Roboflow published a guide comparing zero-shot and fine-tuned computer vision models, recommending a hybrid approach where zero-shot models prototype and generate training data before fine-tuning for …
The Department of Energy's Genesis Mission is using Meta's SAM 3 and DINOv3 vision models to turn raw X-ray scans into labeled 3D images in about 15 minutes, according to a July 21st Meta blog post. B…
Roboflow released a multi-model auto-labeling workflow for segmentation that combines SAM 3, Google Gemini, and OpenAI's GPT to produce pixel-perfect masks via a 2-of-3 consensus rule, eliminating unc…
RF-DETR is the strongest starting point for most computer vision projects in 2026, topping both COCO and the real-world RF100-VL benchmark for object detection and segmentation, with SAM 3, DINOv3, GL…
Meta's SAM 3 model natively performs promptable concept segmentation, accepting a plain-language prompt such as "helmet" or "safety vest" and returning pixel-level masks for every matching object in a…
Roboflow released a guide on building a promptable object detection project using SAM 3, enabling users to detect objects like soda cans from text prompts without datasets or training. The workflow al…
NVIDIA Research released SpatialClaw, a training-free framework that uses code as the action interface for spatial reasoning in vision-language models. The framework achieves 59.9% average accuracy ac…
Researchers propose sub-semantic image segmentation, a new category that partitions images into stable appearance patterns described by language rather than naming whole objects. They introduce DETECT…
Roboflow has released an open-source inference library that enables developers to deploy computer vision models entirely offline on edge devices, laptops, or air-gapped systems without relying on clou…