Multimodal Vision-Language Learning
Aishwarya Agrawal presents on the advancements and persistent challenges in multimodal vision-language learning, including the limitations of current large VL systems like GPT-4V.
Faculty & Researcher Profile
Aishwarya Agrawal
Assistant Professor of Computer Science
Aishwarya Agrawal is an Assistant Professor of Computer Science at the University of Montreal and Mila, specializing in multimodal vision-language learning.
1standalone talk1total lecture2hrecorded
Education & Doctoral Lineage
- PhD in Computer Science, Georgia Institute of Technology
- MS in Computer Science, Georgia Institute of Technology
- B.Tech in Computer Science, Jaypee Institute of Information Technology
Appointments & Career
- Assistant Professor, University of Montreal & Mila (2023-Present)
- Research Scientist, Google (2022-2023)
- Postdoctoral Researcher, Georgia Institute of Technology (2022)
- Research Intern, Google (2018, 2019, 2020, 2021)
- Research Intern, Facebook AI Research (2017)
Landmark Works & Courses
- VQA: Visual Question Answering
- Measuring and Improving Compositional Generalization in VQA
- Fairness in Visual Question Answering: A New Dataset and Analysis
- GQA: A New Dataset for Compositional Question Answering over Images
Intellectual Web & Academic Lineage · Aishwarya Agrawal
1 connectionVerified alma mater degrees, faculty appointments, co-authors, doctoral lineage, and intellectual peers across the archive.
Faculty Appointmentinstitution
University of Montreal, Mila
1 lectures
Faculty & Lecturer · University of Montreal, Mila
Standalone talks by Aishwarya Agrawal
1Self-contained public lectures, keynote addresses, and research seminars.