de Rodrigo PRO

de-Rodrigo's activity

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

liked a model about 8 hours ago

Qwen/SAE-Res-Qwen3-8B-Base-W64K-L0_100

Updated 21 days ago • 81 • 4

liked a Space 2 days ago

Running on Zero

Agents

Featured

262

SmolDocling

🦆

262

Convert document images to structured text and data

updated a dataset 3 days ago

de-Rodrigo/steering

Viewer • Updated 3 days ago • 100 • 114

published a dataset 6 days ago

de-Rodrigo/steering

Viewer • Updated 3 days ago • 100 • 114

updated a dataset 14 days ago

de-Rodrigo/ifeval-decontaminate

Viewer • Updated 14 days ago • 150 • 65

published a dataset 16 days ago

de-Rodrigo/ifeval-decontaminate

Viewer • Updated 14 days ago • 150 • 65

updated a dataset 16 days ago

de-Rodrigo/ifeval-format-clean

Viewer • Updated 16 days ago • 250 • 63

published a dataset 19 days ago

de-Rodrigo/ifeval-format-clean

Viewer • Updated 16 days ago • 250 • 63

upvoted a paper about 1 month ago

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Paper • 2604.22748 • Published Apr 24 • 227

updated 2 models 2 months ago

de-Rodrigo/idefics2-re-verse

Image-Text-to-Text • Updated Mar 28

de-Rodrigo/idefics2-patient-merit

Image-Text-to-Text • Updated Mar 26

published a model 2 months ago

de-Rodrigo/idefics2-re-verse

Image-Text-to-Text • Updated Mar 28

updated a dataset 2 months ago

de-Rodrigo/re-verse

Viewer • Updated Mar 25 • 760 • 22 • 1

upvoted a paper 3 months ago

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Paper • 2504.02821 • Published Apr 3, 2025 • 10

upvoted 2 papers 4 months ago

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

Paper • 2602.00462 • Published Jan 31 • 21

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Paper • 2601.21957 • Published Jan 29 • 23

updated a Space 5 months ago

Sleeping

Embeddings

🐢

Embedding Space Exploration for models fine-tuned on MERIT

authored a paper 5 months ago

VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding

Paper • 2601.05125 • Published Jan 8 • 2

updated a dataset 5 months ago

de-Rodrigo/merit

Viewer • Updated Jan 9 • 478k • 8.25k • 6

upvoted a paper 5 months ago

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

Paper • 2601.05138 • Published Jan 8 • 19