Qi Liu

RoleBreak, an open benchmark for long-horizon role-playing robustness in spoken dialogue, is introduced and four key patterns are found, highlighting persistent gaps in both long-horizon robustness and vocal expressiveness in spoken role-playing systems.

SimSkill transforms traffic simulation mastery by autonomously evolving its capabilities and consolidating knowledge without modifying its core model.

CastClaw achieves unprecedented accuracy in time-series forecasting by seamlessly integrating human expertise with autonomous model evaluation and revision.

Achieving superior driving performance with 40% fewer real-world interactions, Dreamer-SAC redefines sample efficiency in autonomous driving.