Théo Gigant's picture

Théo Gigant

gigant

·

https://giganttheo.github.io/

AI & ML interests

multimodal summarization, generative models

Articles

Design choices for Vision Language Models in 2024

Organizations

gigant's activity

upvoted a paper 1 day ago

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published 3 days ago • 53

upvoted an article 4 days ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

5 days ago

• 95

upvoted a paper 12 days ago

What matters when building vision-language models?

Paper • 2405.02246 • Published 15 days ago • 73

upvoted an article 18 days ago

Article

Improving Prompt Consistency with Structured Generations

19 days ago

• 41

upvoted an article 26 days ago

Article

seemore: Implement a Vision Language Model from Scratch

By

•

6 days ago

• 41

upvoted a collection 27 days ago

Vision Language Models Papers 🖼️💬📝

Papers about vision-language models, most important ones are on top of the list. • 27 items • Updated 19 days ago • 26

upvoted a collection about 1 month ago

Idefics2 🐶

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 13 days ago • 76

upvoted 2 articles about 1 month ago

Article

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

Apr 15

• 126

Article

🥐CroissantLLM: A Truly Bilingual French-English Language Model

By

•

Feb 5

• 4

upvoted 2 papers 3 months ago

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

Paper • 2305.02549 • Published May 4, 2023 • 5

World Model on Million-Length Video And Language With RingAttention

Paper • 2402.08268 • Published Feb 13 • 33

upvoted a paper 5 months ago

Training Compute-Optimal Large Language Models

Paper • 2203.15556 • Published Mar 29, 2022 • 7

upvoted a collection 7 months ago

Vigogne 🦙

Llama-based French chat LLMs • 11 items • Updated Feb 6 • 4

upvoted a paper 7 months ago

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

Paper • 2306.16527 • Published Jun 21, 2023 • 42

upvoted a collection 7 months ago

Computer Vision Backbones 🧩

Collection of useful computer vision backbones to fine-tune. It also includes large image classification models, that can be used as backbone. • 22 items • Updated Sep 19, 2023 • 11

upvoted a paper 10 months ago

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

Paper • 2211.05100 • Published Nov 9, 2022 • 23

upvoted a paper 11 months ago

Extending Context Window of Large Language Models via Positional Interpolation

Paper • 2306.15595 • Published Jun 27, 2023 • 52