Shu'ang Yu

Robots can learn from fleet-wide failures and successes to autonomously improve their policies, achieving near-perfect reliability without any new human corrections.

Even top-performing robotic value models struggle with nuanced instruction grounding and history-dependent progress tracking, exhibiting inconsistent value judgments across valid execution orders.

Co-training speculative draft models directly inside 122B, 256K-token distributed RL runs removes the massive rollout bottleneck without causing pipeline stalls or context-parallel memory blowups.

Achieving up to 5.0× speedup in autoregressive TTS synthesis without sacrificing quality could revolutionize real-time voice applications.