Shaochen Zhong2 papers on this site (2024–2025)Stop Overthinking: A Survey on Efficient Reasoning for Large Language ModelsYang Sui, Yu-Neng Chuang, Guanchu Wang, et al.2025KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV CacheZirui Liu, Jiayi Yuan, Hongye Jin, et al.2024