Jul 2026
BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression
BiSCo-LLM is presented, a codebook-free binary spherical coding framework for extreme low-bit LLM weight compression and its reported storage budget includes binary codes, neural decoders, protected-channel payloads, LoRA adapters, and metadata.
Yuantian Shao, Peisong Wang, Zhilei Liu et al.
· arXiv.org · 0 citations