Frigate NVR, a free open-source AI security camera system using real-time object detection with OpenCV and TensorFlow, surges in popularity with over 33,000 GitHub stars and contributions from 745 developers worldwide.
Meta's SAM 3 is now live on GitHub, a groundbreaking AI model that detects, segments, and tracks objects across 4 million unique concepts in images and videos, achieving up to 80% of human performance — with an updated SAM 3.1 delivering even faster multi-object tracking via a new shared-memory approach.
Microsoft's AI-driven vulnerability system MDASH has discovered 16 previously unknown Windows flaws, including four critical remote code execution vulnerabilities now patched, using over 100 specialized AI agents to scan source code and top a major cybersecurity benchmark.
Microsoft's new AI security system MDASH, orchestrating over 100 specialized agents, achieves an industry-leading 88.45% on a real-world vulnerability benchmark and directly uncovers 16 new Windows CVEs — including four Critical remote code execution flaws — patched in today's Patch Tuesday release.
Facebook Research unveils Tuna-2, a groundbreaking multimodal AI model that ditches traditional vision encoders in favor of direct pixel patch processing, outperforming predecessors on diverse benchmarks while supporting both image understanding and generation tasks in 7B and 2B parameter sizes.
MIT, WPI, and Google researchers unveil WRING, a groundbreaking debiasing technique that eliminates bias in AI vision-language models by rotating bias-responsible coordinates in high-dimensional space, avoiding the 'Whac-A-Mole dilemma' of creating new biases while fixing old ones.
A groundbreaking new AI model called LingBot-Map's Geometric Context Transformer reconstructs 3D scenes in real-time at 20 FPS across sequences exceeding 10,000 frames, offering a powerful open-source tool for streaming 3D scene reconstruction with interactive browser-based visualization.
Niantic Spatial is turning a decade of Pokémon Go player photos into a 30-billion-image map that now powers real-world robot navigation, with Coco Robotics already deploying the technology across 1,000 delivery robots in major cities worldwide.
Baidu launches the Qianfan-VL series of vision-language models ranging from 3B to 70B parameters, alongside a new 4B Qianfan-OCR model featuring 'Layout-as-Thought' reasoning that tops major benchmarks, supports 192 languages, and is built for enterprise document understanding and visual reasoning tasks.
Tsinghua University and Tencent Hunyuan unveil Spatial-TTT, a groundbreaking streaming spatial intelligence framework that uses Test-Time Training to continuously update spatial memory from live video streams, achieving state-of-the-art results on video spatial benchmarks like VSI-Bench, with code, a 97k-sample dataset, and a lightweight model now publicly available.