104 36 72

Hugo Laurençon

HugoLaurencon

HugoLaurencon

AI & ML interests

None yet

Articles

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 63

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

Apr 15

• 160

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

• 24

Putting ethical principles at the core of research lifecycle

May 19, 2022

Organizations

HugoLaurencon's activity

upvoted a paper about 7 hours ago

Qwen2.5-Coder Technical Report

Paper • 2409.12186 • Published about 23 hours ago • 62

upvoted a paper about 8 hours ago

Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey

Paper • 2409.11564 • Published 2 days ago • 10

upvoted a paper 1 day ago

OmniGen: Unified Image Generation

Paper • 2409.11340 • Published 2 days ago • 51

upvoted a paper 2 days ago

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation

Paper • 2409.09214 • Published 6 days ago • 36

upvoted a paper 9 days ago

Towards a Unified View of Preference Learning for Large Language Models: A Survey

Paper • 2409.02795 • Published 15 days ago • 70

upvoted a paper 14 days ago

Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining

Paper • 2409.02326 • Published 16 days ago • 16

upvoted 2 papers 16 days ago

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Paper • 2408.16725 • Published 21 days ago • 49

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Paper • 2408.17253 • Published 20 days ago • 35

upvoted a paper 24 days ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published 28 days ago • 109

upvoted a paper 28 days ago

Scaling Laws and Interpretability of Learning from Repeated Data

Paper • 2205.10487 • Published May 21, 2022 • 1

upvoted a paper about 1 month ago

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Paper • 2408.08872 • Published Aug 16 • 96

upvoted a collection about 1 month ago

PDF Document / OCR Datasets

Collection

Document datasets with .pdf files that are usable with pixparse libraries and tools. • 2 items • Updated Mar 30 • 46

upvoted 2 papers about 1 month ago

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Paper • 2408.04840 • Published Aug 9 • 31

The Evolution of Multimodal Model Architectures

Paper • 2405.17927 • Published May 28 • 1

upvoted an article 2 months ago

Article

Docmatix - a huge dataset for Document Visual Question Answering

Jul 18

• 63

upvoted a paper 3 months ago

WARP: On the Benefits of Weight Averaged Rewarded Policies

Paper • 2406.16768 • Published Jun 24 • 22

upvoted an article 3 months ago

Article

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

Jun 24

• 166

upvoted 4 papers 5 months ago

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 98

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

Paper • 2404.14219 • Published Apr 22 • 250

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 • 28

upvoted a collection 5 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 • 88

upvoted an article 5 months ago

Article

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

Apr 15

• 160

upvoted 2 papers 6 months ago

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

Paper • 2404.02258 • Published Apr 2 • 103

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

Paper • 2403.09029 • Published Mar 14 • 54

upvoted a paper 7 months ago

How to Train Data-Efficient LLMs

Paper • 2402.09668 • Published Feb 15 • 38

upvoted a collection 7 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 8 months ago

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

Paper • 2401.16380 • Published Jan 29 • 46

upvoted a paper 9 months ago

Generative Multimodal Models are In-Context Learners

Paper • 2312.13286 • Published Dec 20, 2023 • 34

upvoted a paper 11 months ago

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

Paper • 2311.00430 • Published Nov 1, 2023 • 56

upvoted 2 papers 12 months ago

Vision Transformers Need Registers

Paper • 2309.16588 • Published Sep 28, 2023 • 77

Small-scale proxies for large-scale Transformer training instabilities

Paper • 2309.14322 • Published Sep 25, 2023 • 19

upvoted 4 papers about 1 year ago