Kim, H., Lee, J., Cho, S., Han, D., Han, I., & Kim, S. (2026). ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit Residuals. https://omanscience.com/en/articles/residualquant-kv-cache-quantization-for-looped-transformers-with-2-bit-residuals