Hugging Face Daily Papers·· 2026-10-14AI score24
Intern Lumina U2: a multi-codebook diffusion language model for full visual understanding and image generation
Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation
AI briefing
Intern Lumina U2 is the first diffusion language model to represent multi-codebook visual tokens in a fully discrete space, where each visual position is represented by a set of codes from complementary codebooks; at the input, embeddings are concatenated by position, and at the output, a lightweight multi-codebook autoregressive head predicts the codes position by position, while the diffusion backbone processes all positions in parallel.
Open original arxiv.org