Qiang Zhang

ARISE-RL transforms agent training by enabling robust self-evolution through a novel rubric-mediated co-evolution framework, achieving state-of-the-art performance across diverse tasks.

Switch Distillation not only enhances reasoning performance by up to 71% but also preserves factual recall, challenging the conventional trade-off in knowledge distillation.

SOLO achieves a remarkable 97.5% mean traversal success on complex terrains, showcasing a leap in humanoid locomotion capabilities.

Generating high-quality synthetic samples for minority classes can dramatically enhance classifier performance in imbalanced time-series tasks.

Achieve significant reasoning gains in frozen LLMs (+22.4%) without retraining by adaptively routing reward model guidance at the token level during inference.

Forget noisy user data: synthetic data unlocks predictable scaling laws for LLMs in recommendation, boosting recall by 130%.