Julien BLANCHON's picture

Julien BLANCHON PRO

blanchon

·

AI & ML interests

Math

Organizations

blanchon's activity

upvoted a collection 1 day ago

Cosmos Tokenizer

A suite of image and video tokenizers • 10 items • Updated 3 days ago • 11

upvoted a collection 7 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 5 days ago • 160

upvoted a paper 7 days ago

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Paper • 2409.11355 • Published Sep 17 • 28

upvoted 2 papers 8 days ago

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

Paper • 2410.22366 • Published 12 days ago • 71

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Paper • 2410.06940 • Published Oct 9 • 4

upvoted a collection 8 days ago

CC Dataset

6 items • Updated 8 days ago • 1

upvoted a collection 10 days ago

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 3 days ago • 89

upvoted a collection 11 days ago

Stable Diffusion 3.5

6 items • Updated 11 days ago • 83

upvoted a paper 16 days ago

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

Paper • 2410.13861 • Published 23 days ago • 53

upvoted a collection 19 days ago

DC-AE

Deep Compression Autoencoder • 7 items • Updated 18 days ago • 11

upvoted a paper 21 days ago

Movie Gen: A Cast of Media Foundation Models

Paper • 2410.13720 • Published 23 days ago • 86

upvoted 2 papers 22 days ago

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Paper • 2410.12705 • Published 24 days ago • 29

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25 • 73

upvoted a collection 22 days ago

LayerSkip

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated 14 days ago • 42

upvoted a collection 26 days ago

FLUX Controlnet

2 items • Updated 28 days ago • 3

upvoted a paper 27 days ago

MaskBit: Embedding-free Image Generation via Bit Tokens

Paper • 2409.16211 • Published Sep 24 • 16

upvoted a collection 29 days ago

Nutrition Dataset

7 items • Updated 29 days ago • 1

upvoted a paper about 1 month ago

Autoregressive Speech Synthesis without Vector Quantization

Paper • 2407.08551 • Published Jul 11 • 14

upvoted an article about 1 month ago

Article

Recoloring photos with diffusers

By

•

Oct 9

• 27

upvoted a paper about 1 month ago

Differential Transformer

Paper • 2410.05258 • Published Oct 7 • 165