Ni, Z., Hu, Z., Cao, R., Ren, W., Shi, B., Zhang, W., Cao, S., Shi, Z., Zhang, Z., Wen, H., & Hu, Z. (2026). ReTaCo: Residual-Target Control for On-Policy Distillation. https://omanscience.com/ar/articles/retaco-residual-target-control-for-on-policy-distillation