Mathieu Jouffroy

CCMat's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 articles 19 days ago

view article

Article

We’re open-sourcing our text-to-image model and the process behind it

• 

21 days ago

•

73

view article

Article

Text-to-image Architectural Experiments

• 

20 days ago

•

36

upvoted an article 23 days ago

view article

Article

You could have designed state of the art positional encoding

• 

Nov 25, 2024

•

403

upvoted 2 papers about 1 month ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 163

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6 • 489

upvoted a collection 3 months ago

DINOv3

Collection

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 396

upvoted 4 papers 9 months ago

Vision Transformers Need Registers

Paper • 2309.16588 • Published Sep 28, 2023 • 83

DINOv2: Learning Robust Visual Features without Supervision

Paper • 2304.07193 • Published Apr 14, 2023 • 8

Intuitive physics understanding emerges from self-supervised pretraining on natural videos

Paper • 2502.11831 • Published Feb 17 • 20

Cluster and Predict Latents Patches for Improved Masked Image Modeling

Paper • 2502.08769 • Published Feb 12 • 5

upvoted a paper 10 months ago

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Paper • 2502.02492 • Published Feb 4 • 66

upvoted a collection 10 months ago

PaliGemma 2 Release

Collection

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 32 items • Updated Jul 10 • 151

upvoted 2 articles 10 months ago

view article

Article

Open-R1: a fully open reproduction of DeepSeek-R1

• 
• 
• +1

Jan 28

•

887

view article

Article

We now support VLMs in smolagents!

• 
• 
• +1

Jan 24

•

110

upvoted a paper 10 months ago

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 428

upvoted 2 articles 11 months ago

view article

Article

Introducing smolagents: simple agents that write actions in code.

• 
• 
• +1

Dec 31, 2024

•

1.15k

view article

Article

Visualize and understand GPU memory in PyTorch

• 

Dec 24, 2024

•

254

upvoted 3 papers about 1 year ago

Pyramidal Flow Matching for Efficient Video Generative Modeling

Paper • 2410.05954 • Published Oct 8, 2024 • 40

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

Paper • 2410.06940 • Published Oct 9, 2024 • 10

Latent Intrinsics Emerge from Training to Relight

Paper • 2405.21074 • Published May 31, 2024 • 1