Roboflow
PulseAugur coverage of Roboflow — every cluster mentioning Roboflow across labs, papers, and developer communities, ranked by signal.
-
Roboflow Playground launches, One UI 9 wallpaper feature teased
Roboflow has launched a new tool called Roboflow Playground that allows users to test and compare 30 different computer vision models. This platform aims to simplify the process of evaluating various models for specific…
-
Roboflow launches Playground for comparing 30 computer vision models
Roboflow has launched a new interactive platform called the Roboflow Playground. This tool allows users to compare up to 30 different computer vision models in a low-code or no-code environment. The playground aims to s…
-
New research distinguishes hazards from anomalies in VLM safety evaluations
A new research paper introduces a method to better evaluate Vision-Language Models (VLMs) by distinguishing between true hazards and mere anomalies in visual scenes. The study found that current VLMs often misinterpret …
-
Roboflow unveils YOLO26 object detection model
Roboflow has introduced YOLO26, a new object detection model. This model is designed for computer vision tasks and aims to improve performance in deep learning applications.
-
New dataset Vines-DB aids AI in identifying ornamental vine species
Researchers have developed Vines-DB, a new dataset featuring over 1,200 high-resolution RGB images of seven ornamental vine species. Collected under field conditions, the dataset includes images captured over multiple g…
-
SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow)
Meta AI has released SAM 3, a significant advancement in their Segment Anything project, capable of concept segmentation, detection, and tracking in images and video using natural language prompts. This new model achiev…
-
Gemma 3n fully available in the open-source ecosystem!
Google DeepMind has fully released Gemma 3n, a mobile-first multimodal model designed for on-device applications. This new architecture supports image, audio, video, and text inputs, with text outputs, and is optimized …