Update README.md

README.md

@@ -11,38 +11,35 @@ pinned: true
 <img src="https://cdn-uploads.huggingface.co/production/uploads/66211794ae2f58da4f00d317/9hcMZ0KiikrSz4TYlCZzT.png" width="700">
 
 ## Description
-This Organisation contains all artefacts released with the paper [ColPali: Efficient Document Retrieval with Vision Language Models.]() [TODO add link],
+
+This organization contains all artefacts released with the paper [ColPali: Efficient Document Retrieval with Vision Language Models.]() [TODO add link],
 including the [ViDoRe](https://huggingface.co/collections/vidore/vidore-benchmark-667173f98e70a1c0fa4db00d) benchmark and our SOTA document retrieval model [*ColPali*](https://huggingface.co/vidore/colpali).
 
 A repository with **training** scripts can be found here. [GitHub](https://github.com/ManuelFay/colpali)
 A repository with **evaluation** scripts can be found here. [GitHub](https://github.com/tonywu71/vidore-benchmark)
 
-
-
-
 ### Abstract
-Documents are visually rich structures that convey information through text, as well as tables, figures, page layouts, or fonts. 
-While modern document retrieval systems exhibit strong performance on query-to-text matching, they struggle to exploit visual cues efficiently, hindering their performance on practical document retrieval applications such as Retrieval Augmented Generation. 
-To benchmark current systems on visually rich document retrieval, we introduce the Visual Document Retrieval Benchmark *ViDoRe*, composed of various page-level retrieving tasks spanning multiple domains, languages, and settings. 
-The inherent shortcomings of modern systems motivate the introduction of a new retrieval model architecture, *ColPali*, which leverages the document understanding capabilities of recent Vision Language Models to produce high-quality contextualized embeddings solely from images of document pages. 
-Combined with a late interaction matching mechanism, *ColPali* largely outperforms modern document retrieval pipelines while being drastically faster and end-to-end trainable.
 
-## Organisation
+Documents are visually rich structures that convey information through text, as well as tables, figures, page layouts, or fonts.
+While modern document retrieval systems exhibit strong performance on query-to-text matching, they struggle to exploit visual cues efficiently, hindering their performance on practical document retrieval applications such as Retrieval Augmented Generation.
+To benchmark current systems on visually rich document retrieval, we introduce the Visual Document Retrieval Benchmark *ViDoRe*, composed of various page-level retrieving tasks spanning multiple domains, languages, and settings.
+The inherent shortcomings of modern systems motivate the introduction of a new retrieval model architecture, *ColPali*, which leverages the document understanding capabilities of recent Vision Language Models to produce high-quality contextualized embeddings solely from images of document pages.
+Combined with a late interaction matching mechanism, *ColPali* largely outperforms modern document retrieval pipelines while being drastically faster and end-to-end trainable.
 
+## Models
 
-### Models
-  - [*ColPali*](https://huggingface.co/vidore/colpali): *ColPali* is our main contribution, it is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs), to efficiently index documents from their visual features.
+- [*ColPali*](https://huggingface.co/vidore/colpali): *ColPali* is our main contribution, it is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs), to efficiently index documents from their visual features.
   It is a [PaliGemma-3B](https://huggingface.co/google/paligemma-3b-mix-448) extension that generates [ColBERT](https://arxiv.org/abs/2004.12832)- style multi-vector representations of text and images.  
-    
-  - [*BiPali*](https://huggingface.co/vidore/bipali): It is an extension of original SigLip architecture, the SigLIP-generated patch embeddings are fed to a text language model, PaliGemma-3B, to obtain LLM contextualized output patch embeddings.
-  These representations are pool-averaged to get a single vector representation and create a PaliGemma bi-encoder, *BiPali*.
 
-  - [*BiSigLip*](https://huggingface.co/vidore/bisiglip): Finetuned version of original [SigLip](https://huggingface.co/google/siglip-so400m-patch14-384), a strong vision-language bi-encoder model.
+- [*BiPali*](https://huggingface.co/vidore/bipali): It is an extension of original SigLIP architecture, the SigLIP-generated patch embeddings are fed to a text language model, PaliGemma-3B, to obtain LLM contextualized output patch embeddings.
+  These representations are pool-averaged to get a single vector representation and create a PaliGemma bi-encoder, *BiPali*.
 
+- [*BiSigLIP*](https://huggingface.co/vidore/bisiglip): Finetuned version of original [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384), a strong vision-language bi-encoder model.
 
+## Datasets
 
-### Datasets
 We organized datasets into collections to constitute our benchmark ViDoRe and its derivates (OCR and Captioning). Below is a brief description of each of them.
+
 - [*ViDoRe Benchmark*](https://huggingface.co/collections/vidore/vidore-benchmark-667173f98e70a1c0fa4db00d): collection regrouping all datasets constituting the ViDoRe benchmark. It includes the test sets from different academic
   datasets ([ArXiVQA](https://huggingface.co/datasets/vidore/arxivqa_test_subsampled), [DocVQA](https://huggingface.co/datasets/vidore/docvqa_test_subsampled),
    [InfoVQA](https://huggingface.co/datasets/vidore/infovqa_test_subsampled), [TATDQA](https://huggingface.co/datasets/vidore/tatdqa_test), [TabFQuAD](https://huggingface.co/datasets/vidore/tabfquad_test_subsampled)) and from datasets synthetically generated spanning various themes and industrial applications:
@@ -51,11 +48,11 @@ We organized datasets into collections to constitute our benchmark ViDoRe and it
   
 - [*OCR Baseline*](https://huggingface.co/collections/vidore/vidore-chunk-ocr-baseline-666acce88c294ef415548a56): Datasets in this collection are the same as in ViDoRe but preprocessed for textual retrieving. The original ViDoRe benchmark was passed to Unstructured to partition each page into chunks. Visual chunks are OCRized with Tesseract.
 
-- [*Captioning Baseline*](https://huggingface.co/collections/vidore/vidore-captioning-baseline-6658a2a62d857c7a345195fd):  Datasets in this collection are the same as in ViDoRe but preprocessed for textual retrieving. The original ViDoRe benchmark was passed to Unstructured to partition each page into chunks. Visual chunks are captioned using Claude Sonnet. 
+- [*Captioning Baseline*](https://huggingface.co/collections/vidore/vidore-captioning-baseline-6658a2a62d857c7a345195fd):  Datasets in this collection are the same as in ViDoRe but preprocessed for textual retrieving. The original ViDoRe benchmark was passed to Unstructured to partition each page into chunks. Visual chunks are captioned using Claude Sonnet.
 
-**Intended use**
+## Intended use
 
-You can either load a specific dataset using the standard `load_dataset` function from huggingface. 
+You can either load a specific dataset using the standard `load_dataset` function from huggingface.
 
 ```python
   from datasets import load_dataset
@@ -80,20 +77,17 @@ To use the whole benchmark, you can list the datasets in the collection using th
       datasets.append(dataset)
 
 ```
-## Autorship + Citation
 
-**Contact**
+## Contact
 
-Please report any issues with the models or the benchmark or contact us: 
+- Manuel Faysse: manuel.faysse@illuin.tech
+- Hugues Sibille: hugues.sibille@illuin.tech
+- Tony Wu: tony.wu@illuin.tech
 
-- Manuel Faysse : [email?]()
-- Hugues Sibille : [email?]()
-- Tony Wu : [email?]()
+## Citation
 
-**BibTeX Citation**
-
-If you use any datasets or models from this organisation in your research, please cite the original dataset as follows:
+If you use any datasets or models from this organization in your research, please cite the original dataset as follows:
 
 ```latex
     [include BibTeX]
-```
+```