Wei, C., Ren, X., Chu, B., Ren, W., Ling, H., Huang, J., Leal-Taixé, L., Fidler, S., Chen, W., Wang, Z., & Wu, J. Z. (2026). PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation. https://omanscience.com/ar/articles/pixelumm-encoder-free-unified-image-and-video-understanding-and-generation