🏗️ Building on HF

Miguel Alba

malba96

3 3

AI & ML interests

Senior ML Engineer interested in Visual Language Models (VLMs), Continual learning, Adversarial Robustness

Recent Activity

updated a collection about 1 month ago

Visual Fashion Model

updated a collection about 1 month ago

Visual Fashion Model

updated a collection 3 months ago

Visual Fashion Model

View all activity

Organizations

updated a collection about 1 month ago

Visual Fashion Model

Collection

Models for visual-language understanding on the fashion domain • 5 items • Updated 26 days ago

updated a collection 3 months ago

Visual Fashion Model

Collection

Models for visual-language understanding on the fashion domain • 5 items • Updated 26 days ago

commented on SigLIP 2: A better multilingual vision language encoder over 1 year ago

I think that example is very specific to multi-label classification. @praveenNathan if you want to continue the "pre-training" and use it for zero-shot classification (or create better vector representations for your specific domain) you can check open-clip implementation https://github.com/mlfoundations/open_clip ... they have the losses there for v1