Get the latest tech news

Xiaomi MiMo Reasoning Model

MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining - XiaomiMiMo/MiMo

Moreover, it was widely considered that achieving uniform and simultaneous improvements in both mathematical and code capabilities within a small model is challenging. By assigning fine-grained scores for test cases with varying difficulty levels, the policy can be more effectively optimized via dense reward signal. We implement a data re-sampling strategy for easy problems to enhance rollout sampling efficiency and stabilize policy updates, particularly in the later phases of RL training.

Get the Android app