IEEE

Mitigating Object Hallucination in Large Vision-Language Models via Visual Attention Direct Preference Optimization

Abstract: Large Vision-Language Models (LVLMs) suffer from severe object hallucinations, leading them to frequently generate outputs that do not correspond to the image content, significantly reducing ...
GitHub

RF-DETR: Real-Time SOTA Object Detection, Instance Segmentation, and Keypoint Detection

RF-DETR is a real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow. Built on a DINOv2 vision transformer backbone, ...
Business Wire

MedX Health Launches SkinSecure™ to Bring Direct, Non-Invasive, Objective Biological Measurement to Skin Health Research

A cloud-based SaaS platform linking MedX’s native SIAscope imaging devices to CRO and sponsor workflows. Mapping collagen, melanin and haemoglobin in skin in around 30 seconds, without any need for ...
IEEE

Deep-Learning-Based Direct Attitude Estimation for Uncooperative Known Space Objects

Abstract: Attitude estimation for uncooperative known space objects plays a critical role in intelligent space technology. In recent years, deep-learning-based methods for estimating the attitude of ...