MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM 文章

ArXiv CS.CL2026-05-26NEWSen作者: Dongwei Wang, Jinhee Kim, Seokho Han, Denis Gudovskiy, Yohei Nakata, Tomoyuki Okuno, KhayTze Peong, Kang Eun Jeon, Jong Hwan Ko, Yiran Chen, Huanrui Yang

查看原文 →

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM · 相关技术

相关技术

LLM ODE PLA language model 远程代码执行（RCE）后训练 Token Resources Referring expression comprehension (REC)Parts-of-Speech (POS) tags LMM HIS For FFI DiT DAPT CIS ARG ANN