Hugues Sibille

HugSib's activity

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

upvoted a paper 6 days ago

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published 8 days ago • 103

updated a dataset 3 months ago

illuin/vdsid_filtered_test

Viewer • Updated Sep 30 • 100 • 35

upvoted a paper 4 months ago

GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering

Paper • 2409.06595 • Published Sep 10 • 37

updated a dataset 4 months ago

vidore/shiftproject_test

Viewer • Updated Sep 4 • 1k • 4.36k • 1

upvoted an article 6 months ago

view article

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By •

Jul 5

• 182

liked 2 Spaces 6 months ago

Running

93

🥇

Vidore Leaderboard

Running on Zero

107

🏃

ColPali

Document Retrieval

New activity in manu/ColPali-demo 6 months ago

feat : add retrieve top-k + improve app style

#1 opened 6 months ago by

HugSib

authored a paper 6 months ago

ColPali: Efficient Document Retrieval with Vision Language Models

Paper • 2407.01449 • Published Jun 27 • 42

updated a model 6 months ago

vidore/bipali

Updated Nov 5 • 2

updated 4 datasets 6 months ago

vidore/syntheticDocQA_energy_test

Viewer • Updated Jul 2 • 1k • 5.3k • 2

vidore/syntheticDocQA_healthcare_industry_test

Viewer • Updated Jul 2 • 1k • 4.26k

vidore/syntheticDocQA_government_reports_test

Viewer • Updated Jul 2 • 1k • 4.14k • 1

vidore/syntheticDocQA_artificial_intelligence_test

Viewer • Updated Jul 2 • 1k • 4.37k • 1

upvoted a paper 6 months ago

ColPali: Efficient Document Retrieval with Vision Language Models

Paper • 2407.01449 • Published Jun 27 • 42

updated a dataset 6 months ago

vidore/arxivqa_test_subsampled

Viewer • Updated Jun 28 • 500 • 4.74k • 3

New activity in vidore/vidore-leaderboard 6 months ago

Update Leaderboard

#1 opened 6 months ago by

HugSib

updated 2 collections 6 months ago

ViDoRe Page OCR (artifact)

Collection

ViDoRe benchmark with the full OCR text of each page. ⚠️ This dataset serves a intermediate step → use "ViDoRe Chunk OCR (baseline)" for evaluation! • 10 items • Updated 17 days ago

ViDoRe Chunk OCR (baseline)

Collection

The ViDoRe benchmark was passed to Unstructured to partition each page into text chunks. Detected figures/tables were captioned with Claude 3-Sonnet. • 11 items • Updated 17 days ago • 2