Julien BLANCHON's picture

Julien BLANCHON PRO

blanchon

·

AI & ML interests

Math

Recent Activity

new activity 35 minutes ago

google/siglip2-base-patch16-224:Error while loading processor: TypeError: expected str, bytes or os.PathLike object, not NoneType

upvoted an article about 1 hour ago

SigLIP 2: A better multilingual vision language encoder

liked a model about 6 hours ago

google/siglip2-base-patch16-224

View all activity

Organizations

blanchon's activity

upvoted an article about 1 hour ago

Article

SigLIP 2: A better multilingual vision language encoder

about 18 hours ago

• 47

upvoted a paper 1 day ago

Gated Linear Attention Transformers with Hardware-Efficient Training

Paper • 2312.06635 • Published Dec 11, 2023 • 7

upvoted a collection 2 days ago

🇫🇷 Calme-3

Here you can find all the new Calme-3 models • 27 items • Updated 12 days ago • 13

upvoted an article 4 days ago

Article

Open Preference Dataset for Text-to-Image Generation by the 🤗 Community

Dec 9, 2024

• 54

upvoted a paper 8 days ago

Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding

Paper • 2401.04575 • Published Jan 9, 2024 • 17

upvoted a collection 9 days ago

Nomic Embed v2

Multilingual Embedding Models • 4 items • Updated 6 days ago • 11

upvoted 2 papers 9 days ago

VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation

Paper • 2502.07531 • Published 10 days ago • 13

Generating Multi-Image Synthetic Data for Text-to-Image Customization

Paper • 2502.01720 • Published 18 days ago • 6

upvoted 2 collections 9 days ago

Terminus XL

v-prediction SDXL clone with zero-terminal SNR noise schedule • 8 items • Updated Apr 24, 2024 • 7

AIMv2

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Nov 22, 2024 • 73

upvoted 2 collections 10 days ago

Ultravox v0.5

Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (fine-tuned) backbone. • 3 items • Updated 11 days ago • 5

R3GAN

R3GAN: A Modern BaselineGAN https://github.com/brownvc/R3GAN/ https://arxiv.org/abs/2501.05441 • 7 items • Updated Jan 10 • 10

upvoted 3 papers 10 days ago

The GAN is dead; long live the GAN! A Modern GAN Baseline

Paper • 2501.05441 • Published Jan 9 • 89

ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Paper • 2502.04320 • Published 15 days ago • 33

Material Anything: Generating Materials for Any 3D Object via Diffusion

Paper • 2411.15138 • Published Nov 22, 2024 • 44

upvoted a paper 11 days ago

Goku: Flow Based Video Generative Foundation Models

Paper • 2502.04896 • Published 14 days ago • 86

upvoted an article 16 days ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

18 days ago

• 106

upvoted a paper 19 days ago

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

Paper • 2412.16112 • Published Dec 20, 2024 • 22

upvoted 2 papers 21 days ago

Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion

Paper • 2402.03162 • Published Feb 5, 2024 • 19

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

Paper • 2401.15977 • Published Jan 29, 2024 • 38