Luo Fuli, head of the Xiaomi Mimo team, published an article on the X platform to reveal for the first time the progress of reinforcement learning training for Xiaomi's new model MiMO-v2.6. Luo Fuli said that in the past six months, the team has been conducting research on the question of how far reinforcement learning can be extended. Currently, MiMO-v2.6 is in the process of reinforcement learning, and the team is expanding the scale in three directions, including computational resources, training environment and task system, and reward evaluation mechanisms.

Luo Fuli, head of the Xiaomi Mimo team, published an article on the X platform to reveal for the first time the progress of reinforcement learning training for Xiaomi's new model MiMO-v2.6. Luo Fuli said that in the past six months, the team has been conducting research on the question of how far reinforcement learning can be extended. Currently, MiMO-v2.6 is in the process of reinforcement learning, and the team is expanding the scale in three directions, including computational resources, training environment and task system, and reward evaluation mechanisms.