← Search

Kunlong Liu

2 accepted papers

2026

MemeBQ:Memory Efficient Binary Quantization of LLMs

AAAI 2026technical

Recent years have witnessed growing scholarly interest in binary post-training quantization (PTQ) techniques for large language models (LLMs). While state-of-the-art (SOTA) binary quantization methods significantly reduce memory footprint and computational demands, they introduce additional memory o

Cited by 0SourcePDFScholar
2026

Proteus: Lookup-Free Trellis-Coded Quantization by Lattice-Breaking Compute Codes for 2-Bit LLMs

ICML 2026poster

Autoregressive decoding of large language models is frequently memory-traffic bound, so ultra-low-bit weight-only PTQ helps only if dequantization avoids irregular codebook or LUT access in the inner loop. Under the GPU-friendly bitshift trellis, existing 2-bit trellis-coded quantization (TCQ) pipel…

Cited by 0SourceScholar