Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL ModelsSivan DovehAssaf Arbelleet al.2023NeurIPS 2023
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual LearningJames Seale SmithLeonid Karlinskyet al.2023CVPR 2023
ConStruct-VL: Data-Free Continual Structured VL Concepts LearningJames SmithPaola Cascante-bonillaet al.2023CVPR 2023
Teaching Structured Vision & Language Concepts to Vision & Language ModelsSivan DovehAssaf Arbelleet al.2023CVPR 2023
FETA: Towards Specializing Foundational Models for Expert Task ApplicationsAmit AlfassyAssaf Arbelleet al.2022NeurIPS 2022
Unsupervised Domain Generalization by Learning a Bridge Across DomainsSivan HararyEli Schwartzet al.2022CVPR 2022
LKLeonid KarlinskyPrincipal Research Scientist @ MIT-IBM Watson AI Lab (Senior Technical Staff Member)