Artemis Panagopoulou

Email Email GitHub GitHub LinkedIn LinkedIn Google Scholar Google Scholar
prof_pic.jpg

I am a fourth year PhD student at the University of Pennsylvania working in the intersection of Natural Language Processing and Computer Vision under the supervision of Professor Chris Callison-Burch and Professor Mark Yatskar.

My research focuses on advancing multimodal AI by integrating diverse modalities such as images, audio, video, text, and 3D. I address challenges in multimodal integration, benchmark development, and enhancing interpretability to build trustworthy models. My mission is to craft models that can see, listen, and comprehend with the nuance of perceptual coherenceβ€”models that are as robust as they are insightful, and as interpretable as they are performant, bringing us closer to a future where machines are not just tools, but reliable, insightful collaborators.

In addition to my academic pursuits, I have a strong passion for education. As a Teaching Assistant at the University of Pennsylvania, and through my community teaching experiences, I strive to challenge students with the beautiful and mentally stimulating concepts of mathematics, logic, and computer science, while also breaking down any mental barriers that may have been created from past negative experiences.

I am convinced that computer science is a field accessible to all, no matter their background, identity, or prior experience. In our technology-driven society, enabling people from various backgrounds and experiences to contribute to and shape the future of computer science is essential for creating strong and inclusive technological solutions.

news

Aug 29, 2024 πŸ“’ Announcement: Our paper Evaluating Vision-Language Models on Bistable Images has received best paper award at CMCL 2024!πŸŽ‰πŸ†
Aug 17, 2024 πŸ“’ Announcement: Our paper X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning has been accepted to ECCV 2024!πŸŽ‰
Mar 17, 2024 πŸ“’ Announcement: Our paper ULIP-2 has been accepted to CVPR2024!πŸŽ‰
Jan 25, 2024 πŸ“’ Announcement: We released X-InstructBLIP a simple and effective, scalable cross-modal framework to empower LLMs to handle a diverse range of tasks across a variety of modalities (image, text, video, audio, and 3D), without requiring modality-specific pre-training. Checkout our paper and codeπŸ€–πŸ€–
Sep 25, 2023 πŸ“’ Exciting News: Honored to have received the CETLI Graduate Fellowship for Teaching Excellence for the year 2023-2024.✨🎊