https://www.numansaeed.com/ Research updates, publications, and news from Numan Saeed, AI Research Scientist at MBZUAI working on medical imaging, multimodal learning, and AI for healthcare and climate. en Sat, 04 Jul 2026 12:38:22 GMT https://arxiv.org/abs/2606.28164 https://www.numansaeed.com/#news-2026-07-03-echosonar-r-accepted-at-eccv-2026 Publication Fri, 03 Jul 2026 00:00:00 GMT 🎉 Our paper "EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography" is accepted at ECCV 2026! EchoSonar-R is a multi-view reasoning vision-language model for joint disease classification and clinical report generation from echocardiography. https://openaccess.thecvf.com/content/CVPR2026F/papers/Ghosh_CarePilot_A_Multi-Agent_Framework_for_Long-Horizon_Computer_Task_Automation_in_CVPRF_2026_paper.pdf https://www.numansaeed.com/#news-2026-06-10-2-papers-accepted-at-cvpr-2026-findings Publication Wed, 10 Jun 2026 00:00:00 GMT 🎉 Two papers accepted to CVPR 2026 (Findings): CarePilot, a multi-agent framework for long-horizon computer task automation, and AnatomiX, an anatomy-aware grounded multimodal large language model for chest imaging. Links: CarePilot Paper (https://openaccess.thecvf.com/content/CVPR2026F/papers/Ghosh_CarePilot_A_Multi-Agent_Framework_for_Long-Horizon_Computer_Task_Automation_in_CVPRF_2026_paper.pdf), AnatomiX Paper (https://openaccess.thecvf.com/content/CVPR2026F/papers/Hashmi_AnatomiX_an_Anatomy-Aware_Grounded_Multimodal_Large_Language_Model_for_Chest_CVPRF_2026_paper.pdf). https://arxiv.org/pdf/2502.14807 https://www.numansaeed.com/#news-2026-06-05-fetalclip-accepted-at-npj-digital-medicine Publication Fri, 05 Jun 2026 00:00:00 GMT 🎉 Our paper "FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis" is accepted at npj Digital Medicine (Nature Portfolio)! FetalCLIP is the first vision-language foundation model for fetal ultrasound, pre-trained on 210,035 image-text pairs and achieving strong performance across classification, gestational age estimation, CHD detection, and segmentation. Links: Paper (https://arxiv.org/pdf/2502.14807), Website (https://biomedia-mbzuai.github.io/FetalCLIP/), Code (https://github.com/biomedia-mbzuai/fetalclip). https://arxiv.org/pdf/2510.00520 https://www.numansaeed.com/#news-2026-04-29-cardiobench-accepted-at-ijcai-2026 Publication Wed, 29 Apr 2026 00:00:00 GMT 🎉 Our paper "CardioBench: Do Echocardiography Foundation Models Generalize Beyond the Lab?" is accepted at IJCAI 2026! The benchmark unifies 8 datasets across 4 regression and 5 classification tasks for evaluating echocardiography foundation models with reproducible evaluation pipelines. https://www.numansaeed.com/mobilefetalclip/ https://www.numansaeed.com/#news-2026-03-06-mobilefetalclip-website-code-and-weights-released Publication Fri, 06 Mar 2026 00:00:00 GMT 🚀 Released MobileFetalCLIP, a mobile fetal ultrasound model distilled from FetalCLIP for handheld deployment. The project page, paper, code, and model weights are now publicly available. Links: Website (https://www.numansaeed.com/mobilefetalclip/), Paper (https://arxiv.org/abs/2603.05421), Code (https://github.com/numanai/MobileFetalCLIP), Weights (https://huggingface.co/collections/numansaeed/fetal-ultrasound-models). https://conferences.miccai.org/2026/en/default.asp https://www.numansaeed.com/#news-2026-01-31-selected-as-area-chair-for-miccai-2026 Award Sat, 31 Jan 2026 00:00:00 GMT 🎖️ Honored to be selected as an Area Chair for MICCAI 2026, the premier international conference on Medical Image Computing and Computer Assisted Intervention. https://arxiv.org/abs/2512.22278 https://www.numansaeed.com/#news-2026-01-25-fetal-gauge-benchmark-accepted-at-iclr-2026 Publication Sun, 25 Jan 2026 00:00:00 GMT 🎉 Our paper "FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound" is accepted to ICLR 2026! The benchmark comprises 42,000+ images and 93,000+ question-answer pairs spanning anatomical plane identification, visual grounding, fetal orientation, clinical view conformity, and diagnosis tasks. Links: Paper (https://arxiv.org/abs/2512.22278), Code (https://github.com/BioMedIA-MBZUAI/FETAL-GAUGE). https://arxiv.org/pdf/2510.03483 https://www.numansaeed.com/#news-2025-11-13-2-papers-accepted-at-wacv-2026 Publication Thu, 13 Nov 2025 00:00:00 GMT 🎉 Two papers accepted to WACV 2026: MAFM³ for modular adaptation of foundation models using lightweight "skill set" components for multi-domain medical AI, and DuPLUS, a dual-prompt vision-language framework for universal segmentation across 10 datasets (30+ organs) with prognosis capabilities achieving C-index of 0.69. Links: DuPLUS Paper (https://arxiv.org/pdf/2510.03483), DuPLUS Code (https://github.com/BioMedIA-MBZUAI/DuPLUS), MAFM³ Code (https://github.com/Areeb2735/CTscan_prognosis_VLM). https://arxiv.org/pdf/2510.00520 https://www.numansaeed.com/#news-2025-10-01-cardiobench-standardized-benchmark-for-echocardiography-fms Publication Wed, 01 Oct 2025 00:00:00 GMT 🫀 Released CardioBench, a comprehensive benchmark unifying 8 datasets across 4 regression and 5 classification tasks for evaluating echocardiography foundation models, with reproducible evaluation pipelines addressing key challenges in cardiac ultrasound. https://www.linkedin.com/feed/update/urn:li:activity:7376503202642526209/ https://www.numansaeed.com/#news-2025-09-23-hecktor-2025-challenge-concluded-successfully-at-miccai Award Tue, 23 Sep 2025 00:00:00 GMT 🎯 Successfully concluded the 4th HECKTOR Challenge at MICCAI 2025 in Daejeon with winners across 3 tasks: MedAI (Segmentation - won NVIDIA DGX SPARK!), SIMS-LIFE (Recurrence Prediction), and Interstellar (HPV Diagnosis). Special thanks to NVIDIA for sponsorship. https://arxiv.org/pdf/2509.00367 https://www.numansaeed.com/#news-2025-09-01-hecktor-dataset-released-1123-head-neck-cancer-pet-ct-studies Publication Mon, 01 Sep 2025 00:00:00 GMT 🗂️ Released a multimodal dataset of 1123 FDG-PET/CT studies from 10 international centers with expert annotations, radiotherapy dose maps, and clinical metadata for tumor segmentation, survival prediction, and HPV classification. Links: Paper (https://arxiv.org/pdf/2509.00367), Dataset (https://hecktor25.grand-challenge.org/), Code (https://github.com/BioMedIA-MBZUAI/HECKTOR2025). https://arxiv.org/pdf/2405.13482 https://www.numansaeed.com/#news-2025-07-25-survey-paper-accepted-at-acm-computing-surveys Publication Fri, 25 Jul 2025 00:00:00 GMT 📚 Comprehensive survey on continual learning in medical imaging accepted at ACM Computing Surveys. The paper addresses catastrophic forgetting and distribution shifts, providing taxonomy, practical insights, and future directions for the field. Links: Paper (https://arxiv.org/pdf/2405.13482), GitHub (https://github.com/BioMedIA-MBZUAI/awesome-cl-in-medical). https://arxiv.org/pdf/2508.09196 https://www.numansaeed.com/#news-2025-07-20-paper-accepted-at-mlhc-2025 Publication Sun, 20 Jul 2025 00:00:00 GMT 📄 FIVA accepted to MLHC 2025: A federated learning approach for universal CT segmentation that uses Bayesian inverse-variance aggregation for privacy-preserving collaboration with uncertainty quantification for clinical reliability. Links: Paper (https://arxiv.org/pdf/2508.09196), Code (https://github.com/asimukaye/fiva). https://arxiv.org/pdf/2508.15298 https://www.numansaeed.com/#news-2025-07-15-2-papers-accepted-at-bmvc-2025 Publication Tue, 15 Jul 2025 00:00:00 GMT 🎉 Two papers accepted to BMVC 2025: TPA for fetal CHD classification achieving 85.40% F1 score using temporal prompt alignment, and InMerge for enhancing robustness of medical imaging models through in-model merging of convolutional kernels. Links: TPA Paper (https://arxiv.org/pdf/2508.15298), InMerge Paper (https://arxiv.org/pdf/2502.20516). https://hecktor25.grand-challenge.org/ https://www.numansaeed.com/#news-2025-04-07-hecktor-2025-4th-head-neck-tumor-challenge-launched Announcement Mon, 07 Apr 2025 00:00:00 GMT 🏆 Proud to lead the 4th edition of the HECKTOR challenge, a satellite event at MICCAI 2025. This year's challenge focuses on three key tasks: segmentation, recurrence prediction, and HPV status diagnosis, utilizing a large multi-center dataset of over 1200 patients. https://arxiv.org/pdf/2502.14807 https://www.numansaeed.com/#news-2025-02-20-fetalclip-first-foundation-model-for-fetal-ultrasound-released Publication Thu, 20 Feb 2025 00:00:00 GMT 🚀 Released FetalCLIP, the first vision-language foundation model for fetal ultrasound images, trained on 210,035 paired images - the largest dataset of its kind. Demonstrates superior performance across classification, gestational age estimation, CHD detection, and segmentation tasks. Links: Paper (https://arxiv.org/pdf/2502.14807), Website (https://biomedia-mbzuai.github.io/FetalCLIP/). https://www.numansaeed.com/#news https://www.numansaeed.com/#news-2025-01-01-aed-2m-research-grant-awarded Award Wed, 01 Jan 2025 00:00:00 GMT 🏆 Awarded a AED 2M research grant from DOH for the project "AI for Cancer Prevention, Prediction, and Prognosis." https://arxiv.org/pdf/2403.09400 https://www.numansaeed.com/#news-2024-11-15-paper-accepted-at-wacv-2025 Publication Fri, 15 Nov 2024 00:00:00 GMT Our paper about the single domain generalization is accepted to WACV 2025. https://www.numansaeed.com/#news https://www.numansaeed.com/#news-2024-09-20-miccai-2024-oral-presentations Publication Fri, 20 Sep 2024 00:00:00 GMT Two of our papers at MICCAI are accepted for Oral Presentation. https://arxiv.org/pdf/2406.08486 https://www.numansaeed.com/#news-2024-07-10-paper-accepted-at-bmvc Publication Wed, 10 Jul 2024 00:00:00 GMT Our paper about the robustness of segmentation models is accepted to BMVC. https://miccai.org/index.php/about-miccai/awards/miccai-registration-and-travel-grants/ https://www.numansaeed.com/#news-2024-06-25-miccai-young-scientists-grant Award Tue, 25 Jun 2024 00:00:00 GMT Selected for MICCAI Young Scientists grant. https://miccai.org/index.php/about-miccai/awards/miccai-registration-and-travel-grants/ https://www.numansaeed.com/#news-2024-06-24-miccai-student-travel-award Award Mon, 24 Jun 2024 00:00:00 GMT Selected for MICCAI Student Travel Award. https://www.linkedin.com/posts/numansaeed-pk_ai-machinelearning-mbzuai-activity-7205086956878209024-Dhyk?utm_source=share&utm_medium=member_desktop https://www.numansaeed.com/#news-2024-06-10-valedictorian-speech-mbzuai Speaking Mon, 10 Jun 2024 00:00:00 GMT Delivered the Valedictorian speech of Class 2024 @ MBZUAI. https://www.numansaeed.com/#news https://www.numansaeed.com/#news-2024-05-20-4-papers-early-accepted-to-miccai-2024 Publication Mon, 20 May 2024 00:00:00 GMT Our 4 papers are early accepted to MICCAI 2024. https://dclibrary.mbzuai.ac.ae/mletd/61/ https://www.numansaeed.com/#news-2023-12-15-ph-d-in-machine-learning-completed Award Fri, 15 Dec 2023 00:00:00 GMT Completed my Ph.D. in Machine Learning @ MBZUAI! https://www.sciencedirect.com/science/article/pii/S1361841523002499 https://www.numansaeed.com/#news-2023-09-10-paper-accepted-to-media Publication Sun, 10 Sep 2023 00:00:00 GMT Our paper about the assessment of glioblastoma is accepted to MedIA journal. https://www.numansaeed.com/#news https://www.numansaeed.com/#news-2023-06-01-visiting-researcher-at-tum Collaboration Thu, 01 Jun 2023 00:00:00 GMT I started working as a Visiting Researcher at the TUM. https://proceedings.mlr.press/v227/abutalip24a https://www.numansaeed.com/#news-2023-03-10-paper-accepted-at-midl-2023 Publication Fri, 10 Mar 2023 00:00:00 GMT Our paper about generalizability is accepted to MIDL 2023. https://link.springer.com/chapter/10.1007/978-3-031-16449-1_31 https://www.numansaeed.com/#news-2022-06-10-paper-accepted-at-miccai-2022 Publication Fri, 10 Jun 2022 00:00:00 GMT Our paper about cancer diagnosis and prognosis is accepted to MICCAI 2022. https://link.springer.com/chapter/10.1007/978-3-030-98253-9_26 https://www.numansaeed.com/#news-2021-09-15-miccai-hecktor-2021-challenge-winner Award Wed, 15 Sep 2021 00:00:00 GMT We won the MICCAI Hecktor 2021 prognosis challenge.