ML Engineer @huggingface. Building @paperswithcodee. @KU_Leuven grad. General interest in machine & deep learning. Making AI more accessible for everyone!
Let's remove VAEs and ViTs from video models!
🚀 Introducing 𝗣𝗶𝘅𝗲𝗹𝗨𝗠𝗠: an encoder-free unified multimodal model for image and video understanding and generation, directly in pixel space.
Code and model available today!
🌐
📄