Cong Wei(@CongWei1230):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! 🌐 https://t.co/RXUObhsSIZ 📄

Cong Wei

@CongWei1230

CS PhD @UWaterloo | MS & B.CS @UofT | Prev Intern @nvidia @AIatMeta @VectorInst

参加 July 2023

476 フォロー中 1.2K ファン

Cong Wei@CongWei1230

2026.10.01 23:56

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! 🌐 📄