🔄 In a Training Loop

Serra

mserrao

3 5

·

https://www.linkedin.com/in/marc-serra-ortega/

AI & ML interests

Multimodal AI & World Models, Computer Vision, Efficiency

Recent Activity

authored a paper 5 days ago

CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books

authored a paper 5 days ago

Linear-Time Context Compression with State-Space Encoding

authored a paper 5 days ago

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

View all activity

Organizations

Papers 3

arxiv:2610.33006

arxiv:2609.25055

arxiv:2507.10053

spaces 1

Marc Serra Ortega

Research Engineer @ CVC — document & multimodal AI

models 0

None public yet

datasets 0

None public yet