HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs
NeurIPSSpotlight2025
TL;DR
We introduce HBLLM, a wavelet-enhanced high-fidelity $1$-bit post-training quantization method for Large Language Models (LLMs)
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
large language model language model quantization llm
← All NeurIPS 2025 Spotlight papers · Browse the whole archive