Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Proposes the Mobius-v0 architecture: a globally shared Memory (FFN) stores knowledge vectors while multiple Reasoners (Self-Attention) iteratively query it via hidden states. A 7B model trained from scratch matches a Transformer baseline with 62.6% of the data, and Intern-S2-Mobius continually pretrained from Qwen3.5-35B matches its downstream score while delivering nearly 4x end-to-end inference speedup.