3 papers
cs.CV2026
Unsupervised Domain Adaptation for Enhanced Radiometer Image Precipitation Estimation using Conditional Flow Matching
Victor Enescu, Assaad Zeghina, Matthieu Meignin +2
Deep generative networks have recently achieved unprecedented performance in precise image and video editing using sophisticated textual prompts. However, the effectiveness of such…
cs.CV2025
Deep Generative Continual Learning using Functional LoRA: FunLoRA
Victor Enescu, Hichem Sahbi
Continual adaptation of deep generative models holds tremendous potential and critical importance, given their rapid and expanding usage in text and vision based applications. Incr…
cs.CV2025
Frugal Incremental Generative Modeling using Variational Autoencoders
Victor Enescu, Hichem Sahbi
Continual or incremental learning holds tremendous potential in deep learning with different challenges including catastrophic forgetting. The advent of powerful foundation and gen…