Julien BLANCHON's picture

Julien BLANCHON PRO

blanchon

·

AI & ML interests

Math

Recent Activity

liked a dataset about 2 hours ago

Yuanshi/Subjects200K

upvoted a paper about 3 hours ago

Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator

View all activity

Organizations

blanchon's activity

upvoted a paper about 3 hours ago

Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator

Paper • 2411.15466 • Published Nov 23, 2024 • 35

upvoted a collection 3 days ago

Graph-Aware Isomorphic Attention in Transformers

We present an approach to modifying Transformer architectures by integrating graph-aware relational reasoning into the attention mechanism. • 4 items • Updated 3 days ago • 2

upvoted a paper 6 days ago

CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models

Paper • 2407.15886 • Published Jul 21, 2024 • 2

upvoted a paper 10 days ago

In-Context LoRA for Diffusion Transformers

Paper • 2410.23775 • Published Oct 31, 2024 • 11

upvoted a paper 13 days ago

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering

Paper • 2408.09702 • Published Aug 19, 2024 • 10

upvoted a collection 17 days ago

DeepSeek-V3

3 items • Updated 7 days ago • 112

upvoted an article 25 days ago

Article

Metric and Relative Monocular Depth Estimation: An Overview. Fine-Tuning Depth Anything V2 👐 📚

By

•

Jul 10, 2024

• 44

upvoted a collection 25 days ago

OneDiffusion

Collection of different version of OneDiffusion models • 8 items • Updated 14 days ago • 2

upvoted a collection 26 days ago

Bamba

Collection of Bamba - hybrid Mamba2 model architecture based models trained on open data • 8 items • Updated 25 days ago • 18

upvoted a collection about 1 month ago

WavTokenizer-Medium-Large

https://arxiv.org/abs/2408.16532 • 5 items • Updated Oct 23, 2024 • 6

upvoted 3 collections about 2 months ago

Qwen2-VL

Vision-language model series based on Qwen2 • 16 items • Updated Dec 6, 2024 • 189

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 7 items • Updated 6 days ago • 33

Cephalo

Cephalo is a series of multimodal vision large language models (V-LLMs) designed to integrate visual and linguistic reasoning in materials science. • 15 items • Updated Oct 25, 2024 • 4

upvoted a paper about 2 months ago

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Paper • 2411.09595 • Published Nov 14, 2024 • 71

upvoted a paper 2 months ago

RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting

Paper • 2305.15685 • Published May 25, 2023 • 4

upvoted 2 collections 2 months ago

Cosmos Tokenizer

A suite of image and video tokenizers • 13 items • Updated 1 day ago • 36

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated 21 days ago • 198

upvoted 3 papers 2 months ago

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

Paper • 2409.11355 • Published Sep 17, 2024 • 29

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

Paper • 2410.22366 • Published Oct 28, 2024 • 77

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

Paper • 2410.06940 • Published Oct 9, 2024 • 6