Scholar
Walid Bousselham
Google Scholar ID: vbx_PS0AAAAJ
University of Bonn
Citations & Impact
Citations
257
H-index
6
i10-index
5
Publications
14
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Grounding Everything: Emerging Localization Properties in Vision-Language Transformers' accepted at CVPR 2024; developed several open-source libraries such as MaskInversion, LeGrad, GEM (Grounding Everything Method), and Data Stream; involved in research projects like DEX-AR, MaskInversion, LeGrad, etc.
Research Experience
- Spent the summer 2024 at MIT CSAIL as a visiting scholar, working with Hendrik Strobelt and Angie Boggust; attended the BMVA Symposium on Vision and Language, presenting both an oral and a poster; gave a talk at Cohere For AI - Community Talks.
Education
- Master of Engineering in Applied Mathematics from ENSTA Paris (France); Master of Science in Statistics and applied Probabilities from the National University of Singapore (NUS). PhD student at Tübingen AI Center, advised by Prof. Hilde Kuehne.
Background
- Primary research area: deep learning for multimodal models, including improving pretraining processes, understanding internal prediction mechanisms, and exploring zero-shot adaptation capabilities. Participating in the MIT-IBM Watson Sight and Sound Project.
Miscellany
- Personal interests not mentioned.
