Intern Lumina U2

A unified multimodal diffusion language model that covers text QA, text-to-image generation, image understanding and editing, video understanding, and 3D understanding in one 16B-A1B MoE. Its language backbone is Ant Group's LLaDA-2.0 block-diffusion MoE, extended to vision through a fully discrete multi-codebook representation: Apple's AToken tokenizer describes each visual position with eight complementary codebooks, whose embeddings are concatenated into one backbone token on input and decoded by a codebook-depth autoregressive head with spatially parallel denoising on output. The inference code landed in August; the weights released on September 10 are the Ascend-trained checkpoint, with an NVIDIA-trained twin promised, and Shanghai AI Lab reports operator-level numerical alignment between the two backends.

Preliminary results: ChartQA 86.52, CharXiv-DQ 83.65, MathVision 33.22, DynaMath 56.37. Apache 2.0; the technical report is still marked "coming soon."