Abrar Majeedi

I'm a PhD candidate at the University of Wisconsin-Madison, working on multimodal deep learning. I am fortunate to be advised by Prof. Yin Li.

I have also gained valuable research experience through internships at Amazon, Microsoft and Dell EMC.

I'm on the job market for Research or Applied Scientist roles starting Dec 2025! My work focuses on LLMs, vision-language, and multimodal models in diverse applications. Feel free to email me at majeedi@wisc.edu if you’d like to discuss positions or potential research collaborations.

Email  /  CV  /  Scholar  /  Github

Research

My research focus is multimodal deep learning for sequential data. I am also interested in Vision Language Models, Large Language Models, and their applications in sequential data such as videos, sensor data (time series) and text.

News and Updates

• July 2025: Our paper "Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering" accepted as an Oral presentation at BioNLP @ ACL 2025.
• June 2025: Our team was awarded 2nd position in the Shared Task on grounded question answering (QA) from electronic health records (ArchEHR-QA 2025) at BioNLP@ACL 2025.
• June 2025: Our paper "LETS Forecast: Learning Embedology for Time Series Forecasting" has been accepted at the International Conference on Machine Learning (ICML) 2025.
• April 2025: Our team was awarded 1st place in the Machine Learning Challenge at the Pediatric Academic Societies (PAS) 2025 Conference, Honolulu, Hawaii.
• Jan 2025: Our Poster "Deep learning to quantify care manipulation activities in neonatal intensive care units" won an Award for Best Innovation in Neonatology at the Cleveland Clinic Children's SHINE (Syposium on Health Innovation and Neonatal Excellence) Conference, Orlando, FL.
• Nov 2024: Our paper "RICA2: Rubric-Informed, Calibrated Assessment of Actions" won the Best Poster Award at NSF Poster Competition at Purdue University, West Lafayette, IN.

Publications

A novel time series forecasting method that combines principles from nonlinear dynamical systems with deep learning to model latent temporal structure for accurate forecasts.

Action quality assessment in videos by incorporating human designed scoring rubrics while providing calibrated uncertainty estimates.

Auotmatically detect the glottic opening during neonatal intubation using video laryngoscopy to improve intubation outcomes.

Automatically quantify care manipulation activities in neonatal intensive care units (NICUs), while integrating physiological signal data to monitor neonatal stress in NICUs.

Assess perceptual quality of videos encoded by Machine Learning-based Video Codecs.

Won 2nd place in the Egocentric action detection challenge