Serra

mserrao's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 5 days ago

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

Paper • 2507.10053 • Published Jul 14, 2025 • 1

Linear-Time Context Compression with State-Space Encoding

Paper • 2610.33006 • Published Oct 7 • 1

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

Paper • 2609.25055 • Published Sep 8 • 1

updated a Space 6 days ago

Running

Marc Serra Ortega

📄

Research Engineer @ CVC — document & multimodal AI

published a Space 6 days ago

Running

Marc Serra Ortega

📄

Research Engineer @ CVC — document & multimodal AI

upvoted 2 papers 6 days ago

ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains

Paper • 2609.25055 • Published Sep 8 • 1

Linear-Time Context Compression with State-Space Encoding

Paper • 2610.33006 • Published Oct 7 • 1

liked a model 4 months ago

linear-moe-hub/Gated-Deltanet-1.3B

1B • Updated Mar 18, 2025 • 330 • 8

liked 2 Spaces 6 months ago

Running

4.13k

The Ultra-Scale Playbook

🌌

4.13k

The ultimate guide to training LLM on large GPU Clusters

Running on Zero

Agents

684

MinerU Document Extraction Tools

📚

684

Embedded MinerU document extraction demo

liked a Space 7 months ago

Running

Featured

79

FinePDFs: Liberating 3T of the finest tokens from PDFs

📄

79

Explore the FinePDFs PDF token dataset

updated a dataset 8 months ago

VLR-CVC/DocVQA-2026

Viewer • Updated Sep 8 • 73 • 944 • 74

liked a dataset 9 months ago

VLR-CVC/DocVQA-2026

Viewer • Updated Sep 8 • 73 • 944 • 74

upvoted a paper about 1 year ago

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6, 2025 • 521