27 1 9

Romain Beaumont

rom1504

https://rom1504.fr

AI & ML interests

Attention, similarity learning, multimodal

Recent Activity

upvoted an article 5 days ago

GLM-5.2: Built for Long-Horizon Tasks

new activity over 1 year ago

laion/relaion-high-resolution:Average Token Length

new activity almost 2 years ago

laion/relaion2B-en-research:How many disk space will be consumed if downloading all images?

View all activity

Organizations

liked a dataset almost 3 years ago

HuggingFaceM4/OBELICS

Viewer • Updated Aug 22, 2023 • 276M • 7.05k • 171

liked a dataset about 3 years ago

mlfoundations/datacomp_pools

Preview • Updated Aug 21, 2023 • 61.2k • 18

liked a model over 3 years ago

laion/CoCa-ViT-L-14-laion2B-s13B-b90k

Updated Feb 1, 2023 • 10.1k • 18

liked 2 Spaces over 3 years ago

Comparing Captioning Models

🔥

459

Generate captions using several AI models

CoCa

🐢

126

Generate descriptive captions for images using advanced AI technology

liked a model over 3 years ago

laion/CLIP-ViT-bigG-14-laion2B-39B-b160k

Zero-Shot Image Classification • Updated Jan 22, 2025 • 65.5k • 314

liked a dataset about 4 years ago

ILSVRC/imagenet-1k

Viewer • Updated Sep 17, 2025 • 1.43M • 105k • 844

liked a model about 4 years ago

sentence-transformers/clip-ViT-B-32-multilingual-v1

liked a Space about 4 years ago

Latent Diffusion

👁

512

Generate images from a text prompt with Latent Diffusion