่จปๅ†Šไธฆๅˆ†ไบซ้‚€่ซ‹้€ฃ็ต๏ผŒๅฏ็ฒๅพ—ๅฝฑ็‰‡ๆ’ญๆ”พ่ˆ‡้‚€่ซ‹็Žๅ‹ตใ€‚

Cong Wei
@CongWei1230
CS PhD @UWaterloo | MS & B.CS @UofT | Prev Intern @nvidia @AIatMeta @VectorInst
ๅŠ ๅ…ฅ July 2023
476 ๆญฃๅœจ้—œๆณจ    1.2K ็ฒ‰็ตฒ
Let's remove VAEs and ViTs from video models! ๐Ÿš€ Introducing ๐—ฃ๐—ถ๐˜…๐—ฒ๐—น๐—จ๐— ๐— : an encoder-free unified multimodal model for image and video understanding and generation, directly in pixel space. Code and model available today! ๐ŸŒ ๐Ÿ“„
้กฏ็คบๆ›ดๅคš