The HUST Vision Lab, led by Prof. Xinggang Wang, is a research group at the Artificial Intelligence Institute, School of Electronic Information and Communications, Huazhong University of Science & Technology (HUST).
We are dedicated to pushing the frontiers of general visual intelligence and perception. Our core research areas include:
- Multimodal Foundation Models
- Visual Representation Learning
- Object Detection, Segmentation, and Tracking
- End-to-end Autonomous Driving
- Novel Neural Architectures
Our contributions to the field include a portfolio of influential works such as CCNet, Mask Scoring R-CNN, FairMOT, ByteTrack, EVA, MapTR, Vectorized Autonomous Driving (VAD), DiffusionDrive, Vision Mamba (Vim), 4D Gaussian Splatting (4DGS), YOLOS, YOLO-World, and LightningDiT & VA-VAE.
Highlights
Our Research
Our lab pioneers cutting-edge research in visual intelligence and perception. We focus on foundational challenges and innovative applications across General Visual Intelligence, Multimodal Foundation Models, Autonomous Driving, and 3D Generation to shape the future of AI.
Our Projects
Our projects transform cutting-edge research into solutions with real-world impact. From open-source models to pioneering applications, we are dedicated to tackling key challenges and driving technological progress.
Our Group
Our group consists of exceptional researchers and is led by distinguished experts in the field. United by a passion for innovation, we are dedicated to shaping the future of artificial general intelligence. Get to know the brilliant minds driving our groundbreaking work.