Akshita Gupta M.Sc.
Multimodal Reliable AI
Working area(s)
Multimodal Reasoning and Generation
Contact
akshita.gupta@tu-...
Work
S4|23 217
Landwehrstr. 50A
64293
Darmstadt
Links
| Mar 2025 | ongoing | ELLIS PhD student at the Multimodal AI group (Supervisor: Prof. Dr. Marcus Rohrbach ), ELLIS co-supervisor: Dr. Federico Tombari (Google Zurich) |
| Jun 2024 | Feb 2025 | Research Intern, Apple (Cupertino, CA) |
| May 2024 | Aug 2024 | Scientist in Residence, NextAI (Toronto, Canada) |
| Jun 2023 | Mar 2024 | Research Intern, Microsoft Research (Remote) |
| Jan 2023 | May 2023 |
Applied Machine Learning Intern, Vector Institute (Toronto, Canada) |
| Sep 2022 | Sep 2024 | MASc in Computer Engineering (Specialization in AI) at University of Guelph, Canada -> Supervisor: Graham W. Taylor |
| Jan 2022 | Aug 2022 | Data Scientist, Bayanat for Mapping & Surveying (Abu Dhabi, UAE) |
| Dec 2018 | Jan 2022 | Research Engineer, Inception Institute of Artificial Intelligence (Abu Dhabi, UAE) |
| May 2018 | Aug 2018 | Research & Development Intern, Mozilla (Remote) |
| Aug 2014 | Dec 2018 | B.Tech in Computer Science Engineering at DIT University, India |
I'm interested in multimodal learning, video understanding, and open-world recognition, with a focus on developing scalable and generalizable AI systems. My research explores how models can efficiently adapt to new tasks with minimal supervision, leveraging cross-modal interactions between vision, language, and speech. I aim to build systems that go beyond static, task-specific training to enable robust, open-world reasoning. Additionally, I am interested in efficient model adaptation for large-scale AI, ensuring computational feasibility while maintaining strong performance.