Publications
Here is a selected list of my most relevant publications. You can also find the full list on my Google Scholar profile.
MDETR : Modulated Detection for End-to-End Multi-Modal Understanding
Aishwarya Kamath, Mannat Singh, Yann LeCun, Ishan Misra, Gabriel Synnaeve, Nicolas Carion
TLDR: We train a detector to detect objects based on a plain text description, and apply it to a variety of multimodal understanding tasks.