the same request, so you can ask questions about screenshots, read charts, and extract information from visual content. The model has a 1 million token context window and supports responses up to 384,000 tokens, along with reasoning, tool use, and prompt caching. Its new architecture processes input and generates output with separate components, reducing the active computation needed for each stage. Use deepseek/deepseek-v4.1-flash as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select deepseek/deepseek-v4.1-flash in the agent. See the coding agents guide for details. Try DeepSeek V4.1 Flash in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more ## Fovii Showcases Immersive Videos And Their Creators On Apple Vision Pro DevFeed: [Fovii Showcases Immersive Videos And Their Creators On Apple Vision Pro]() Original publisher: [Read original article]() Author: Laura Mingail Published: 2026-09-08T14:00:00Z Content type: article Language: en Sources: [UploadVR]() Topics: [App](), [Streaming](), [ui]() Tags: [apple](), [business](), [creators](), [immersive-video](), [launch](), [subscriptions](), [ui](), [video](), [video-streaming](), [vision]() ### AI overview The Fovii app is available on Apple Vision Pro as a platform for on-demand and live-streamed 180-degree immersive videos. It also highlights the creators, studios, and production work behind each project, with additional materials such as behind-the-scenes videos and spatial photos. The app is free to download, with monthly and annual subscriptions, individual rentals, and a limited launch selection. ### Source excerpt The Fovii app on Apple Vision Pro offers a new platform to experience 180-degree immersive videos and discover the creators behind them. ## FunFitLand Brings Live Heart Rate Tracking Into VR With New Phone App DevFeed: [FunFitLand Brings Live Heart Rate Tracking Into VR With New Phone App]() Original publisher: [Read original article]() Author: Craig Storm Published: 2026-09-08T02:00:00Z Content type: news Language: en Sources: [UploadVR]() Topics: [App](), [data](), [Android](), [iOS](), [Mobile](), [Bluetooth](), [Meta](), [Server]() Tags: [android](), [app](), [apple](), [bluetooth](), [compatibility](), [fitness](), [meta](), [phone-app](), [servers](), [smartphone](), [testing](), [vision]() ### AI overview FunFitLand's new iOS and Android companion app connects compatible wearables to VR workouts on Meta Quest and Apple Vision Pro, displaying live heart rate data and recording workout metrics. ### Source excerpt FunFitLand's new smartphone app brings live heart rate data from compatible wearables directly into your VR workouts on Quest and Apple Vision Pro. ## Museas & Astronoma On Apple Vision Pro Support Curiosity & Discovery DevFeed: [Museas & Astronoma On Apple Vision Pro Support Curiosity & Discovery]() Original publisher: [Read original article]() Author: Laura Mingail Published: 2026-09-07T23:28:57Z Content type: article Language: en Sources: [UploadVR]() Topics: [3D](), [App]() Tags: [3d](), [apple](), [apps](), [art](), [design](), [discovery](), [education](), [exploration](), [interview](), [learning](), [science](), [technologies](), [vision]() ### AI overview An interview with Miguel Garcia Gonzalez examines how the Apple Vision Pro apps Museas and Astronoma use immersive design, real-world source material, and selective 3D presentation to encourage curiosity and exploration of art and science. ### Source excerpt What makes exploring art and science in spatial apps so compelling? We look at Apple Vision Pro apps Museas and Astronoma to learn how to design for curiosity and discovery. ## Building a Real-Time 3D Face Mask with MediaPipe, Threlte and Three.js DevFeed: [Building a Real-Time 3D Face Mask with MediaPipe, Threlte and Three.js]() Original publisher: [Read original article]() Author: Marek Jóźwiak Published: 2026-09-06T13:09:52Z Content type: tutorial Language: en Sources: [Codrops]() Topics: [Three.js webcam]() Tags: [3d](), [3d-face-mask](), [canonical-face-model](), [creative-coding](), [face-landmarks](), [face-mesh](), [face-tracking](), [facial-landmarks](), [generative-graphics](), [gpu](), [inference](), [interactive-3d](), [javascript-3d](), [mediapipe](), [mediapipe-face-landmarker](), [mesh](), [real-time](), [real-time-3d](), [real-time-face-tracking](), [svelte](), [three-js](), [three-js-face-mask](), [three-js-webcam](), [threlte](), [threlte-three-js](), [tutorial](), [tutorials](), [video](), [vision](), [wasm](), [webcam](), [webcam-effects](), [webcam-face-tracking](), [webgl](), [webgl-face-tracking]() ### AI overview Tutorial on building a real-time textured 3D face mask by mapping MediaPipe face landmarks onto a Three.js mesh with Threlte. ### Source excerpt Learn how MediaPipe's face landmarks, Google's canonical face model, and Three.js come together to create a real-time textured 3D face mask. ## Strengthening Camera Support in Zephyr for Advanced Vision Applications DevFeed: [Strengthening Camera Support in Zephyr for Advanced Vision Applications]() Original publisher: [Read original article]() Author: Zephyr Project Published: 2026-09-04T21:12:17Z Content type: article Language: en Sources: [Zephyr Project]() Topics: [Embedded Systems](), [Embedded Software Dev](), [Open Source](), [Framework](), [Artificial Intelligence](), [object-detection](), [real-time](), [Streaming](), [Robotics]() Tags: [ai](), [blog](), [cameras](), [development](), [embedded](), [embedded-systems](), [events](), [india](), [industry-conference](), [object-detection](), [open-source](), [open-source-summit](), [real-time](), [robotics](), [streaming](), [vision](), [zephyr](), [zero-copy]() ### AI overview This event recap examines proposed changes to Zephyr's camera and driver architecture for AI-driven vision workloads. The proposals include attaching metadata and inference results to individual video buffers and adding per-buffer callbacks to improve buffer ownership, reduce CPU wakeups, and support more manageable camera pipelines. The changes remain under exploration through prototypes and community discussions. ### Source excerpt The Zephyr community came together at Open Source Summit India 2026 in Mumbai to share knowledge and explore developments, tooling, and real-world applications across embedded systems. In this second post event blog, we recap two lightning talks from the Zephyr track focused on camera support. ## Strengthening Camera Support in Zephyr for Advanced Vision Applications DevFeed: [Strengthening Camera Support in Zephyr for Advanced Vision Applications]() Original publisher: [Read original article]() Author: Zephyr Project Published: 2026-09-04T21:12:17Z Content type: article Language: en Sources: [Zephyr Project]() Topics: [Embedded Software Dev](), [Embedded Systems](), [Open Source](), [Artificial Intelligence](), [systems]() Tags: [ai](), [blog](), [cameras](), [embedded](), [embedded-systems](), [events](), [industry-conference](), [object-detection](), [open-source](), [vision](), [zephyr]() ### AI overview This event recap examines proposed changes to Zephyr's camera and driver architecture for AI vision workloads. It discusses metadata attached to video buffers, per-buffer callbacks, zero-copy sharing, bounded latency, backpressure, and streaming coordination. The proposals remain under exploration through prototypes and community discussions. ### Source excerpt The Zephyr community came together at Open Source Summit India 2026 in Mumbai to share knowledge and explore developments, tooling, and real-world applications across embedded systems. In this second post event blog, we recap two lightning talks from the Zephyr track focused on camera support. ## ArduinoCore-Zephyr 1.0.0 adds support for Arduino VENTUNO Q, updates to Zephyr 4.4.1, and more DevFeed: [ArduinoCore-Zephyr 1.0.0 adds support for Arduino VENTUNO Q, updates to Zephyr 4.4.1, and more]() Original publisher: [Read original article]() Author: Jean-Luc Aufranc (CNXSoft) Published: 2026-09-04T10:27:38Z Content type: release Language: en Sources: [CNX Software - Embedded Systems News]() Topics: [Arduino](), [Zephyr RTOS](), [Embedded Systems](), [Embedded Software Dev](), [Hardware](), [Microcontroller](), [webcam](), [ci]() Tags: [arduino](), [bug-fixes](), [camera](), [ci](), [development-board](), [embedded-systems](), [hardware](), [mcu](), [real-time](), [release](), [software-management](), [ventuno-q](), [vision](), [zephyr](), [zephyr-os]() ### AI overview Arduino has released ArduinoCore-Zephyr 1.0.0 with support for the VENTUNO Q SBC and Nicla Vision camera, an update to Zephyr 4.4.1, and bug-fix and CI improvements. The article also lists supported Arduino platforms and installation steps. ### Source excerpt Arduino has just announced the release of ArduinoCore-Zephyr version 1.0.0, with new hardware support, including the VENTUNO Q SBC, an updated Zephyr 4.4.1 base, support for the Nicla Vision camera, and various fixes and improvements. Arduino first announced its plans to switch from Arm Mbed to Zephyr RTOS in July 2024, before releasing the first beta of Arduino Core for Zephyr in December of the same year. ArduinoCore-Zephyr 1.0.0 is not the first stable version, since that was version 0.90.0 released on July 29, 2026. The new release builds on that, so let's see what's new. ArduinoCore-Zephyr 1.0.0 highlights Support for Arduino VENTUNO Q SBC, specifically the STM32H5F5 real-time MCU on the board Update to Zephyr 4.4.1 with the latest upstream improvements, security fixes, and driver support Added Nicla Vision camera support to capture and process image data directly through the Zephyr core Various bug fixes and CI improvements Currently [...] The post ArduinoCore-Zephyr 1.0.0 adds support for Arduino VENTUNO Q, updates to Zephyr 4.4.1, and more appeared first on CNX Software - Embedded Systems News. ## NeoMME: an efficient Multimodal-native and Multilingual Encoder DevFeed: [NeoMME: an efficient Multimodal-native and Multilingual Encoder]() Original publisher: [Read original article]() Author: Tony Wu; Aurélien Lac Published: 2026-09-03T13:13:48Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [vlm](), [Fine-tuning](), [Large Language Model](), [GPU]() Tags: [apache](), [architecture](), [diffusion](), [embeddings](), [fine-tuning](), [gpu](), [hugging-face](), [multimodal](), [quantization](), [retrieval](), [training](), [transformers](), [vector](), [vision](), [vlm]() ### AI overview NeoMME is a family of multilingual multimodal encoders trained from scratch with a masked discrete-diffusion objective. It uses one bidirectional Transformer for text tokens and image patches, and is fine-tuned for visual document retrieval with dense and late-interaction embeddings. ### Source excerpt We introduce NeoMME, a family of 260M and 800M multilingual multimodal encoders. Unlike many generative visual language models, NeoMME does not use a separate pretrained vision tower or a causal language model. A single bidirectional Transformer processes both text tokens and raw image patches, and we train the entire model from scratch with a masked discrete-diffusion objective. We fine-tuned NeoMME for visual document retrieval using ColPali's page-image approach. ## Playco cut manual fixes 50% prototyping games with GPT-6 Astra DevFeed: [Playco cut manual fixes 50% prototyping games with GPT-6 Astra]() Original publisher: [Read original article]() Published: 2026-09-03T12:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Game engine](), [ide](), [Code]() Tags: [ai](), [ai-models](), [bugs](), [game-development](), [gpt](), [ide](), [performance](), [prototypes](), [prototyping](), [reasoning](), [startup](), [ui](), [vision]() ### AI overview Playco reports that GPT-6 Astra helped it create three themed game prototypes from a shared grey-box foundation, with 50% fewer manual fixes than its previous model. The company uses the model in Playbot, an AI-powered IDE connected to game engines for editing, testing, validation, and bug finding. ### Source excerpt Using GPT-6 Astra, Playco built three themed game prototypes from one grey box foundation and reported 50% fewer manual fixes than with the previous model. ## What Is the Raspberry Pi AI Kit? And What Replaced It? DevFeed: [What Is the Raspberry Pi AI Kit? And What Replaced It?]() Original publisher: [Read original article]() Author: Dhairya Parikh Published: 2026-09-03T01:38:42Z Content type: tutorial Language: en Sources: [RaspberryTips]() Topics: [Hardware](), [Machine learning](), [Person Detection](), [object-detection](), [Linux](), [Generative AI]() Tags: [artificial-intelligence](), [chatgpt](), [guide](), [hardware](), [how-to-tutorials](), [linux](), [models](), [object-detection](), [raspberry-pi](), [raspberry-pi-5](), [tutorial](), [update](), [vision]() ### AI overview A tutorial explaining what the Raspberry Pi AI Kit was, how it enabled AI and computer vision projects on the Raspberry Pi 5, why it was discontinued, and what replaced it. The article also highlights its affordability, Hailo collaboration, software examples, and current availability. ### Source excerpt When I first wrote about the Raspberry Pi AI Kit, it was one of the easiest ways to add AI acceleration to a Raspberry Pi 5. Well, things moved fast: Raspberry Pi has since discontinued it and introduced newer options instead. The official Raspberry Pi AI Kit made it much easier to run AI applications... ## PereStruct: Modular Pipeline and Dataset for Parsing Historical Newspapers DevFeed: [PereStruct: Modular Pipeline and Dataset for Parsing Historical Newspapers]() Original publisher: [Read original article]() Author: makSShan (Яндекс, Yandex Cloud & Yandex Infrastructure) Published: 2026-09-01T07:05:21Z Content type: tutorial Language: ru Sources: [Яндекс - Как мы делаем Яндекс / Статьи]() Topics: [Artificial Intelligence](), [яндекс](), [vlm]() Tags: [ai](), [ai-studio](), [bleu](), [computervision](), [ocr](), [perestruct](), [rouge](), [tag-4004cf5948d3](), [tag-65c8d6d9e736](), [tag-9bf5e01ce62e](), [tag-d27a0708d400](), [vision](), [vlm](), [yandex-ai-studio](), [yolo]() ### AI overview The article presents PereStruct, a modular pipeline for reconstructing articles from historical newspaper scans. It combines YOLO-based layout detection, Yandex Vision OCR, Yandex AI Studio models for error correction, and a semantic model for assembling article blocks; the authors also publish code, an annotated dataset, and a benchmark. ### Source excerpt Попробуйте открыть скан советской газеты и прочитать одну статью от начала до конца. Человек быстро замечает крупный заголовок, продолжение в соседней колонке и подпись под фотографией. Для алгоритма перед ним -- это выцветшая страница с десятками тесно расположенных прямоугольников, нестандартными шрифтами и неоднозначным порядком чтения. Даже если OCR правильно распознаёт почти все слова, на выходе ещё не получится документ. Нужно понять, какие фрагменты относятся к одной статье, где её начало, в каком порядке соединить блоки и что не следует включать в основной текст. Мы разработали PereStruct -- модульный пайплайн для разбора исторических газет. Он объединяет детектор вёрстки на базе YOLO, Yandex Vision OCR, коррекцию ошибок с помощью моделей Yandex AI Studio и отдельную модель семантической сборки статей. Вместе с кодом мы публикуем размеченный датасет и бенчмарк, чтобы другие команды могли изучать подход и ставить эксперименты на исторических документах. Читать далее ## Qwen 3.8 Max 0902 now available on AI Gateway DevFeed: [Qwen 3.8 Max 0902 now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-01T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [qwen](), [Language models](), [AI-assisted coding]() Tags: [ai-gateway](), [coding-agents](), [models](), [qwen](), [release](), [vision]() ### AI overview Qwen 3.8 Max 0902, a new Alibaba snapshot, is now available through AI Gateway. The release focuses on coding for larger projects, unsupervised long-horizon tasks, agent runs, and improved vision handling for charts and dense documents. It can be selected directly, pinned by its dated model ID, or reached through a rewrite routing rule. It is also supported in several coding-agent integrations and the model playground. ### Source excerpt Qwen 3.8 Max 0902 from Alibaba is now available on AI Gateway. This is a new snapshot of Qwen 3.8 Max, with the gains concentrated in coding on larger projects, long-horizon work that runs without supervision, and agent runs. Vision handling is more accurate on charts and dense documents. To use Qwen 3.8 Max 0902, set model to alibaba/qwen3.8-max-0902: The dated ID pins this snapshot, so a later release will not change what your requests run against. To move existing traffic onto it without a code change, add a rewrite routing rule. The gateway substitutes the destination transparently, so an application that still asks for alibaba/qwen3.8-max runs on the new snapshot: To use it in a coding agent, see the coding agents guide, then run vercel ai-gateway coding-agents setup to connect agents like Claude Code, Codex, OpenCode, Cursor, Pi, and more and select alibaba/qwen3.8-max-0902. Try Qwen3.8-Max-0902 in the model playground. You can view all language models available on AI Gateway. Read more ## CodeScanner.scan(): Barcode Scanning Without Rebuilding the Camera Pipeline DevFeed: [CodeScanner.scan(): Barcode Scanning Without Rebuilding the Camera Pipeline]() Original publisher: [Read original article]() Author: Shai Almog Published: 2026-08-26T00:00:00Z Content type: release Language: en Sources: [CodeName One]() Topics: [Barcode](), [QR Code](), [webcam](), [Code]() Tags: [camera](), [code](), [component](), [on-device](), [pipeline](), [vision]() ### AI overview Codename One adds CodeScanner and VisionCameraView, higher-level APIs for full-screen barcode scanning and embedded live vision analysis. The update also introduces typed results, coordinate helpers, image bridging, and analyzer-specific native dependency selection. ### Source excerpt CodeScanner and VisionCameraView put full-screen scanning and embedded live analysis above Codename One's on-device vision APIs, with typed results and simulator scripting. ## Luce: Relightable Gaussians for 3D Asset Generation DevFeed: [Luce: Relightable Gaussians for 3D Asset Generation]() Original publisher: [Read original article]() Published: 2026-08-26T00:00:00Z Content type: article Language: en Sources: [Apple Machine Learning Research]() Topics: [Artificial Intelligence](), [Benchmark]() Tags: [3d](), [ai](), [benchmark](), [computer-vision](), [generation](), [images](), [mesh](), [models](), [multimodal](), [techniques](), [vision]() ### AI overview Luce is a multimodal 3D representation for generating relightable assets from a single image. It combines geometry with physically based materials in a voxelized Gaussian cloud, compresses them into a material-aware latent space, and generates relightable PBR Gaussians and optional textured meshes. On Toys4K, it reports a 28% FID improvement over the strongest baseline and improves alignment on an AI-generated image benchmark. ### Source excerpt High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include physically based rendering (PBR) modalities such as albedo, metallic-roughness, and surface normals. We propose Luce, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for each modality. A variational autoencoder compresses this representation into a unified material-aware latent space. A... [Next page]()