Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens Paper • 2501.07730 • Published Jan 13 • 17
Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k Paper • 2503.09642 • Published 2 days ago • 7
UniTok: A Unified Tokenizer for Visual Generation and Understanding Paper • 2502.20321 • Published 15 days ago • 29