1
RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs
残差感知新方法让大模型二值化训练更准更高效，已被ICML 2026接收。
arXiv:2602.05367v3 Announce Type: replace Abstract: Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a crit…