Xiaomi MiMo moves to causal encoder-decoder

After DeepSeek V4.1 Flash, Xiaomi MiMo is moving to a causal encoder-decoder for its next-gen models. HySparse2: prompts run through only 25 of 49 layers. Decoder KV is projected from encoder states. At 1M context vs MiMo-V2: 5x less prefill compute, 4.5x smaller KV cache. https://t.co/ZVxZ4FDCDx Open article →