Search

Results for "MOTLS"

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

arXiv · Jun 5

Researchers from MBZUAI have introduced VideoMolmo, a large multimodal model for spatio-temporal pointing conditioned on textual descriptions. The model incorporates a temporal module with an attention mechanism and a temporal mask fusion pipeline using SAM2 for improved coherence across video sequences. They also curated a dataset of 72k video-caption pairs and introduced VPoS-Bench, a benchmark for evaluating generalization across real-world scenarios, with code and models publicly available.

When the Cloud Meets the Ground - TRENDS Research & Advisory

The National · Mar 27

The article content was not provided. Therefore, a factual summary describing what happened cannot be generated as there is no information to extract.

MOFs for clean energy

KAUST · Dec 27

KAUST Professor Mohamed Eddaoudi is researching MOFs (metal-organic frameworks). MOFs have applications for clean energy. Why it matters: This research contributes to KAUST's and Saudi Arabia's broader clean energy and sustainability initiatives.

Faculty Focus: Mo Li

KAUST · May 1

Mo Li, an assistant professor of bioscience, is featured in a faculty focus article by KAUST. The article appears on the university's Biological and Environmental Science and Engineering Division page. Why it matters: This highlights KAUST's ongoing efforts to showcase faculty expertise and research areas within the university.