Researchers posting to arXiv (paper 2609.12155v1) proposed a person-centric formulation for bimanual hand-object interaction detection in which a single query predicts a structured output for one pers…
A new study from arXiv (arXiv:2609.00231v1) identifies visual-origin hallucination as a complementary cause of object hallucination in multimodal large language models (MLLMs), showing hallucinated sa…
Researchers at an undisclosed institution report that targeting 32 attention heads in the LLaVA-1.5-7B vision-language model reduces object hallucination in image captions, lowering CHAIRs from 0.370 …
Researchers introduced the first adversarial attack that directly optimizes an encoder-attention objective in detection transformers, reducing DETR-R50 mAP on COCO from 42.1 to 0.97, a ~4x reduction o…
Roboflow published a guide showing how to run RF-DETR inside NVIDIA DeepStream on a Jetson Orin NX, using JetPack 6.2, DeepStream 7.1, and TensorRT 10.3. The post details exporting RF-DETR Nano to ONN…
A new framework called C-GAP (Caption-Guided Augmentation and Prompting) improves minority-class detection in vision-language models by up to 53% without retraining or additional annotations, accordin…
Roboflow released a tutorial on fine-tuning RF-DETR Keypoints on custom data, demonstrating the process using a basketball court detection dataset with 33 landmarks. The model extends the RF-DETR arch…
Seeed's reComputer AI Lab, an edge AI development platform, now supports one-click deployment of YOLO models on RK3588/RK3576 hardware. The platform pre-packages 18 YOLO variants across YOLOv5, YOLOv8…
Roboflow launched RF-DETR Keypoint, a real-time end-to-end pose model that outperforms YOLO26-pose on accuracy and speed, with calibrated per-keypoint uncertainty and an Apache 2.0 license. The model …
Google's Gemini model now natively outputs bounding box coordinates as part of its vocabulary, eliminating the need for separate computer vision pipelines. The system normalizes all images to a 1000x1…