Tag
A hands-on benchmark of TypeSafe's Jev 1.14 image input and new Box (bounding-box) output across 48 labeled COCO photos, finding strong yes/no accuracy (98.4%) but notable pitfalls: Box never answers "not found", confidence thresholds don't transfer between model versions, and wording strongly affects probabilities. The author recommends pairing every Box with a presence check, per-question thresholds, and pinning the model version.
Jev decision model now supports multimodal input, allowing images in both state and questions, plus a new Box type that returns YOLO-style bounding boxes for object localization. The update also supports parallel question answering for interactive vision applications, with images and Box still in experimental status.
介绍 Jag，一个 0.8B 视觉定位模型，通过单次前向传播直接预测边界框而非自回归生成坐标，在保持与 LocateAnything 相当精度的同时，速度提升 3.62 倍、峰值 GPU 显存降低 73.88%，并开源了模型权重、代码与在线演示。
NVIDIA has open-sourced the LocateAnything model, using parallel bounding box decoding technology to predict complete coordinates in one step, fast and accurate. The model has only 3B parameters and can run on consumer-grade GPUs, supporting video object localization, UI recognition, OCR, and other tasks.
NVIDIA's LocateAnything, a vision-language detection model rethinking bounding box prediction, is now available as a Hugging Face Space and trending #1 on the platform. The space template was created by @_akhaliq.
NVIDIA's research team released LocateAnything, a vision-language detection model that rethinks bounding box prediction, which is trending #1 on HuggingFace.