82 22 60

Hugo Laurençon

HugoLaurencon

HugoLaurencon

AI & ML interests

None yet

Articles

Docmatix - a huge dataset for Document Visual Question Answering

2 days ago

• 33

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 149

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

Mar 15

• 5

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model

Aug 22, 2023

• 15

Putting ethical principles at the core of research lifecycle

May 19, 2022

Organizations

HugoLaurencon's activity

upvoted an article 1 day ago

Article

Docmatix - a huge dataset for Document Visual Question Answering

2 days ago

• 33

upvoted a paper 24 days ago

WARP: On the Benefits of Weight Averaged Rewarded Policies

Paper • 2406.16768 • Published 25 days ago • 21

upvoted an article 25 days ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

26 days ago

• 139

upvoted a paper 2 months ago

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 93

upvoted 3 papers 3 months ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 243

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12 • 62

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Paper • 2211.05100 • Published Nov 9, 2022 • 26

upvoted a collection 3 months ago

Idefics2 🐶

Collection

Idefics2-8B is a foundation vision-language model. In this collection, you will find the models, datasets and demo related to its creation. • 11 items • Updated May 6 • 87

upvoted an article 3 months ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 149

upvoted 2 papers 4 months ago

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published Apr 2 • 102

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

Paper • 2403.09029 • Published Mar 14 • 54

upvoted a paper 5 months ago

How to Train Data-Efficient LLMs

Paper • 2402.09668 • Published Feb 15 • 37

upvoted a collection 5 months ago

From screenshots to HTML

Collection

WebSight is a dataset of 823,000 HTML/CSS codes representing synthetically generated English websites, each accompanied by a corresponding screenshot. • 4 items • Updated Apr 15 • 17

upvoted a paper 6 months ago

Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling

Paper • 2401.16380 • Published Jan 29 • 46

upvoted a paper 7 months ago

Generative Multimodal Models are In-Context Learners

Paper • 2312.13286 • Published Dec 20, 2023 • 33

upvoted a paper 9 months ago

Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Paper • 2311.00430 • Published Nov 1, 2023 • 54

upvoted 3 papers 10 months ago

upvoted a paper 12 months ago

How to Scale Your EMA

Paper • 2307.13813 • Published Jul 25, 2023 • 8

upvoted 2 papers about 1 year ago

LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding

Paper • 2306.17107 • Published Jun 29, 2023 • 12

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Paper • 2306.16527 • Published Jun 21, 2023 • 44