Yiming Liu

Achieving speech intelligibility that consistently surpasses ground-truth recordings, Phoenix TTS redefines the boundaries of zero-shot TTS and voice conversion.

Attack success rates in cowork agents can vary dramatically, with some models achieving up to 94.4% effectiveness in executing adversarial tasks.

Test suites can dramatically enhance issue localization accuracy, bridging the gap between abstract descriptions and concrete code.

Achieving over 2.2x inference speedup in Vision Transformers while maintaining accuracy reveals the untapped potential of hardware-software co-design in optimizing model performance.

Real-time differentiable clothing simulation enables robots to assist with dressing tasks more effectively than ever before, overcoming the limitations of traditional discrete garment models.

A unified decision process for multi-modal reasoning reveals that joint optimization of text and image generation can dramatically enhance performance in complex reasoning tasks.

Last-utterance clarifications can worsen parsing accuracy, with parser-agnostic rewrites introducing more errors than fixes in real-world applications.