Kyutai's Voice of Reason uses reinforcement learning to lift GLM-4-Voice from 27.3% to 77.1% on spoken GSM8K math.
Artificial intelligence systems may be good at generating text, recognizing images, and even solving basic math problems—but when it comes to advanced mathematical reasoning, they are hitting a wall.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results