14 21 30

Mathieu Jouffroy

CCMat

mathieujouffroy

AI & ML interests

Computer Vision, NLP, Generative Models

Recent Activity

upvoted a paper 3 days ago

Vision Transformers Need Registers

upvoted a paper 3 days ago

DINOv2: Learning Robust Visual Features without Supervision

updated a collection 9 days ago

LLMs

View all activity

Organizations

None yet

CCMat's activity

upvoted 2 papers 3 days ago

Vision Transformers Need Registers

Paper • 2309.16588 • Published Sep 28, 2023 • 79

DINOv2: Learning Robust Visual Features without Supervision

Paper • 2304.07193 • Published Apr 14, 2023 • 6

upvoted 2 papers 10 days ago

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

Paper • 2502.11831 • Published 20 days ago • 18

Cluster and Predict Latents Patches for Improved Masked Image Modeling

Paper • 2502.08769 • Published 25 days ago • 4

upvoted a paper about 1 month ago

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

Paper • 2502.02492 • Published Feb 4 • 61

upvoted a collection about 1 month ago

PaliGemma 2 Release

Collection

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 32 items • Updated 1 day ago • 145

upvoted 2 articles about 1 month ago

Article

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

Jan 28

• 795

Article

We now support VLMs in smolagents!

Jan 24

• 91

upvoted a paper about 2 months ago

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

Paper • 2501.12948 • Published Jan 22 • 341

upvoted 2 articles about 2 months ago

Article

Introducing smolagents: simple agents that write actions in code.

Dec 31, 2024

• 840

Article

Visualize and understand GPU memory in PyTorch

Dec 24, 2024

• 193

upvoted a paper 4 months ago

Pyramidal Flow Matching for Efficient Video Generative Modeling

Paper • 2410.05954 • Published Oct 8, 2024 • 39

upvoted 2 papers 5 months ago

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

Paper • 2410.06940 • Published Oct 9, 2024 • 7

Latent Intrinsics Emerge from Training to Relight

Paper • 2405.21074 • Published May 31, 2024 • 1

upvoted a paper 10 months ago

Better & Faster Large Language Models via Multi-token Prediction

Paper • 2404.19737 • Published Apr 30, 2024 • 77

upvoted 4 papers 11 months ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22, 2024 • 256

Scalable Diffusion Models with Transformers

Paper • 2212.09748 • Published Dec 19, 2022 • 18

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

Paper • 2404.02905 • Published Apr 3, 2024 • 69

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published Apr 2, 2024 • 104

upvoted a paper 12 months ago

Evolutionary Optimization of Model Merging Recipes

Paper • 2403.13187 • Published Mar 19, 2024 • 52