Apply now arrow right icon
University news

Connecting you to the latest AI research and innovation

Stay up-to-date with the latest news from MBZUAI and the wider industry, featuring insights into ongoing University research, innovations, and developments shaping the future of artificial intelligence. The Node gathers expert commentary, press announcements, and initiatives from the University and its partners, keeping you informed on the most relevant trends and breakthroughs.

Results: 85 Tag: computer vision
Clear filters
The AI model improving air pollution prediction

Wednesday, 23 July, 2025

The AI model improving air pollution prediction

arrow image icon

MBZUAI's Salman Khan and Vishal Nedungadi won the best paper award at ICML's TerraBytes workshop for AirCast – a real-time air quality forecasting system.

Create and edit images like a smart artist

Monday, 21 July, 2025

Create and edit images like a smart artist

arrow image icon

Shaoan Xie and Lingjing Kong presented research at ICML that could make it possible to create and edit an image precisely, without collateral damage.

AI in bloom: How MBZUAI graduate is helping preserve the world’s plants

Wednesday, 16 July, 2025

AI in bloom: How MBZUAI graduate is helping preserve the world’s plants

arrow image icon

Kane Lindsay has enjoyed a gap year like no other — combining his passions for gardening, AI, and travel — while securing a Ph.D. in his home country.

New multimodal model brings pixel-level precision to satellite imagery

Tuesday, 15 July, 2025

New multimodal model brings pixel-level precision to satellite imagery

arrow image icon

MBZUAI's Akashah Shabbir presented GeoPixel at ICML: a multimodal model that supports the task of pixel grounding with remote sensing images.

MBZUAI’s UGRIP draws record global interest with projects for real-world impact

Thursday, 10 July, 2025

MBZUAI’s UGRIP draws record global interest with projects for real-world impact

arrow image icon

The Undergraduate Research Internship Program brought together 57 top-performing undergraduate students from leading global institutions.

A compact multimodal model for real-time video understanding on edge devices

Monday, 23 June, 2025

A compact multimodal model for real-time video understanding on edge devices

arrow image icon

Mobile-VideoGPT uses efficient token projection to enhance a model’s efficiency while maintaining high performance.

A two-stage approach for making AI image generators safer | CVPR

Wednesday, 18 June, 2025

A two-stage approach for making AI image generators safer | CVPR

arrow image icon

MBZUAI's Karthik Nandakumar presented STEREO at CVPR – a new framework that uses adversarial training and concept erasure to boost AI safety.

When models see what isn’t there: Reducing hallucinations with FarSight

Friday, 13 June, 2025

When models see what isn’t there: Reducing hallucinations with FarSight

arrow image icon

MBZUAI researchers shared FarSight at CVPR, showcasing its ability to improve the performance of multimodal large language models.

A new vision-language model for analyzing remote sensing data | CVPR

Thursday, 12 June, 2025

A new vision-language model for analyzing remote sensing data | CVPR

arrow image icon

Researchers at MBZUAI have developed EarthDial, a new VLM that can handle a range of complex geospatial data and perform numerous tasks.

Making computer vision more efficient with state-space models

Wednesday, 11 June, 2025

Making computer vision more efficient with state-space models

arrow image icon

Researchers from MBZUAI have developed a new set of SSMs that they will present at the Computer Vision and Pattern Recognition Conference.

Ready to start your new education journey?

Apply now arrow right icon