A new paper at ICCV 2025, co-authored by MBZUAI Ph.D. student Dmitry Demidov, introduces Dense-WebVid-CoVR, a 1.6-million sample benchmark for composed video retrieval (CoVR). The benchmark features longer, context-rich descriptions and modification texts, generated using Gemini Pro and GPT-4o, with manual verification. The paper also presents a unified fusion approach that jointly reasons across video and text inputs, improving performance on fine-grained edit details. Why it matters: This work advances video search capabilities by enabling more human-like queries, which is crucial for creative and analytic workflows that require nuanced video retrieval.
MBZUAI Ph.D. students Muhammad Maaz and Hanoona Rasheed interned at Meta, developing a vision encoder for images and videos. They created PerceptionLM, a multimodal language model, to generate synthetic video-caption data to train the Perception Encoder. The team addressed the challenge of limited labeled video data by building a multimodal language model called PerceptionLM to understand video's spatial and temporal aspects. Why it matters: This highlights MBZUAI's strength in computer vision and provides students opportunities to contribute to cutting-edge research at global tech firms.
MBZUAI Ph.D. student Raza Imam and colleagues presented a new benchmark called MediMeta-C to test the robustness of medical vision-language models (MVLMs) under real-world image corruptions. They found that top-performing MVLMs on clean data often fail under mild corruption, with fundoscopy models particularly vulnerable. To address this, they developed RobustMedCLIP (RMC), a lightweight defense using few-shot LoRA tuning to improve model robustness. Why it matters: This research highlights the critical need for robustness testing in medical AI to ensure reliability in clinical settings, particularly in resource-constrained environments where image quality may be compromised.
KAUST Ph.D. student Mohammed Aljahdali received the Best Paper award at the International Conference on Federated Learning Technologies and Applications (FLTA) 2025 for his research on federated learning. His paper, "Flashback: Understanding and Mitigating Forgetting in Federated Learning," introduces an algorithm to help AI systems retain knowledge across diverse datasets while preserving privacy. Aljahdali's research, supervised by Professor Marco Canini, focuses on training machine learning models directly on user devices. Why it matters: This award recognizes the growing talent and impactful research emerging from Saudi universities in the field of privacy-preserving AI.
KAUST is highlighting women in STEM, including Professor Leena Ibrahim, Ph.D. student Amani Al-Amodi, and postdoc Dr. Wejdan Alghamdi. Leena Ibrahim's research focuses on understanding how sensory perception is established across development, studying the role of inhibitory neurons in the cortex. She aims to uncover how disruptions in sensory processing contribute to neurodevelopmental disorders like autism. Why it matters: Showcasing women's contributions can inspire future generations of female researchers in the Kingdom and beyond.
KAUST hosted Fireside Talks during its Spring Career Fair, focusing on aligning talent development with Saudi Arabia's evolving workforce needs in AI and sustainability. Speakers included KAUST's VP for Strategic National Advancement, a KAUST Ph.D. student/entrepreneur, the director of KAUST's AI Initiative, and the CEO of the National Center for AI (SDAIA). Discussions covered entrepreneurship, the transformative role of AI, and the importance of human-AI collaboration. Why it matters: The event highlights KAUST's key role in developing a skilled workforce to support Saudi Arabia's ambitions in AI and sustainable technologies.
KAUST Assistant Professor Dana Alsulaiman was named a L'Oréal-UNESCO For Women in Science Middle East Regional Young Talent. Alsulaiman was recognized for her work developing biomarker detection technologies for early and accurate disease detection. KAUST Ph.D. student Lila Aldakheel also received an award for her research on microplastics in mangrove forests. Why it matters: The recognition highlights the rising prominence and impact of female scientists at Saudi institutions in addressing key challenges like healthcare and environmental sustainability.
KAUST Ph.D. student Afrah Alothman is participating in the OceanX mission, exploring the Red Sea using advanced technology like manned submersibles. Alothman, also a mother of four, previously studied at King Faisal University and Dalhousie University, focusing on marine biology and climate change. She is the only Arab woman working on Phase 1 of the OceanXmission. Why it matters: This highlights KAUST's role in marine research and the increasing participation of Arab women in STEM fields, addressing critical environmental challenges in the region.