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

DART: Detect Anything in Real Time

Training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector. Achieves 55.8 AP on COCO val2017 (80 classes) at 15.8 FPS (4 classes, 1008px) on a single RTX 4080.
JD Supra

The Intellectual Property Behind the Soccer World Cup: How to Avoid Offsides When Securing IP “Goals”

As the 2026 FIFA World Cup unfolds across North America, the world is focused on the players, coaches, and dramatic moments on the field.
VoxelMatters

AFIT doctoral student builds custom 3D printer to produce radiation detectors for USAF

Chandler Moore, a doctoral student at the Air Force Institute of Technology (AFIT), part of Air University, led the institute ...
IEEE

An Efficient Object Detection Model Based on NanoDet

Abstract: Object detection is a fundamental task in computer vision, involving the prediction of bounding boxes and class labels for Regions of Interest (ROI) within images. Traditionally, ...