Ge Liu

Training voice agents in an audio-native environment can more than double their task success rates and enhance efficiency without external dependencies.

The Qwen3-Omni model can reconstruct complex narratives from garbled audio inputs, revealing a hidden layer of reasoning that challenges our understanding of audio language processing.

LLMs can achieve a "free lunch" in reasoning tasks, simultaneously improving accuracy and reducing token usage by simply training them to solve multiple problems in parallel.